Research

• Dynamic model and policy routing for general-purpose AI1 paper raises it · 1 addresses it

  Orchestrating heterogeneous models and tools efficiently while balancing quality and cost remains unsolved for AGI-scale systems.

  • Route Anything: A Study of Model and Policy Routing for General-Purpose AI Systemsraises · addresses
• Cross-repository consistency in multi-repo software development1 paper raises it · 0 address it

  Agents fail to maintain consistency across interdependent repositories, a critical gap for real-world software engineering.

  • CrossSWE: Benchmarking Cross-Repository Joint Development for Coding Agentsraises
• Long-video generation with consistent appearance and motion1 paper raises it · 1 addresses it

  Chunk-wise methods degrade quality and cause drift over long rollouts, limiting real-time streaming video generation.

  • Wave Forcing: Towards Speed-of-Light Streaming Video Generationraises · addresses
• Local decision-making for reasoning compression1 paper raises it · 1 addresses it

  Existing methods reduce chain-of-thought length without addressing when to stop reasoning, leading to inefficiency or overthinking.

  • Think Less, Locally: Local Preference Learning for Reasoning Compressionraises · addresses
• Topological pathologies in physics-informed neural networks1 paper raises it · 1 addresses it

  Vanilla PINNs fail on problems with holes, punctures, or discontinuous interfaces due to path dependence and non-exact forms.

  • De Rham cohomological architectures for PINNs and PDEs with topological holesraises · addresses

Named by an AI from these papers' abstracts.

• arXiv cs.LGOct 4

  Software World Models: From Consequence Prediction to Decision Value

  Tongli Su, Yuntong Hu, Liang Zhao, Bowen Zhu, JayaSai Somasundaram +1

  A coding agent may safely modify one repository while silently breaking downstream services, libraries, or datastores that depend on it. Exhaustively running integration tests after every agent action is impractical, so the agent must predict these failures before executing them. Existing software world models predict the agent's own observations, while static change-impact analysis only identifies where a change may propagate. We instead introduce the Software World Model (SWM), which models the broader system affected by a code change and predicts its blast set: the components that the change will break. SWM follows three stages: explore, learn, and act. Explore executes candidate changes from restored system states, prioritizing regions where observed failures contradict the dependency graph. Learn fine-tunes a language model on these execution outcomes to predict downstream breakage. Act converts sampled predictions into per-consumer break probabilities for change ranking, proactive migration, and deciding when another execution is worth its cost. On held-out synthetic systems, SWM improves blast-set F1 from 0.431 for static reachability to $0.571\pm0.037$, more than halves…

  PDF

  Summarize this
• arXiv cs.LGOct 4

  A Graph-Based Inspection and Intervention Tool for Assessing Mechanistic Learning in PINNs

  Adwait Patkhedkar, Alifaraz Lakhani, Prathmesh Mohite, Abhijeet Salunke

  We ask whether physically meaningful correspondences discovered inside a trained scientific model remain meaningful outside the conditions under which they were discovered. We introduce GIIT (Graph-based Inspection and Intervention Tool), which represents governing physics as a computational physics dependency graph, maps graph nodes to internal network components via sensitivity- and trend-based discovery, and tests the resulting mapping under targeted intervention. Evaluating on temporal extrapolation out-of-distribution (OOD) regimes of increasing severity, we find that temporal extrapolation is associated with layer-wise correspondence drift and reduced functional correspondence. Specifically, while the model achieves low physics residual in-distribution (1.915 x 10-4 on full ID and 1.01 x 10-4 on an ID sub-window t in [0.5, 0.8]), the functional mapping changes even before leaving the training domain, and the shift continues as the evaluation window extends beyond the training domain: residual error increases from 2.81 x 10-2 on the boundary-crossing window (t in [0.5, 1.5]) to 3.30 x 10-1 on severe OOD (t in [1, 2]), accompanied by a systematic leftward shift of internal…

