Research

• Lack of benchmarks for agent harness reliability1 paper raises it · 1 addresses it

  Existing benchmarks focus on model capabilities rather than the reliability of the systems that support agent operation.

  • Trial by Trace: Benchmarking AI Agent Harnesses for Reliability and Failure Attributionraises · addresses
• Unclear net value of agent memory1 paper raises it · 1 addresses it

  Dedicated memory systems often underperform naive retrieval, making their benefits uncertain.

  • Memory Tax: Dissecting the Net Value of Agent Memoryraises · addresses
• Token collapse in graph soft prompting1 paper raises it · 0 address it

  Graph-specific tokens become indistinguishable, failing to convey intended relational information.

  • On the Token Collapse Phenomenon in Textual Graph Soft Promptingraises
• Poor trajectory supervision for tool-use agents1 paper raises it · 1 addresses it

  Successful trajectories may lack compositional coverage or decision grounding, limiting agent learning.

  • Trajectory2Gym: Decision-Grounded Compositional Interaction Synthesis for Tool-Use Agentsraises · addresses
• Uneven evaluation of coupled agent-world model systems1 paper raises it · 1 addresses it

  Separate evaluation of agents and world models fails to predict their joint performance or sustained learning.

  • Dual Exam: Controlled Evaluation of Multimodal Agents and World Modelsraises · addresses

Named by an AI from these papers' abstracts.

• arXiv cs.LGOct 8

  PRAXIS: Learning Dynamics of Self-Improving Models with Symbolic Archives

  Venkat Margapuri, Mustafa Teber

  Self-improving learning systems adapt data selection, optimization, and auxiliary symbolic components, inducing nonstationary objectives outside standard learning assumptions. We introduce \textsc{PRAXIS}, a co-evolutionary framework that models generators, learners, and symbolic archives as interacting dynamical processes. We prove that KL-constrained generator updates and controlled archive-weight movement bound one-step objective drift, that archive updates suppress a program relative to any fixed comparator with a persistent cumulative utility advantage under sub-Gaussian noise, and that stochastic gradient descent achieves an average-stationarity guarantee whose degradation is governed by cumulative objective drift. Experiments across visual robustness, relational graph reasoning, and algorithmic graph reasoning exhibit generator stabilization, decreasing learner loss, and archive concentration consistent with these theoretical mechanisms.

  PDF

  Summarize this
• arXiv stat.MLOct 8

  Softmax Attention on Gaussian Mixtures: Linear When It Can, Selective When It Must

  Simon Gabet, Etienne Boursier, Claire Boyer

  Softmax attention, at the heart of Transformers, has demonstrated remarkable capabilities. Yet its underlying mechanisms remain only partially understood. Recent theoretical work studies Gaussian prompts, where the infinite-prompt limit reduces softmax attention to a linear map, but also removes the query-dependent selection that distinguishes it from linear attention. This work studies the infinite-prompt limit of softmax attention on Gaussian mixtures, which retain the tractability of Gaussian data while introducing latent structure, multimodality, and nonlinear dependencies. We show that softmax attention can represent and learn, via gradient-based methods, optimal solutions to a range of statistical tasks, including supervised classification and denoising. Our results highlight two complementary capabilities of softmax attention: it can recover linear tasks as effectively as its simpler linear counterpart, while also exploiting query-dependent context selection to solve nonlinear tasks beyond the reach of linear attention.

  PDF

  Summarize this
• arXiv cs.AIOct 8▲ 47

  Memento 3: Model-Based Recursive Self-Improvement through Reflective Rulebooks

  Haoyu Zhao, Zhengxu Yu, Zhiyuan He, Meng Fang, Rasul Tutunov +3

  Learning to act in unfamiliar environments requires agents to infer how the world works and revise that understanding as new evidence arrives. Yet limited observations can support multiple world models that explain past interactions but predict different outcomes in unseen states. We introduce Memento 3, building on the Memento series to enable frozen LLM agents to continually learn explicit world models through external memory. The agent maintains a natural-language rulebook as persistent semantic memory, recording revisable hypotheses about environment dynamics while leaving unknown aspects underspecified. It compiles this rulebook into executable code for prediction and planning. Through a continual loop of observation, reflection, rule revision, compilation, and verification, the agent uses prediction errors to refine both the rulebook and its code. Updated code is accepted only when the LLM judges it faithful to the rulebook and cell-exact replay reproduces the observed transitions. We investigate this process as a model-based route to recursive self-improvement (RSI): the agent autonomously explores the environment, revises its world model, and uses verified updates to…

