Research

New papers ranked by attention, with their code, models and discussion linked. Pick a field on the left.

Week Month Quarter All

Newest Most relevant

Papers

Research

New papers ranked by attention, with their code, models and discussion linked. Pick a field on the left.

Week Month Quarter All

Newest Most relevant

Papers

arXiv cs.LGSep 28
ZeroCode: On-demand Error-Correcting Code Construction from the Zero Matrix via Reinforcement Learning
Ju-Hyeong Lee, Yongjune Kim, Sang-Hyo Kim, Dae-Young Yun, Hee-Youl Kwak
Error-correcting codes (ECCs) are essential across diverse applications, from wireless communications and storage to quantum computing, yet each application imposes distinct design requirements on the parity-check matrix (PCM). To address these on-demand requirements in a unified framework, we propose ZeroCode, a reinforcement learning (RL)-based approach that constructs PCMs sequentially from the all-zero matrix. ZeroCode formulates construction as a discrete sequential decision-making problem and uses proximal policy optimization with action masking to select valid edges. ZeroCode achieves a gain of approximately 1 dB over the prior RL-based construction method at a bit error rate (BER) of $10^{-4}$ for the (32,16) code and outperforms existing genetic, differentiable, and classical code-design methods in our experiments. Beyond optimizing decoding performance, the masking mechanism allows on-demand structural constraints, such as a maximum degree, 4-cycle-free structure, and quasi-cyclic structure, to be flexibly incorporated. Moreover, a single policy rollout yields a library of PCMs with varying edge counts, offering trade-offs between decoding performance and complexity…
PDF
arXiv cs.LGSep 28
Rotated Manifold Optimization for Low-Rank Adaptation
Yuhui Ding, Javier Zazo, James Hensman
We propose a novel optimizer for low-rank adaptation (LoRA) that explicitly incorporates the gauge symmetry of low-rank factorization. Our optimizer extends recent matrix optimizers for full-parameter training to the manifold of fixed-rank matrices by interpreting them as normalization under a rotated basis. We show how rotation and normalization can be integrated with the fixed-rank manifold efficiently. Our optimizer converges faster to lower held-out loss and achieves better or comparable downstream performance on both supervised finetuning and reinforcement learning tasks.
PDF
arXiv cs.AISep 28
Maintaining Benchmarks Against Increasingly Capable Agents: Detection and Remediation of Unearned Passes
Weijun Luo, Kelvin Luu, Xinyi Liu, Guangze Luo, Miguel Romero Calvo +4
Agentic benchmarks guide model selection and training. Yet an agent can pass a task without demonstrating the intended capability. Such outcomes constitute unearned passes; their proportion among all passes defines the integrity gap. As agents improve, benchmark surfaces that once seemed harmless can become exploitable, making benchmark validity an ongoing maintenance problem. We introduce a process-verification framework that audits passing trajectories, distinguishes evidenced reward hacking from verifier weakness, and localizes exploitable surfaces for repair. Across 3,810 passing trajectories from 29 model-benchmark cohorts, confirmed violations often increase with model generation but not monotonically. On SWEBench Pro V1.0, confirmed violation rates rise from 24% to 73% between Opus 4.7 and Fable 5 on matched tasks; later cohorts fall to 11% for Fable 5.1 and 0% for GPT-6 Astra. These comparisons are descriptive: configurations were not normalized, and the latest models also pass fewer exploitable tasks. Violations concentrate around a small set of recurring surfaces, especially unintended access to reference solutions through git history. Three repair case studies across…
PDF
arXiv cs.ROSep 28
RoboICL: Embodied In-Context Learning with GPT-6 Astra
Fangcheng Liu, Yeqing Shen, Anda Cheng, Weishi Mi, Chao Tang +5
General-purpose vision-language models offer a promising way to zero-shot robot control: \gptastra{} excels at open-ended and language- or image-conditioned manipulation but remains substantially weaker on high-precision and long-horizon tasks. We introduce \emph{RoboICL}, an in-context robot-control framework that narrows these gaps without robot-specific parameter updates or a learned VLA. RoboICL separates \emph{demonstration context}, which provides recorded examples when available, from \emph{interaction memory}, which accumulates the model's own actions and observed outcomes. Both use a shared observation--action--receipt--observation grammar. To preserve experience across task stages, RoboICL combines sampled demonstration blocks with bounded anchored memory. Fixed anchors keep earlier rollout interactions available for in-context learning, while the latest interaction supports immediate error correction. Across 30 RoboDojo tasks, using zero shot for Open and one demonstration elsewhere, RoboICL improves on official zero-shot \gptastra{} by 20--27 progress-score points in every category. It leads the leaderboard baselines on Memory and Open, achieves comparable performance…
PDF
arXiv cs.AISep 28
QuantaSpike: Short-Window Spike-Driven Quantization for Large Language Models
Bang Hu, Guowei Zhu, Changze Lv, Xiaoqing Zheng, Fengzhe Zhang +2
Large language models (LLMs) achieve strong performance across many tasks but rely on dense multiply-accumulate (MAC) operations during inference, resulting in high energy cost. Spiking neural networks (SNNs) offer an event-driven alternative in which synaptic integration uses lightweight accumulation. However, spike-driven LLM inference remains difficult because outlier-heavy activations typically require long firing windows or auxiliary non-spiking paths. We propose QuantaSpike, a short-window spike-driven quantization framework for LLMs built around Logarithmic Ternary Integrate-and-Fire (LTIF) neurons. LTIF uses ternary events with power-of-two membrane-response quanta, improving the information represented by each firing step while retaining shift-ACC-compatible computation. QuantaSpike combines this neuron with group-adaptive gain and selective outlier admission: normal values use residual LTIF steps, whereas admitted outliers receive one additional onset spike before entering the same residual dynamics. Across OPT and Llama-2, QuantaSpike achieves state-of-the-art or competitive perplexity and zero-shot accuracy among spike-driven LLM quantization methods. It also…