  PDF

  Summarize this
• arXiv cs.LGOct 4

  D-DOIT: Training-free Adaptation of Discrete Diffusion via Doob's h-Transform

  Jieke Wu, Qijie Zhu, Weimin Wu, Zeqi Ye, Minshuo Chen +1

  We propose D-DOIT (Discrete Doob-Oriented Inference-time Transformation), a training-free and efficient adaptation method for discrete diffusion models with generic rewards. D-DOIT formulates adaptation as sampling from a reward-tilted target distribution and realizes this transport through Doob's h-transform of the discrete diffusion reverse kernel, using only reward values rather than reward gradients. Unlike continuous diffusion, masked discrete diffusion samples categorical token-reveal transitions rather than continuous state updates. D-DOIT derives the corresponding discrete Doob's h-transform, which guides sampling by reweighting reverse transition probabilities instead of adding a drift correction. To make this transformation practical, D-DOIT avoids expensive future rollouts. At each guided step, D-DOIT samples candidate next states, uses the model prediction head to complete each candidate into a clean sequence, evaluates each completion with the reward oracle, and resamples the next state with probabilities proportional to the rewards. An optional late-stage best-of-K refinement further improves sample quality by branching trajectories only near the end of denoising,…

  PDF

  Summarize this
• arXiv cs.LGOct 4

  Learning under Localized Minority Imbalance

  Amin Hosseininasab, Steven M. Shugan

  Class-imbalance methods implicitly assume that the minority class is uniformly undersampled relative to the majority class. However, in many real-world settings, minority instances may be disproportionately under-observed in certain regions of the feature space. For example, small businesses that go bankrupt may disappear from records, while those that survive remain visible, making bankruptcy appear less common among small firms than it actually is. This gives rise to localized minority imbalance (LMI), a challenge that is often overlooked and extends beyond general class-count imbalance. We show that under LMI, existing imbalance mitigation techniques can fit observation-induced biases in the training data and generalize poorly to under-observed regions of the true minority distribution. To address this, we propose a tree-based stratified approach that recursively partitions the feature space with the goal of reducing within-stratum LMI distortion. For each resulting stratum, we pair its majority instances with the full observed minority set and train a base classifier to create an ensemble. Extensive experiments over benchmark tabular datasets simulated with LMI show that our…

  PDF

  Summarize this
• arXiv cs.ROOct 4▲ 17

  DiVeR: Decision-Critical Verifier Learning for VLA Test-Time Scaling

  Seongheon Park, Heecheol Kim, Shulin Tian, Lilika Makabe, Namiko Saito +3

  Scaling robot data and model capacity has improved Vision-Language-Action (VLA) policies, but further progress is constrained by the high cost of robotic data. Verifier-guided test-time scaling offers an efficient alternative by sampling multiple action candidates and selecting the one most likely to lead to task success at inference time. Existing classification-based verifiers learn from trajectory-level outcomes but treat all visited states equally, even though their value for candidate discrimination can vary across a trajectory. At many states, plausible actions are similar and provide limited discrimination signal, while only a sparse set of decision-critical states admits meaningfully different actions that can substantially affect downstream outcomes. To address this, we propose DiVeR, which estimates decision criticality from the dispersion of sampled action representations. DiVeR then uses this signal to reweight verifier learning toward states where action selection is most consequential, without requiring step-level annotations or additional environment interaction. Across LIBERO, RoboCasa, and real-world experiments on a Franka Research 3 robot, DiVeR consistently…

  PDF

  Summarize this
• arXiv cs.LGOct 4

  Billion-Scale Thumbnail Optimization for Uncurated Short-Form Videos via Multi-Armed Bandits

  Ying Han, Ling Liu, Fabio Soldo, Vu Nguyen, Danio Wang +5

  This paper introduces a real-time thumbnail optimization system deployed at a global $O(B)$ scale on a major short-form video platform. Unlike traditional long-form content, where custom thumbnails are heavily curated by creators, a considerable fraction of short-form videos are published without human-selected artwork. To address this uncurated corpus, we present a fully automated, end-to-end framework that replaces static default frames with dynamic, data-driven selections across billions of videos. To the best of our knowledge, this is the first published work demonstrating an online Multi-Armed Bandit framework successfully deployed at an $O(B)$ scale for uncurated short-form video discovery. Our solution pairs a multi-stage candidate generation pipeline with a low-latency serving infrastructure. By initializing the exploration framework with image-specific priors derived from a deep visual quality model, the system minimizes exploration costs and dynamically serves optimal thumbnails at serving time. Global deployment demonstrates statistically significant improvements in core user discovery and engagement metrics.