  PDF

  Summarize this
• arXiv cs.MMOct 8

  AuraLuxMuse: Adaptive Fusion Modeling for Aesthetic Stage Lighting Design with Music and Expert Guidance

  Junyu Deng, Jiale Cao, Mengtian Li, Zhongxia Ji, Ruhua Chen +3

  We present AuraLuxMuse, a novel system for automated aesthetic stage lighting design that integrates expert knowledge, representation learning, and preference-adaptive modeling. Lighting design in live performance settings requires the seamless translation of musical features into dynamic lighting behaviors. However, traditional workflows remain time-consuming, labor-intensive, and difficult to transfer. AuraLuxMuse encodes music and professional cue sequences into a shared retrieval space, estimates cue-event density, and retargets selected fixture commands to the destination stage. It assists pre-production authoring by returning editable cues rather than replacing the designer with an unconstrained generator. At the heart of AuraLuxMuse are two key modules: Lighting-Aligned Music Pretraining (LAMP), which performs contrastive learning between audio and lighting cues for alignment, and Preference-Adaptive Mixture of Experts (PAMoE), which conditions preference-aware cue retrieval and adaptation on designers' intent through a gated ensemble of style-specific expert networks. To support training and evaluation, we introduce Musilux, the first dataset of paired musical audio and…

  PDF

  Summarize this
• arXiv cs.CVOct 8

  Phase-aware video generation for physics-grounded dynamics and interactions

  Jingfeng Ou, Kun Wang, Rui Zhao, Jingwei Guan, Limin Wang +2

  Generating physically plausible videos for solid-gas dynamics is challenging as different phases exhibit distinct dynamics yet remain coupled through physical interactions. We present PAVG, a Phase-Aware Video Generator for solid-gas dynamics and interactions. It employs a dual-branch architecture to explicitly model the distinct dynamics of solids and gases, while spatiotemporal cross-attention captures their physical interactions. This design enables PAVG to preserve phasespecific motion characteristics while producing physically consistent responses across phases. To facilitate this task, we further construct a simulation corpus comprising over 700K physical trajectories across diverse solid, gas, and solid-gas interaction scenarios. Extensive evaluations demonstrate that our PAVG produces videos with improved motion adherence, physical plausibility, and visual quality compared with existing approaches.

  PDF

  Summarize this
• arXiv cs.CLOct 8

  Easy to anticipate, hard to compute: boundary dependence finds the computed outputs that entropy patching misses

  Nicolás Vera Zúñiga

  Byte-level language models such as the Byte Latent Transformer (BLT) group bytes into patches and run their large global model once per patch. BLT starts a patch where a small model's next-byte entropy is high, so global compute goes where the next byte is hard to predict. We show that this rule has a systematic blind spot: positions whose type is predictable but whose value must be computed, such as the number after "=" in a worked math solution. Under tight patch budgets, entropy-triggered layouts skip these positions, and accuracy on them collapses. In Meta's BLT-1B with patch starts on 10% of bytes, the entropy rule puts a patch start at 16% of the computed results in GSM8K solutions and gets 19.0% of them exactly right; a boundary after each "=" at the same patch count gets 51.8%, and entropy combined with a label-free boundary-dependence signal gets 67.1% (default layout at 26% of bytes: 76.8%). The gap survives adapting BLT-1B to the budget with low-rank fine-tuning (32.9% vs 72.7%, three runs per rule, paired p < 1e-200) and grows with model size in byte models trained from scratch at a 10% budget: at 1M, 12M and 50M parameters, boundary dependence beats entropy on final…

  PDF

  Summarize this
• arXiv cs.CLOct 8

  From Sparse Representations to Behavioral Insights for Multimodal Depression Assessment