PDF
arXiv cs.CYSep 28
Investigating Human--AI Discrepancies via Multiple-Solution Problems
Zihao Wang, Francesco Insulla, Andrea Montanari
Frontier artificial intelligence (AI) models are benchmarked on whether they reach a correct answer. Yet many problems admit several correct answers and repeated attempts, by different people or by the same model resampled, trace out a distribution over them. In this work, we ask whether human and model reasoning lead to different distributions over valid solutions. Our testbed comprises 270 reasoning puzzles across five puzzle families. These multiple-solution puzzles each have 3 to 8 valid solutions and are simple enough that humans and models can solve them reliably. The resulting distributions differ markedly: models differ from one another, yet resemble each other far more than they resemble humans. Model distributions are, moreover, within every puzzle family, less diverse than human ones. We compare these discrepancies across puzzle categories, and trace how they respond to reasoning-effort settings, to prompting, and to perturbations of the puzzle that leave its solutions unchanged. Together, these results point at significant differences between human and AI problem-solving processes, and their choice among equally defensible solutions. As progressive deployment of AI…
PDF
arXiv cs.CLSep 28
Recursive LLM Degradation in Biomedical Question Answering: A Cross-Generation Study
Bibek Bhandari, Kshitij Lingthep
Repeatedly training language models on their own generated data may create a synthetic-data feedback loop in which errors and distributional biases are reintroduced into subsequent training datasets. This paper studies that process in biomedical question answering (QA) using PubMedQA and two Qwen2.5 model sizes, 0.5B and 3B parameters. The study compares a recursive synthetic-data condition, in which generation G(k+1) is trained on answers produced by G(k), against a Human-Control condition that repeatedly uses the original human training data. The study evaluates across four generations from G0-G3 with two random seeds (42 and 123) and a fixed evaluation set of 1,000 expert-labeled samples. The evaluation includes disease and chemical entity F1, context-supported rate, lexical and semantic similarity, answer length, repetition rate, and other evaluation metrics. The Recursive condition for both model sizes and both seeds showed larger declines than the Human-Control condition in disease entity F1, chemical entity F1, context-supported rate, ROUGE-L, and cosine similarity. Under the fixed no-repeat 3-gram decoding constraint, the main observed behavioral change was increased…
PDF
arXiv cs.LGSep 28
DreamingGoose: Staged Distillation from Autoregressive Transformers to Bidirectional Recurrent Diffusion Language Models
Julian Boesch, Andrew Wee, Alexander Stranzl
Pretrained autoregressive Transformers represent a large sunk investment in compute. Existing conversion methods reuse that investment by changing either the architecture (attention to recurrence) or the objective (next-token prediction to denoising), never both. We convert Qwen3 teachers at 1.7B and 8B into attention-free, bidirectional, gated-delta-rule diffusion students in three stages, so that each capability can be traced to the stage that kept or lost it. Language modeling transfers only partially and in-distribution; in-context retrieval does not transfer. On a multi-query recall probe where the teachers score 0.34-0.58, both converted students score 0.000, and diffusion pretraining alone does not restore retrieval. A retrieval curriculum in the final stage, which gradually lengthens the gap between a key-value table and the queries that address it, restores it only stochastically: on a fixed schedule, one seed in three learns to retrieve. Advancing the gap only while a running accuracy estimate stays above a threshold works for all three of those seeds, holds on real text, and carries unchanged to 8B, where two of three seeds succeed. The third had not learned within its…
PDF
arXiv cs.ROSep 28
WAM-OPD: Sharpening World Action Models via On-Policy Distillation
Panjun Liu, Xiaohan Lei, Shiqi Zhang, Yikun Wang, Yongxin Zhang +6
Pretrained world action models (WAMs) provide generalist capabilities across diverse robotic manipulation tasks, yet improving target-task performance to an expert level without degrading pretrained skills remains challenging. We explore on-policy distillation (OPD) for WAMs and introduce WAM-OPD. WAM-OPD inherits the advantage of OPD methods that transfer task-specific teacher knowledge under the student's own induced distribution, rather than directly fitting the student to a narrow task-specific data distribution. However, in closed-loop manipulation, the observation histories change as the student policy evolves, requiring fresh environment rollouts to remain on-policy. Applying OPD to WAMs entails repeated data collection, which is costly even in simulation and often impractical on real robots. To avoid repeated environment rollouts during distillation, we introduce prefix-weighted trajectory replay (PWTR). PWTR uses a fixed trajectory pool composed primarily of initial-student rollouts, supplemented with task-specific teacher rollouts to broaden trajectory coverage. For each trajectory replayed from this pool, PWTR conditions the current policy on successive stored…
PDF
arXiv cs.AISep 28
Evolving Support Priorities in Empathetic Reinforcement Learning
Pengyu Huang, Zhiyuan Han, Wenwen Tong, Hewei Guo, Jiangnan Chen +4