  PDF

  Summarize this
• arXiv cs.LGOct 4

  Prompt Dominance and Asymmetric Verifier Costs: Empirical Ablations of GRPO at 1B Scale on GSM8K

  Yi Hou

  This paper studies GRPO at 1B scale from both directions: what estimator choices do to the learning signal, and what a degraded reward signal does to what is learned. We train OLMo-2-0425-1B on GSM8K with a from-scratch implementation and measure both sides in controlled sweeps, including a verifier-quality experiment that degrades the training reward and the test-time selector identically. Four results stand out. The prompt is the first-order decision: the zero-shot prompt leaves the base model at 0.08% (its outputs are degenerate continuations, not wrong answers), so almost no group carries a gradient, and training succeeds because the 3-shot prompt reaches 18.3%. At this scale the estimator variants sit within seed noise, with Dr. GRPO ahead on both seeds. In the off-policy regime, clipping is the whole story: training on data without a clipped ratio loses 4-6 points relative to the on-policy reference, while GRPO-style clipping and GSPO recover the loss entirely. Finally, the same weak verifier is far cheaper in RL than in test-time selection: a 10%-flip verifier leaves RL's attainable gain intact (91% and 106% retained across two seeds) where selection retains 57%, and a…

  PDF

  Summarize this
• arXiv cs.SEOct 4

  Assembling Insights for Agentic Machine Learning Engineering Systems

  Bihui Jin, Yinxi Li, Kaiyuan Wang, Pengyu Nie

  Agentic machine learning engineering (MLE) is an emerging AI4SE application for complex ML tasks and a step toward recursive self-improvement of AI systems. Recent agentic MLE systems show the value of leveraging insights from related MLE tasks: some systems condition code generation on expert domain knowledge, which is implicitly curated from peer MLE tasks; some systems have a loop of solving an MLE task, gathering memory to benefit future tasks. However, insight collection and injection remain ad hoc, and existing evaluations often do not control insight sources, making data leakage a threat to validity. To close these gaps, we systematically study how insights from related MLE tasks affect agentic MLE systems, and how their impact depends on insight type and injection method. We introduce MLE-InsightBench, a benchmark of 160 Kaggle competitions across 12 domains. To prevent leakage, one competition per domain is held out as the target, while the remaining 148 serve as sources only when they cannot have been influenced by the target task, such as through later editions or reused solutions. We also develop MLE-InsightForge, an insight assembly agent that explores source…

  PDF

  Summarize this
• arXiv cs.LGAI safetyOct 4

  TSAE: Structured Sparse Autoencoders for Interpreting Time-Series Forecasting Models

  Baoxi Liu, Yi Xie

  Time-series forecasting informs critical decisions in energy dispatch, industrial operations, and environmental monitoring; understanding the patterns models rely on is essential for assessing reliability and identifying failures. Input attribution identifies important variables and time segments but offers limited insight into internal features, while standard sparse autoencoder (SAE) objectives do not directly constrain cross-variable structure or temporal continuity. We introduce TSAE, a structured sparse autoencoder for forecasting representations that decomposes hidden states into individually inspectable features. TSAE organizes cross-variable structure through shared and variable-routed private dictionaries, separates feature detection from magnitude estimation with gated encoding, and constrains neighboring sparse-code changes according to raw-segment similarity. These mechanisms support analysis of variable context, activation strength, and temporal evolution. Forecast-consistency fine-tuning further improves preservation of the frozen forecaster's outputs. The accompanying TSEVAL protocol separately audits fidelity, feature coherence, and physical calibration to ground…

  AIEvals40PDF

  Summarize this
• arXiv cs.CVOct 4

  TRACE: Time-Adaptive Residual Attention Control with Content-Style Decomposition for Training-Free Diffusion Style Transfer