  Guimin Hu, Zihao Song, Jiachen Luo, Jiayuan Xie, Ruichu Cai

  Multimodal depression assessment offers a promising approach to analyzing behavioral patterns associated with depression. However, existing methods often rely on dense and opaque multimodal representations, making it difficult to interpret the behavioral patterns underlying their predictions. In this work, we introduce BehavDep, a sparse factor-based framework that decomposes multimodal behavioral representations into sparse latent factors and associates them with behaviorally meaningful concepts through a semantic bridge. To address the mismatch between user-level annotations and heterogeneous video-level behaviors, BehavDep further learns video-level depression tendency scores under weak supervision and aggregates information across multiple observations for user-level assessment. Extensive experiments demonstrate that BehavDep achieves the best overall assessment performance while revealing complementary modality contributions, heterogeneous behavioral patterns across observations, and prediction responses to concept-level editing. These results show that BehavDep provides a structured and interpretable approach to analyzing multimodal behavioral representations for depression…

  PDF

  Summarize this
• arXiv cs.LGOct 8

  Compile the Table: Query-Calibrated Operator Compression for Tabular In-Context Learning

  Xu Zhao, Jiaming Zhao, Bin Zhao, Yong Yang

  Tabular in-context learning (ICL) has emerged as a training-free and accurate paradigm for tabular prediction, but current approaches to compressing its in-context examples face an accuracy-throughput tradeoff: fixed subsets can sacrifice accuracy, while query-specific retrieval limits cache reuse and batching across queries, reducing throughput. We propose QCOC (Query-Calibrated Operator Compression), which exploits the exchangeability and repeated use of in-context examples by compiling their full KV cache once into compact memory shared across subsequent queries. Instead of retaining raw examples, QCOC clusters their states into joint-KV prototypes, preserves per-cluster multiplicities and the original example count, and calibrates prototype values against attention query vectors produced by the in-context examples through an anchored closed-form solution. Prototype compression drives the speedup, while value fitting helps preserve accuracy. On 64 held-out OpenML-CC18 datasets, QCOC achieves the highest mean accuracy among the compared compression and retrieval methods at both retained counts. Across 12 configurations on seven long tables, it ranks first among compressed…

  PDF

  Summarize this
• arXiv cs.LGOct 8

  In-Ride Alcohol-Impairment Detection in E-Scooterists with False-Alarm Control

  Marco Capuccini, Rahul Rajendra Pai

  Shared e-scooter services have become a widely adopted urban transport mode. While most users ride responsibly, alcohol intoxication stands out among the factors contributing to severe crashes. Nonetheless, countermeasures remain limited to single-point reaction tests and night bans that suspend the service altogether. This paper proposes a new approach in which onboard sensors evaluate the rider as the trip unfolds, raising an alarm as soon as enough evidence of impairment has accumulated. Specifically, we introduce a detector that operates on inertial and throttle measurements, with a provable bound on the rate of false alarms. Experiments on sensor data from 141 rides, in which 25 participants rode while sober and at two target blood alcohol concentration levels, confirm that the bound holds, whereas baselines and ablations either exceed it or lose detection performance, and in some cases delay the alarm. At a bound of 0.023, the detector identifies 91% of the rides performed at the higher concentration and 50% of those at the lower one, with median detection times of 25 and 27 seconds, respectively. We further show that an embedded implementation meets the real-time…

  PDF

  Summarize this
• arXiv cs.CVOct 8

  Skill-V: Verifiable Self-Evolving Skill Library for Interactive Agents

  Jie Ma, Zhipeng Qian, Yufei Ma, Zihan Liang, Jiayi Ji +4

  Interactive agents can turn experience into reusable skills, yet existing self-evolving skill libraries primarily improve by accumulating new knowledge. Failures may lead to new skills, while previously stored skills are less often revisited as new evidence arrives. However, growth alone does not ensure reliability, as a retrieved skill may be inapplicable under the current task conditions, and an existing skill may encode a mis-specified operational boundary. Reliable skill evolution therefore requires not only adding knowledge, but also testing and revising what is already stored. We introduce Skill-V, a verifiable self-evolving skill library. To make stored knowledge testable, we propose representing skills as versioned, falsifiable contracts that link semantic intent to observable behavioral criteria. We use environment outcomes to drive library evolution. Specifically, task failures motivate skill addition, while disagreements between contract evaluations and task outcomes guide revisions to existing skill boundaries. To validate these revisions, we require them to preserve protected semantic constraints and satisfy non-regression criteria for rubric-outcome metrics on…