We identify a fundamental mismatch in empathetic reinforcement learning: support priorities evolve with the dialogue state, yet existing methods typically optimize predefined reward specifications that remain fixed across turns. To model these evolving support priorities, we organize empathetic support along cognitive, affective, and proactive empathy, and propose Context-Adaptive Rubric Evolution (CARE). At each turn, CARE generates a context-adaptive rubric by adjusting both the weights of these three empathy dimensions and their fine-grained evaluation criteria. The rubric generator is trained with turn-level rubric supervision and human preference data through supervised fine-tuning followed by preference-based reinforcement learning, and then serves as an adaptive reward interface for online empathetic RL. Integrated with both RLVER and MICA, CARE achieves state-of-the-art performance across SentientBench, EQBench3, and EMPA under three independent LLM judges. Notably, on EMPA, CARE improves EPM-Idx over the strongest baseline by at least 13 points under all three judges, including an increase from 28.11 to 83.54 under Gemini-2.5-Pro. Further analyses show that learned…
PDF
arXiv cs.CLVoice AISep 28
SALMONN-duo: Adaptive Dual-System Coordination for Full-Duplex Voice Agents
Wenyi Yu, Siyin Wang, Terumi Chiba, Xianzhao Chen, Xiaohai Tian +3
Full-duplex speech large language models (LLMs) enable low-latency, natural voice interaction. However, real-world agents must also use tools and perform deliberative reasoning-operations whose variable latency and computational cost conflict with the stringent timing requirements of real-time conversation. To reconcile these demands, we propose SALMONN-duo, an adaptive dual-system voice agent inspired by dual-process theories of cognition. SALMONN-duo separates real-time interaction from deliberative computation by pairing an always-on, fast-thinking full-duplex speech LLM (system 1) with a powerful asynchronous slow-thinking LLM agent (system 2). Beyond handling real-time interaction, system 1 learns when to answer directly and when to delegate, remaining responsive during backend execution and seamlessly integrating returned information into the ongoing dialogue without exposing tool traces or losing conversational context. Evaluations on single-turn spoken question answering (QA) and multi-turn conversations demonstrate that adaptive delegation substantially improves accuracy on knowledge-intensive and multi-hop reasoning questions, while knowledge-boundary-aware training…
AIAgents90PDF
arXiv cs.LGSep 28
CasEm: A Cascade Architecture for Long-Horizon Neural Emulation
Zhaoyi Li, Jingtao Ding, Shihua Li
Autoregressive neural emulators can drift or diverge over long rollouts despite accurate short-term predictions. We introduce Cascaded Emulation (CasEm), a one-way rollout architecture that augments an existing full-state backbone with an independently evolving model of physically specified aggregates. Its forecasts guide corrections to full-state predictions, without feedback from the backbone to the aggregate model. Effective guidance requires aggregates that cover substantial backbone error, remain accurately predictable, and support useful full-state corrections. We derive a finite-horizon error bound that clarifies these three factors and use empirical diagnostics to guide subsystem selection. Across four ODE/PDE benchmarks, CasEm reduces long-horizon rollout errors across diverse backbones and suppresses the trend toward error divergence in both diffusion tasks using Fourier neural operator backbones. In global climate emulation, CasEm with a regional total-water subsystem reduces 10-year full-state time-mean error by 66.6% and 46.3% for frozen ACE and Spherical DYffusion backbones, respectively, while adding less than 3% to inference time.
PDF
arXiv cs.CRSep 28
Certified Multi-Source Integrity for Structured Agent Actions
Anmol Pandey, Aditya Jain, Liang Chen, Carsten Maple, Christo Panchev
LLM agents increasingly take privileged, often irreversible structured actions, such as paying an invoice. They assemble each action from action-critical fields in documents and tool outputs that an adversary can corrupt, and indirect prompt injection can drive the model itself to extract attacker-chosen values. Current defenses gate on a source's trust label or certify free-text answer quality. None certifies the integrity of a coupled, policy-bound structured action under a corruption budget that accounts for shared upstream sources. We characterize when such an action is safely certifiable and give the maximally live safe certifier. It admits an action only when each field clears the rule its evidence structure supports: a bounded corruption radius over corruption-distinct evidence classes, counted by a minimum hitting set so that re-publishing or laundered copies cannot manufacture a quorum, deterministic reconciliation for complementary fields, and a trusted anchor where the evidence leaves a field single-sourced. We formalize two robustness notions, validate each mechanism by ablation, and measure how often the multi-source precondition holds on sanctions designations…
PDF
arXiv cs.AIAgentsSep 28
Stashbird: Efficient Speaker-Indexed Memory for Conversational Agents
Chidera Biringa, Lucas Yannul, Xiaowen Wang, Marco Ayala, Nicholas Yi +3
AI agents require memory that preserves information across user-agent exchanges, user-to-user conversations, and group conversations with or without agent participation, while supporting updates as evidence changes or is removed. We present Stashbird, an agent memory system that links source episodes to derived memory state through explicit provenance. Stashbird organizes memory into episodic records, semantic relations, community summaries, and persisted graph state, with lifecycle operations for incremental updates and episode-level deletion. We evaluate question-answering accuracy and model-facing workload across four long-term memory benchmarks. On LoCoMo, Stashbird uses 76.4x fewer ingestion prompt tokens than Graphiti. Compared with reproduced Hindsight on the same benchmark, it uses 8.1x fewer retrieval prompt tokens, with accuracy 1.6 percentage points lower. It achieves higher accuracy than Hindsight on LongMemEval-S and GroupMemBench and comparable accuracy on EverMemBench.