  Duc Khoan Le, Kim Ngoc Tran, Minh Nhat Le, Thanh An Tran, Viet Toan Nguyen +3

  Reference-guided style transfer aims to preserve the semantic structure of a content image while transferring the visual appearance of a style reference. Recent diffusion-based methods achieve impressive stylization quality by exploiting strong pretrained generative priors. However, training-free approaches still face a difficult trade-off among style fidelity, content preservation, and content leakage. Direct style injection may unintentionally transfer semantic content from the style image, while fixed guidance schedules often ignore the time- and state-dependent nature of diffusion sampling. To address these limitations, we propose TRACE, a training-free diffusion style transfer framework with Time-adaptive Residual Attention Control and Content-Style Decomposition. TRACE first performs offline CLIP-based subspace analysis to separate content and style directions from paired data. During inference, it removes content-related components from the style reference and style-related components from the content reference to reduce leakage. It then injects style information through residual cross-attention and applies uncertainty-aware guidance to adapt the guidance signal at each…

  PDF

  Summarize this
• arXiv cs.SEOct 4

  Complex Agents, Shallow Tests: Demystifying and Enhancing Test Adequacy of Agent Harness in the Wild

  Yifan Xiong, Jingyi Ge, Zhenpeng Chen, Yiling Lou

  LLM-based agentic systems are emerging as a new software paradigm. Modern agents are typically composed of backbone LLMs and a surrounding harness that serves as the operational software infrastructure for agent execution. As agent harnesses grow increasingly complex, agents suffer from diverse harness implementation bugs, raising substantial reliability concerns. In this work, we conduct the first empirical study to systematically investigate the test adequacy of harness in real-world agentic systems. Our analysis reveals that agent harness remains substantially undertested. In particular, LLM-dependent harness (LDH) code, despite its critical role in processing LLM outputs and governing agent behavior, receives limited testing attention, with less than half of its lines and branches covered by existing tests. Motivated by these findings, we further propose HarnessTester, the first harness-oriented test generation technique that incorporates explicit agent-harness contract support to construct contract-faithful test setups and extensively exercise LDH code. Our evaluation shows that HarnessTester substantially outperforms state-of-the-art general-purpose test generation…

  PDF

  Summarize this
• arXiv cs.CVOct 4

  PWM: Personalized World Models with Online Reinforcement Learning

  Zhexin Lou, Guancheng Lu, Zeyu Zhang, Yi Zhang, Yang Zhao +1

  Pretrained world models can generate diverse environments, yet users often want to explore a particular scene specified by their own video. This requires learning the scene's visual identity while retaining the quality of action-conditioned generation. We introduce Personalized World Models (PWM), a framework for customizing interactive world models from short scene videos through online reinforcement learning. In PWM, the support trajectory and its associated controls provide reward feedback on continuations sampled from the current policy. In the GRPO instantiation, group-relative optimization updates a compact LoRA adapter using a unified reward for scene appearance, visual continuity, and motion, while base-policy anchoring regularizes changes to the pretrained generation prior of a frozen Yume-5B backbone. The same adaptation procedure is applied across real and rendered environments. We also instantiate PWM with DiffusionNFT as an alternative reward-guided optimization method for learning the scene-specific adapter. We also introduce PWM-Bench, comprising 150 customization tasks across Indoor, Outdoor, and Gaming, with paired evaluation on held-out continuations. The GRPO…

  PDF

  Summarize this
• arXiv cs.LGOct 4

  Residual Visual Credit Optimization: Conserved Evidence Routing for Multimodal Reinforcement Learning

  Lin Qiu, Yao Liu, Diyi Hu, Hanqing Zeng, Onur Gungor +4

  Reinforcement learning with verifiable rewards scales multimodal reasoning, but an outcome reward says how much a trajectory is worth, not how that value should be spread over the decisions that produced it. We introduce Residual Visual Credit Optimization (RVCO), which treats token credit as a conserved routing problem. A controlled visual intervention yields a per-token evidence response; robust within-trajectory coordinates remove incidental scale; and a budgeted entropic router distributes a fixed amount of sequence utility according to perceptual dependence. A residual support path guarantees positive credit at every valid position, and an analytic correction restores the prescribed credit mass exactly. The resulting field is selective, bounded, full-support, and invariant to response-local score shifts, and recovers hard token selection as a limiting case. Across four model families and seven reasoning benchmarks, RVCO improves accuracy over strong RLVR baselines while maintaining late-stage optimization stability, corruption robustness, and competitive training cost. Rewards, rollouts, and the group-relative advantage estimator are unchanged; only the geometry of…