AIEvals80PDF
arXiv cs.AISep 28
AdaGuard: An Adaptive Guard Model with User-defined Policies
Yunhao Feng, Yifan Ding, Yuxiang Xie, Zheng Li, Mingrui Lao +2
Guard models support the safe deployment of language model agents, but fixed risk taxonomies limit their ability to accommodate requirements that vary across applications and tasks. Under user-defined policies, detecting violations requires interpreting both the applicable rules and the agent's behavior, since identical actions can receive different judgments under different policies. To support learning this capability, we introduce AdaptiveSafety, a dataset of 10,939 training examples and 1,000 test examples covering policies with 1--100 rules. The dataset combines trajectories from multiple sources with policy and behavioral counterfactuals, pairing each example with an explanation and the complete set of violated rules. These counterfactuals expose changes that alter compliance, while structural augmentations provide supervision for consistency under rule reordering and identifier remapping. Building on this supervision, we propose SafePO, a reinforcement learning algorithm for refining violation identification while balancing explanatory reasoning and final verdicts. SafePO uses structured rewards to assess prediction correctness, retains group-relative advantages at the…
PDF
arXiv cs.CLSep 28
Coherence-Aware Distributional Evaluation of Open-Ended Text Generation
Jinnuo Liu, Junhao Zhu, Weifeng Jiang, Haoming Liu, Hongyi Wen
Existing open-ended generation metrics measure likelihood, lexical diversity, or distributional similarity in generic representation space, yet can miss fundamental dimensions of quality. A prominent blind spot is global coherence: a generated passage may be locally fluent while remaining globally contradictory, causally inconsistent, or topically disconnected. We identify representation as a central bottleneck in detecting these failures and introduce CHORD (Coherence-aware Hidden-state Open-generation Reference Distance), a coherence-sensitive distributional metric. CHORD encodes generated and human-written corpora in the hidden-state space of a frozen LLM using a coherence-eliciting prompt, and compares the resulting distributions using RBF-MMD. To test coherence sensitivity and selectivity, we construct a counterfactual evaluation suite pairing graded coherence-degrading perturbations with meaning-preserving controls. CHORD selectively detects relation, discourse, structural, and mixture failures that perplexity, entropy, MAUVE, FBD, and MMD-based baselines either miss or cannot separate from benign rewriting. Factorial ablations show that representation is the primary source…
PDF
arXiv cs.CVSep 28
DecFlowEdit: Self-Localized Flow-based Image Editing via Guidance Decoupling
Zheyuan Zhan, Can Wang, Jiawei Chen, Chun Chen, Siwei Lyu +2
Flow-based image editing (FlowEdit) enables inversion-free semantic changes through the difference between source and target velocities. In this paper, we observe that FlowEdit's default classifier-free guidance (CFG) configuration, with asymmetric source and target scales, causes substantial background leakage. Matching these guidance scales, for example by removing CFG, improves edit-relevant localization but severely degrades editability. To get the best of both worlds, we propose DecFlowEdit, which decouples the optimal guidance scales for localization and for editing in flow-based generative models. In particular, DecFlowEdit first extracts an edit-relevant prior by temporally aggregating velocity differences evaluated without CFG, and then uses this prior to reweight the original updates under default CFG. Our method remains training-free and inversion-free, requiring neither external spatial masks nor attention manipulation. Experiments on PIE-Bench across FLUX, SD3, and SD3.5 show that DecFlowEdit improves background preservation, reducing structure distance by approximately 61 to 73 percent and background LPIPS by 68 to 80 percent relative to FlowEdit at comparable…
PDF
arXiv cs.CVSep 28
SegBanana: Steering Unified Multimodal Models into Medical Segmenters
Xiaoye Liang, Ye Yan, Mingze Yin, Shikun Feng, Mai Xu +3
Medical image segmentation remains challenging in practical deployment, as models often struggle to generalize beyond the distributions covered by their training data and high-quality pixel-level annotations are typically unavailable for adaptation. Inspired by the cross-task transferability of large language models, we investigate whether unified multimodal models (UMMs) can transfer their pretrained visual understanding, reasoning, and generation capabilities to medical image segmentation without task-specific post-training. By recasting segmentation as structured visual generation, we find that frontier UMMs (e.g., Nano Banana) already exhibit basic segmentation capabilities across diverse clinical scenarios, but still struggle with challenging tasks requiring specialized anatomical or domain-specific knowledge. We further show that these limitations can be effectively mitigated by incorporating visual anatomical knowledge from in-context exemplars, expanding candidate solutions through repeated sampling, and refining suboptimal predictions via targeted editing.Motivated by these observations, we propose SegBanana, to our knowledge, the first agentic visual generation…
PDF
arXiv cs.CLSep 28
MAS-OPD: On-Policy Distillation for Multi-agent Systems
Qiyong Zhong, Mao Zheng, Mingyang Song, Houcheng Jiang, Jiajie Su +3
Multi-agent systems (MAS) split a task across specialized roles and are promising on complex tasks, yet a prevailing approach relies on inference-time orchestration alone. General-purpose APIs are costly and hard to customize, while small models with role prompts rarely develop stable role competence or reliable collaboration, so post-training a MAS jointly is central. Most attempts use reinforcement learning, whose team-level reward leaves undetermined which step of which agent brought about the outcome, while local rewards need redesigning per task. On-policy distillation (OPD) gives token-level teacher supervision on trajectories the student samples, a denser signal needing no local reward, yet is underexplored for the interdependent agents of a MAS. Two difficulties arise: building complementary specialization from a judgement of which role a behavior belongs to while preserving the knowledge all roles need, and turning cross-agent collaborative information into supervision OPD can exploit. We present MAS-OPD, where Role-Advantage Specialization defines the role advantage as the difference between the teacher signals under target and non-target role conditions, and Privileged…
PDF
arXiv cs.CVSep 28
Trustworthy synthetic visual media: Evidence across the media lifecycle
Zexi Jia, Zhiqiang Yuan, Jie Zhou, Jinchao Zhang
Images and videos have long helped people understand what happened and how a work came into being. Generative systems complicate that role. Realistic media can now be produced and revised without leaving a stable history, so appearance no longer reveals whether a scene was captured, synthesized, or altered along the way. Trust must instead come from evidence that explains the path an asset has taken and the circumstances in which it was used. Some of this evidence can be recovered from the media, while some must be recorded during production and preserved as the asset circulates. This review brings those approaches together and asks when their claims remain meaningful after ordinary processing or deliberate manipulation. We argue that trustworthy media do not depend on one universal marker of authenticity. The evidence must suit the question at hand, reach the person making the judgment, and remain open to correction when better information emerges. The larger goal is to keep the history of media intelligible even as the media itself continues to change.
PDF

Papers

arXiv cs.LGSep 28
ZeroCode: On-demand Error-Correcting Code Construction from the Zero Matrix via Reinforcement Learning
Ju-Hyeong Lee, Yongjune Kim, Sang-Hyo Kim, Dae-Young Yun, Hee-Youl Kwak
Error-correcting codes (ECCs) are essential across diverse applications, from wireless communications and storage to quantum computing, yet each application imposes distinct design requirements on the parity-check matrix (PCM). To address these on-demand requirements in a unified framework, we propose ZeroCode, a reinforcement learning (RL)-based approach that constructs PCMs sequentially from the all-zero matrix. ZeroCode formulates construction as a discrete sequential decision-making problem and uses proximal policy optimization with action masking to select valid edges. ZeroCode achieves a gain of approximately 1 dB over the prior RL-based construction method at a bit error rate (BER) of $10^{-4}$ for the (32,16) code and outperforms existing genetic, differentiable, and classical code-design methods in our experiments. Beyond optimizing decoding performance, the masking mechanism allows on-demand structural constraints, such as a maximum degree, 4-cycle-free structure, and quasi-cyclic structure, to be flexibly incorporated. Moreover, a single policy rollout yields a library of PCMs with varying edge counts, offering trade-offs between decoding performance and complexity…
PDF
arXiv cs.LGSep 28
Rotated Manifold Optimization for Low-Rank Adaptation
Yuhui Ding, Javier Zazo, James Hensman
We propose a novel optimizer for low-rank adaptation (LoRA) that explicitly incorporates the gauge symmetry of low-rank factorization. Our optimizer extends recent matrix optimizers for full-parameter training to the manifold of fixed-rank matrices by interpreting them as normalization under a rotated basis. We show how rotation and normalization can be integrated with the fixed-rank manifold efficiently. Our optimizer converges faster to lower held-out loss and achieves better or comparable downstream performance on both supervised finetuning and reinforcement learning tasks.
PDF
arXiv cs.AISep 28
Maintaining Benchmarks Against Increasingly Capable Agents: Detection and Remediation of Unearned Passes
Weijun Luo, Kelvin Luu, Xinyi Liu, Guangze Luo, Miguel Romero Calvo +4
Agentic benchmarks guide model selection and training. Yet an agent can pass a task without demonstrating the intended capability. Such outcomes constitute unearned passes; their proportion among all passes defines the integrity gap. As agents improve, benchmark surfaces that once seemed harmless can become exploitable, making benchmark validity an ongoing maintenance problem. We introduce a process-verification framework that audits passing trajectories, distinguishes evidenced reward hacking from verifier weakness, and localizes exploitable surfaces for repair. Across 3,810 passing trajectories from 29 model-benchmark cohorts, confirmed violations often increase with model generation but not monotonically. On SWEBench Pro V1.0, confirmed violation rates rise from 24% to 73% between Opus 4.7 and Fable 5 on matched tasks; later cohorts fall to 11% for Fable 5.1 and 0% for GPT-6 Astra. These comparisons are descriptive: configurations were not normalized, and the latest models also pass fewer exploitable tasks. Violations concentrate around a small set of recurring surfaces, especially unintended access to reference solutions through git history. Three repair case studies across…
PDF
arXiv cs.ROSep 28
RoboICL: Embodied In-Context Learning with GPT-6 Astra
Fangcheng Liu, Yeqing Shen, Anda Cheng, Weishi Mi, Chao Tang +5
General-purpose vision-language models offer a promising way to zero-shot robot control: \gptastra{} excels at open-ended and language- or image-conditioned manipulation but remains substantially weaker on high-precision and long-horizon tasks. We introduce \emph{RoboICL}, an in-context robot-control framework that narrows these gaps without robot-specific parameter updates or a learned VLA. RoboICL separates \emph{demonstration context}, which provides recorded examples when available, from \emph{interaction memory}, which accumulates the model's own actions and observed outcomes. Both use a shared observation--action--receipt--observation grammar. To preserve experience across task stages, RoboICL combines sampled demonstration blocks with bounded anchored memory. Fixed anchors keep earlier rollout interactions available for in-context learning, while the latest interaction supports immediate error correction. Across 30 RoboDojo tasks, using zero shot for Open and one demonstration elsewhere, RoboICL improves on official zero-shot \gptastra{} by 20--27 progress-score points in every category. It leads the leaderboard baselines on Memory and Open, achieves comparable performance…
PDF
arXiv cs.AISep 28
QuantaSpike: Short-Window Spike-Driven Quantization for Large Language Models
Bang Hu, Guowei Zhu, Changze Lv, Xiaoqing Zheng, Fengzhe Zhang +2
Large language models (LLMs) achieve strong performance across many tasks but rely on dense multiply-accumulate (MAC) operations during inference, resulting in high energy cost. Spiking neural networks (SNNs) offer an event-driven alternative in which synaptic integration uses lightweight accumulation. However, spike-driven LLM inference remains difficult because outlier-heavy activations typically require long firing windows or auxiliary non-spiking paths. We propose QuantaSpike, a short-window spike-driven quantization framework for LLMs built around Logarithmic Ternary Integrate-and-Fire (LTIF) neurons. LTIF uses ternary events with power-of-two membrane-response quanta, improving the information represented by each firing step while retaining shift-ACC-compatible computation. QuantaSpike combines this neuron with group-adaptive gain and selective outlier admission: normal values use residual LTIF steps, whereas admitted outliers receive one additional onset spike before entering the same residual dynamics. Across OPT and Llama-2, QuantaSpike achieves state-of-the-art or competitive perplexity and zero-shot accuracy among spike-driven LLM quantization methods. It also…