  PDF

  Summarize this
• arXiv cs.ROOct 4

  PreAct-Nav: Agentic Reasoning Before Action for Urban Navigation

  Jing Xie, Shouwei Ruan, Yubin Wang, Yuxiang Zhang, Junwei Yang +2

  Urban navigation requires embodied agents to pursue long-horizon goals through local decisions based on egocentric observations. However, existing agentic navigation methods often struggle to translate distant goals into coherent local decisions in large-scale physical environments. Their reliance on linguistic reasoning over transient observations or limited history constrains anticipation of the consequences of actions and future conditions, despite the importance of such foresight for navigating long and complex urban routes. To bridge this gap, we propose PreAct-Nav, an agentic navigation framework that equips frozen policies with anticipatory reasoning for robust urban navigation. Our central idea is to anchor local decisions in persistent medium-horizon subgoals, assess the consequences of predicted actions before execution, and continually update the reasoning context using actual outcomes. At its core, a navigation memory module maintains the active subgoal and relevant experience across decisions, translating distant goals into actionable intermediate objectives. We further introduce a predictive world sandbox that uses an action-conditioned world model (AC-WM) to…

  PDF

  Summarize this
• arXiv cs.AIOct 4

  Are We Measuring Scientific Intelligence? Rethinking the Evaluation of AI Scientists

  Kate Zhang, Yuante Li

  AI agents can now carry out data-driven scientific analyses end to end, and benchmarks assess them by giving an agent a question and a dataset and scoring its final answer against a fixed key. These benchmarks assume that a correct answer was derived from the supplied data, a property we call evidence grounding. However, an agent can also reach the key from prior knowledge or by ruling out the other options, and a score based on a single run cannot tell these cases apart. We show how to test this assumption and find that it often fails. For each question, we build versions of its data files in which the evidence for the answer is left intact, withdrawn or reversed, check each edit with a pre-registered reference statistic, and run the same agent on every version. We then measure evidence-grounded accuracy, which credits a correct answer only if the agent also responds when the evidence is withdrawn and follows it when it is reversed. We evaluate three agent scaffolds and five models on 18 single-cell questions from BAISBench and four synthetic problems from GeneBench-Pro. On the single-cell questions, the Claude agents are 95% accurate and answer 83% correctly without any data,…

  PDF

  Summarize this
• arXiv cs.AIOct 4

  Monitorability Disposition in Large Reasoning Models

  Shahriar Golchin, Marc Wetter

  Monitoring the chain-of-thought (CoT) of large reasoning models (LRMs) is a common way to detect misbehavior in real-world practice. However, current monitoring is passive: a separate model inspects the session only after execution. This means harm may already have occurred before it is caught. An active alternative is to have the model self-report its misbehavior as it happens. Whether models are willing to do this, however, is unknown. We introduce "monitorability disposition": a model's willingness to make itself monitorable and stay monitored throughout inference when warranted. We measure it as the fraction of warranted cases in which a model self-reports its own misbehavior via tool calls to available monitoring channels. We evaluate four LRMs on three misbehaviors (sycophancy, reward hacking, and bias) while varying the available monitors (AI and human) and the pressure to use the monitoring tools. We find that when tool use is optional, models self-report in only about 16% of warranted cases on average. Increasing tool-use pressure does not improve reporting where it matters: high-severity misbehavior is never self-reported. Models also systematically select the monitor…

  PDF

  Summarize this
• arXiv cs.CROct 4

  Static Bootstrap Placement for Encrypted Language Model Decoding

  Halil Ibrahim Kanpak, Didem Unat

  Language models increasingly serve prompts that carry private data, and secure inference under homomorphic encryption lets a client outsource the computation without revealing the prompt. Existing secure inference systems run a forward pass without consuming a token under encryption, and generating text with them requires a client round trip at every generated token. Keeping the loop on the server instead requires selecting and consuming a token under encryption, and placing bootstraps for a loop body that grows with the context. We build AR-HE, which runs the whole loop on the server, selects each token under encryption, retrieves its embedding, and writes it back into the encrypted state. The client sends one prompt and remains offline until the output. One rule places every bootstrap in the run, without search, so the bootstrap cost of a token is a formula in the context length that is known before the run starts. The schedule skips work whose result cannot reach the output, packs bootstraps that share an operand, and keeps the keys and values of past positions in an encrypted cache. With every optimization applied, generating a GPT-2 small token costs 544 seconds on one…