PDF
arXiv cs.CYSep 28
Investigating Human--AI Discrepancies via Multiple-Solution Problems
Zihao Wang, Francesco Insulla, Andrea Montanari
Frontier artificial intelligence (AI) models are benchmarked on whether they reach a correct answer. Yet many problems admit several correct answers and repeated attempts, by different people or by the same model resampled, trace out a distribution over them. In this work, we ask whether human and model reasoning lead to different distributions over valid solutions. Our testbed comprises 270 reasoning puzzles across five puzzle families. These multiple-solution puzzles each have 3 to 8 valid solutions and are simple enough that humans and models can solve them reliably. The resulting distributions differ markedly: models differ from one another, yet resemble each other far more than they resemble humans. Model distributions are, moreover, within every puzzle family, less diverse than human ones. We compare these discrepancies across puzzle categories, and trace how they respond to reasoning-effort settings, to prompting, and to perturbations of the puzzle that leave its solutions unchanged. Together, these results point at significant differences between human and AI problem-solving processes, and their choice among equally defensible solutions. As progressive deployment of AI…
PDF
arXiv cs.CLSep 28
Recursive LLM Degradation in Biomedical Question Answering: A Cross-Generation Study
Bibek Bhandari, Kshitij Lingthep
Repeatedly training language models on their own generated data may create a synthetic-data feedback loop in which errors and distributional biases are reintroduced into subsequent training datasets. This paper studies that process in biomedical question answering (QA) using PubMedQA and two Qwen2.5 model sizes, 0.5B and 3B parameters. The study compares a recursive synthetic-data condition, in which generation G(k+1) is trained on answers produced by G(k), against a Human-Control condition that repeatedly uses the original human training data. The study evaluates across four generations from G0-G3 with two random seeds (42 and 123) and a fixed evaluation set of 1,000 expert-labeled samples. The evaluation includes disease and chemical entity F1, context-supported rate, lexical and semantic similarity, answer length, repetition rate, and other evaluation metrics. The Recursive condition for both model sizes and both seeds showed larger declines than the Human-Control condition in disease entity F1, chemical entity F1, context-supported rate, ROUGE-L, and cosine similarity. Under the fixed no-repeat 3-gram decoding constraint, the main observed behavioral change was increased…
PDF
arXiv cs.LGSep 28
DreamingGoose: Staged Distillation from Autoregressive Transformers to Bidirectional Recurrent Diffusion Language Models
Julian Boesch, Andrew Wee, Alexander Stranzl
Pretrained autoregressive Transformers represent a large sunk investment in compute. Existing conversion methods reuse that investment by changing either the architecture (attention to recurrence) or the objective (next-token prediction to denoising), never both. We convert Qwen3 teachers at 1.7B and 8B into attention-free, bidirectional, gated-delta-rule diffusion students in three stages, so that each capability can be traced to the stage that kept or lost it. Language modeling transfers only partially and in-distribution; in-context retrieval does not transfer. On a multi-query recall probe where the teachers score 0.34-0.58, both converted students score 0.000, and diffusion pretraining alone does not restore retrieval. A retrieval curriculum in the final stage, which gradually lengthens the gap between a key-value table and the queries that address it, restores it only stochastically: on a fixed schedule, one seed in three learns to retrieve. Advancing the gap only while a running accuracy estimate stays above a threshold works for all three of those seeds, holds on real text, and carries unchanged to 8B, where two of three seeds succeed. The third had not learned within its…
PDF
arXiv cs.ROSep 28
WAM-OPD: Sharpening World Action Models via On-Policy Distillation
Panjun Liu, Xiaohan Lei, Shiqi Zhang, Yikun Wang, Yongxin Zhang +6
Pretrained world action models (WAMs) provide generalist capabilities across diverse robotic manipulation tasks, yet improving target-task performance to an expert level without degrading pretrained skills remains challenging. We explore on-policy distillation (OPD) for WAMs and introduce WAM-OPD. WAM-OPD inherits the advantage of OPD methods that transfer task-specific teacher knowledge under the student's own induced distribution, rather than directly fitting the student to a narrow task-specific data distribution. However, in closed-loop manipulation, the observation histories change as the student policy evolves, requiring fresh environment rollouts to remain on-policy. Applying OPD to WAMs entails repeated data collection, which is costly even in simulation and often impractical on real robots. To avoid repeated environment rollouts during distillation, we introduce prefix-weighted trajectory replay (PWTR). PWTR uses a fixed trajectory pool composed primarily of initial-student rollouts, supplemented with task-specific teacher rollouts to broaden trajectory coverage. For each trajectory replayed from this pool, PWTR conditions the current policy on successive stored…
PDF
arXiv cs.AISep 28
Evolving Support Priorities in Empathetic Reinforcement Learning
Pengyu Huang, Zhiyuan Han, Wenwen Tong, Hewei Guo, Jiangnan Chen +4
We identify a fundamental mismatch in empathetic reinforcement learning: support priorities evolve with the dialogue state, yet existing methods typically optimize predefined reward specifications that remain fixed across turns. To model these evolving support priorities, we organize empathetic support along cognitive, affective, and proactive empathy, and propose Context-Adaptive Rubric Evolution (CARE). At each turn, CARE generates a context-adaptive rubric by adjusting both the weights of these three empathy dimensions and their fine-grained evaluation criteria. The rubric generator is trained with turn-level rubric supervision and human preference data through supervised fine-tuning followed by preference-based reinforcement learning, and then serves as an adaptive reward interface for online empathetic RL. Integrated with both RLVER and MICA, CARE achieves state-of-the-art performance across SentientBench, EQBench3, and EMPA under three independent LLM judges. Notably, on EMPA, CARE improves EPM-Idx over the strongest baseline by at least 13 points under all three judges, including an increase from 28.11 to 83.54 under Gemini-2.5-Pro. Further analyses show that learned…
PDF
arXiv cs.CLVoice AISep 28
SALMONN-duo: Adaptive Dual-System Coordination for Full-Duplex Voice Agents
Wenyi Yu, Siyin Wang, Terumi Chiba, Xianzhao Chen, Xiaohai Tian +3
Full-duplex speech large language models (LLMs) enable low-latency, natural voice interaction. However, real-world agents must also use tools and perform deliberative reasoning-operations whose variable latency and computational cost conflict with the stringent timing requirements of real-time conversation. To reconcile these demands, we propose SALMONN-duo, an adaptive dual-system voice agent inspired by dual-process theories of cognition. SALMONN-duo separates real-time interaction from deliberative computation by pairing an always-on, fast-thinking full-duplex speech LLM (system 1) with a powerful asynchronous slow-thinking LLM agent (system 2). Beyond handling real-time interaction, system 1 learns when to answer directly and when to delegate, remaining responsive during backend execution and seamlessly integrating returned information into the ongoing dialogue without exposing tool traces or losing conversational context. Evaluations on single-turn spoken question answering (QA) and multi-turn conversations demonstrate that adaptive delegation substantially improves accuracy on knowledge-intensive and multi-hop reasoning questions, while knowledge-boundary-aware training…
AIAgents90PDF
arXiv cs.LGSep 28
CasEm: A Cascade Architecture for Long-Horizon Neural Emulation
Zhaoyi Li, Jingtao Ding, Shihua Li
Autoregressive neural emulators can drift or diverge over long rollouts despite accurate short-term predictions. We introduce Cascaded Emulation (CasEm), a one-way rollout architecture that augments an existing full-state backbone with an independently evolving model of physically specified aggregates. Its forecasts guide corrections to full-state predictions, without feedback from the backbone to the aggregate model. Effective guidance requires aggregates that cover substantial backbone error, remain accurately predictable, and support useful full-state corrections. We derive a finite-horizon error bound that clarifies these three factors and use empirical diagnostics to guide subsystem selection. Across four ODE/PDE benchmarks, CasEm reduces long-horizon rollout errors across diverse backbones and suppresses the trend toward error divergence in both diffusion tasks using Fourier neural operator backbones. In global climate emulation, CasEm with a regional total-water subsystem reduces 10-year full-state time-mean error by 66.6% and 46.3% for frozen ACE and Spherical DYffusion backbones, respectively, while adding less than 3% to inference time.
PDF
arXiv cs.CRSep 28
Certified Multi-Source Integrity for Structured Agent Actions
Anmol Pandey, Aditya Jain, Liang Chen, Carsten Maple, Christo Panchev
LLM agents increasingly take privileged, often irreversible structured actions, such as paying an invoice. They assemble each action from action-critical fields in documents and tool outputs that an adversary can corrupt, and indirect prompt injection can drive the model itself to extract attacker-chosen values. Current defenses gate on a source's trust label or certify free-text answer quality. None certifies the integrity of a coupled, policy-bound structured action under a corruption budget that accounts for shared upstream sources. We characterize when such an action is safely certifiable and give the maximally live safe certifier. It admits an action only when each field clears the rule its evidence structure supports: a bounded corruption radius over corruption-distinct evidence classes, counted by a minimum hitting set so that re-publishing or laundered copies cannot manufacture a quorum, deterministic reconciliation for complementary fields, and a trusted anchor where the evidence leaves a field single-sourced. We formalize two robustness notions, validate each mechanism by ablation, and measure how often the multi-source precondition holds on sanctions designations…
PDF
arXiv cs.AIAgentsSep 28
Stashbird: Efficient Speaker-Indexed Memory for Conversational Agents
Chidera Biringa, Lucas Yannul, Xiaowen Wang, Marco Ayala, Nicholas Yi +3
AI agents require memory that preserves information across user-agent exchanges, user-to-user conversations, and group conversations with or without agent participation, while supporting updates as evidence changes or is removed. We present Stashbird, an agent memory system that links source episodes to derived memory state through explicit provenance. Stashbird organizes memory into episodic records, semantic relations, community summaries, and persisted graph state, with lifecycle operations for incremental updates and episode-level deletion. We evaluate question-answering accuracy and model-facing workload across four long-term memory benchmarks. On LoCoMo, Stashbird uses 76.4x fewer ingestion prompt tokens than Graphiti. Compared with reproduced Hindsight on the same benchmark, it uses 8.1x fewer retrieval prompt tokens, with accuracy 1.6 percentage points lower. It achieves higher accuracy than Hindsight on LongMemEval-S and GroupMemBench and comparable accuracy on EverMemBench.