  PDF

  Summarize this
• arXiv cs.AIOct 4

  VideoResearchAgent: Grounded Task Synthesis and Sim-to-Real RL for Open-Web Video Research

  Yuhang Zhou, Fei Li, Yuxi Wu, Bin Zhu, Jingjing Chen

  Existing deep research agents are designed primarily for text- and image-based web sources, while video reasoning systems typically assume that relevant videos are provided in advance. We study open-web video research, where an agent must autonomously discover relevant videos, navigate their temporal content, and ground answers in visual evidence. Training such agents at scale is challenging as live video interaction is slow and unreliable, whereas fixed local simulation can induce retrieval-specific shortcuts that fail to transfer to the open web. We introduce VideoResearchAgent, a scalable training framework to address these challenges. First, we introduce controllable task synthesis pipeline to synthesize multi-hop research tasks from timestamped visual evidence while filtering text-only shortcuts. Second, we build a field-aligned local video simulator that preserves deployment-facing search and watch interactions while accelerating video search by a factor of 34.5-64.6. Third, we introduce Retrieval-Domain-Randomized GRPO (RDR-GRPO), which diversifies candidate rankings, distractors, metadata, and result structure during training to reduce overfitting to simulated retrieval.…

  PDF

  Summarize this
• arXiv cs.LGOct 4

  Why Subliminal Learning Needs So Much Data: A Noisy Inverse View through Steering Vector Recovery

  Luoyu Chen, Xiaoyu Ding, Weiqi Wang, Chenhan Zhang, Zhiyi Tian +2

  Subliminal learning lets a student inherit a teacher's behavioral trait from semantically unrelated data, yet published demonstrations typically require tens of thousands of carrier examples. We ask where this data requirement comes from. Our testbed is subliminal steering: the teacher trait is a known residual-stream vector $Δ_T$, so transfer can be measured directly as parameter recovery. On identical carrier prefixes, we compare token-level (hard) NLL supervision with full-distribution (soft) KL supervision. At initialization the two objectives give nearly collinear gradients, and both align poorly with $Δ_T$. Under iterative optimization, however, they diverge: soft supervision recovers $Δ_T$ almost exactly from a few hundred carriers, while hard supervision stays well below it even with tens of thousands. We explain this gap by casting steering-vector distillation as a noisy linear inverse problem. Locally, the carrier task maps the trait through its Fisher matrix $F$, so gradients point toward $FΔ_T$ rather than $Δ_T$. Gradient descent then acts as a progressively less-damped inverse of $F$. With soft targets, this inverse restores low-curvature directions. With hard…

  PDF

  Summarize this
• arXiv cs.CLOct 4▲ 2

  Scaling Verifiable Environments for Long-horizon Work Agents

  Jiazheng Zhang, Long Ma, Yunxian Yang, Zhiheng Xi, Zhikai Lei +22

  Work agents operate over digital artifacts to execute professional knowledge-intensive work, requiring training environments that support long-horizon interaction and trustworthy verification. However, hand-crafted environments incur prohibitive engineering overhead that prevents environment scaling, whereas synthesis methods sacrifice workspace complexity, realism, or grounded verifiability. To bridge this gap, we introduce WorkForge, a scalable synthesis framework for constructing verifiable work-agent environments from real-world resources. Starting from expert workflows, WorkForge first identifies the resources, decisions, and deliverables required by each workflow. It then retrieves relevant real-world files and organizes them into a workspace. WorkForge inspects the workspace to extract concrete, checkable facts about its content. These factual anchors fix which task types the workspace can support and how their outcomes can be verified. Therefore, WorkForge derives each task's instructions, solution plan, and complementary programmatic and semantic verifiers directly from these factual anchors, keeping verification traceable to observable workspace evidence. Furthermore,…

  Code

• Databases8+100.0%
• Diffusion priors25+38.9%
• DevOps & cloud11+37.5%
• Federated learning41+32.3%
• Algorithmic trading26+30.0%
• Programming languages13+30.0%
• Linear bandits99+28.6%
• Speech emotion15+25.0%