AIEvals80PDF
arXiv cs.AISep 28
AdaGuard: An Adaptive Guard Model with User-defined Policies
Yunhao Feng, Yifan Ding, Yuxiang Xie, Zheng Li, Mingrui Lao +2
Guard models support the safe deployment of language model agents, but fixed risk taxonomies limit their ability to accommodate requirements that vary across applications and tasks. Under user-defined policies, detecting violations requires interpreting both the applicable rules and the agent's behavior, since identical actions can receive different judgments under different policies. To support learning this capability, we introduce AdaptiveSafety, a dataset of 10,939 training examples and 1,000 test examples covering policies with 1--100 rules. The dataset combines trajectories from multiple sources with policy and behavioral counterfactuals, pairing each example with an explanation and the complete set of violated rules. These counterfactuals expose changes that alter compliance, while structural augmentations provide supervision for consistency under rule reordering and identifier remapping. Building on this supervision, we propose SafePO, a reinforcement learning algorithm for refining violation identification while balancing explanatory reasoning and final verdicts. SafePO uses structured rewards to assess prediction correctness, retains group-relative advantages at the…
PDF
arXiv cs.CLSep 28
Coherence-Aware Distributional Evaluation of Open-Ended Text Generation
Jinnuo Liu, Junhao Zhu, Weifeng Jiang, Haoming Liu, Hongyi Wen
Existing open-ended generation metrics measure likelihood, lexical diversity, or distributional similarity in generic representation space, yet can miss fundamental dimensions of quality. A prominent blind spot is global coherence: a generated passage may be locally fluent while remaining globally contradictory, causally inconsistent, or topically disconnected. We identify representation as a central bottleneck in detecting these failures and introduce CHORD (Coherence-aware Hidden-state Open-generation Reference Distance), a coherence-sensitive distributional metric. CHORD encodes generated and human-written corpora in the hidden-state space of a frozen LLM using a coherence-eliciting prompt, and compares the resulting distributions using RBF-MMD. To test coherence sensitivity and selectivity, we construct a counterfactual evaluation suite pairing graded coherence-degrading perturbations with meaning-preserving controls. CHORD selectively detects relation, discourse, structural, and mixture failures that perplexity, entropy, MAUVE, FBD, and MMD-based baselines either miss or cannot separate from benign rewriting. Factorial ablations show that representation is the primary source…
PDF
arXiv cs.CVSep 28
DecFlowEdit: Self-Localized Flow-based Image Editing via Guidance Decoupling
Zheyuan Zhan, Can Wang, Jiawei Chen, Chun Chen, Siwei Lyu +2
Flow-based image editing (FlowEdit) enables inversion-free semantic changes through the difference between source and target velocities. In this paper, we observe that FlowEdit's default classifier-free guidance (CFG) configuration, with asymmetric source and target scales, causes substantial background leakage. Matching these guidance scales, for example by removing CFG, improves edit-relevant localization but severely degrades editability. To get the best of both worlds, we propose DecFlowEdit, which decouples the optimal guidance scales for localization and for editing in flow-based generative models. In particular, DecFlowEdit first extracts an edit-relevant prior by temporally aggregating velocity differences evaluated without CFG, and then uses this prior to reweight the original updates under default CFG. Our method remains training-free and inversion-free, requiring neither external spatial masks nor attention manipulation. Experiments on PIE-Bench across FLUX, SD3, and SD3.5 show that DecFlowEdit improves background preservation, reducing structure distance by approximately 61 to 73 percent and background LPIPS by 68 to 80 percent relative to FlowEdit at comparable…
PDF
arXiv cs.CVSep 28
SegBanana: Steering Unified Multimodal Models into Medical Segmenters
Xiaoye Liang, Ye Yan, Mingze Yin, Shikun Feng, Mai Xu +3
Medical image segmentation remains challenging in practical deployment, as models often struggle to generalize beyond the distributions covered by their training data and high-quality pixel-level annotations are typically unavailable for adaptation. Inspired by the cross-task transferability of large language models, we investigate whether unified multimodal models (UMMs) can transfer their pretrained visual understanding, reasoning, and generation capabilities to medical image segmentation without task-specific post-training. By recasting segmentation as structured visual generation, we find that frontier UMMs (e.g., Nano Banana) already exhibit basic segmentation capabilities across diverse clinical scenarios, but still struggle with challenging tasks requiring specialized anatomical or domain-specific knowledge. We further show that these limitations can be effectively mitigated by incorporating visual anatomical knowledge from in-context exemplars, expanding candidate solutions through repeated sampling, and refining suboptimal predictions via targeted editing.Motivated by these observations, we propose SegBanana, to our knowledge, the first agentic visual generation…
PDF
arXiv cs.CLSep 28
MAS-OPD: On-Policy Distillation for Multi-agent Systems
Qiyong Zhong, Mao Zheng, Mingyang Song, Houcheng Jiang, Jiajie Su +3
Multi-agent systems (MAS) split a task across specialized roles and are promising on complex tasks, yet a prevailing approach relies on inference-time orchestration alone. General-purpose APIs are costly and hard to customize, while small models with role prompts rarely develop stable role competence or reliable collaboration, so post-training a MAS jointly is central. Most attempts use reinforcement learning, whose team-level reward leaves undetermined which step of which agent brought about the outcome, while local rewards need redesigning per task. On-policy distillation (OPD) gives token-level teacher supervision on trajectories the student samples, a denser signal needing no local reward, yet is underexplored for the interdependent agents of a MAS. Two difficulties arise: building complementary specialization from a judgement of which role a behavior belongs to while preserving the knowledge all roles need, and turning cross-agent collaborative information into supervision OPD can exploit. We present MAS-OPD, where Role-Advantage Specialization defines the role advantage as the difference between the teacher signals under target and non-target role conditions, and Privileged…
PDF
arXiv cs.CVSep 28
Trustworthy synthetic visual media: Evidence across the media lifecycle
Zexi Jia, Zhiqiang Yuan, Jie Zhou, Jinchao Zhang
Images and videos have long helped people understand what happened and how a work came into being. Generative systems complicate that role. Realistic media can now be produced and revised without leaving a stable history, so appearance no longer reveals whether a scene was captured, synthesized, or altered along the way. Trust must instead come from evidence that explains the path an asset has taken and the circumstances in which it was used. Some of this evidence can be recovered from the media, while some must be recorded during production and preserved as the asset circulates. This review brings those approaches together and asks when their claims remain meaningful after ordinary processing or deliberate manipulation. We argue that trustworthy media do not depend on one universal marker of authenticity. The evidence must suit the question at hand, reach the person making the judgment, and remain open to correction when better information emerges. The larger goal is to keep the history of media intelligible even as the media itself continues to change.
PDF