  PDF

  Summarize this
• arXiv cs.CLOct 8

  DPPM: Dual-Path Parametric Memory for Personalized Language Models

  Yuhao Chen, Shuochen Liu, Jiayao Shi, Jian Hong, Chen Cheng +5

  Long-term personalization requires language models to use interaction history to track users' preferences across sessions. Parametric memory encodes this interaction history into model parameters or adapters, reducing the need to include it in the inference context. However, independent context compilation leaves cross-session integration unspecified, while recurrent updates can attenuate earlier evidence. To address these challenges, we propose Dual-Path Parametric Memory (DPPM). Its Evidence path directly pools representations of the interaction history to preserve earlier evidence, while its Delta path sequentially updates an associative state to capture changes. Fusing both outputs produces history-conditioned LoRA adapters that combine evidence accumulation with ordered revision. Across multiple backbones, DPPM outperforms the evaluated baselines, achieving 54.22% on PersonaMem-v2 and 86.79% on PrefEval. These results suggest that DPPM provides a simple and effective design choice for cross-session personalized parametric memory.

  PDF

  Summarize this
• arXiv cs.AIOct 8

  RouterInterp: Understanding Superposed Specialisation in Mixture of Experts Routing

  Ilya Lasy, Nora Yinuo Cai, Kola Ayonrinde

  Sparse Mixture of Experts (MoE) models scale more efficiently than dense models by routing tokens to modular expert networks that are only active for processing a fraction of tokens. A leading hypothesis for the performance of MoE models is that each expert specialises in a single, coherent domain. However, interpretability efforts that assume this hypothesis have generally been unsuccessful. We propose and present evidence for an alternative account that we call the Superposed Specialisation Hypothesis (SSH): experts specialise in a disjoint union of fine-grained features rather than one broad domain. Leveraging the SSH, we introduce RouterInterp, a method for interpreting expert routing that identifies Sparse Autoencoder features most predictive of routing decisions and produces unified natural language explanations. On gpt-oss-20b, RouterInterp explains expert routing with ${\sim}65\%$ higher detection accuracy than prior token statistics based methods. This work provides a scalable method for generating more accurate explanations of expert routing and increases our understanding of a previously uninterpretable component of foundation models.

  PDF

  Summarize this
• arXiv cs.AIOct 8

  Safe Actions Alone Do Not Ensure Safe Agents: Identifying Unfulfilled Obligations with Guard Models

  Youwei Feng, Yitong Zhang, Yuetong Liu, Jia Li

  Guard models are increasingly used to safeguard LLM-based agents, primarily by identifying actions that agents are forbidden to perform. However, identifying forbidden actions alone is insufficient to ensure agent safety. In this paper, we argue that agent safety also depends on identifying required yet unperformed safety-critical actions, which we call obligations. Our preliminary study on a popular benchmark for evaluating safety shows that 56.92% of GLM-5.3 trajectories contain unfulfilled obligations, compared with only 30.00% containing forbidden actions. This finding reveals unfulfilled obligations as a major and previously overlooked source of safety risk. However, to our knowledge, no existing benchmark evaluates whether guard models can identify these obligations. To close this gap, we introduce ObligationBench, the first benchmark for evaluating the capability of obligation identification, comprising 240 expert-validated trajectories covering issue resolution, feature development, and terminal operations. Our evaluation of 14 representative models reveals substantial limitations: the highest recall and exact-match rate are only 48.97% and 10.00%, respectively. To…

  PDF

  Summarize this
• arXiv math.STOct 8

  Optimal random quantisers for spherically symmetric distributions

  Luc Pronzato, Anatoly Zhigljavsky

  Zador's celebrated theorem is a cornerstone of optimal quantisation: it establishes both the weak limit of the empirical distribution of an optimal $n$-point quantiser in $R^d$ and the decay rate of the associated $L_s$-mean quantisation error. In large dimension, however, observing this asymptotic behaviour requires an astronomically large sample size. We prove that, for spherically symmetric target distributions, optimisation over all spherically symmetric distributions is a convex problem and derive an equivalence theorem that both characterises global optimality and yields a constructive algorithm. We show that, for moderate $n$, random quantisers uniformly distributed on a sphere of suitably chosen radius $R$ perform exceptionally well and, over a broad range of values of $n$, are numerically certified to be optimal among all random quantisers. Their expected distortion has an explicit integral representation that can be evaluated to arbitrary precision, and we prove concentration across random quantisers: the distortion variance tends to zero as $n\to\infty$ for fixed $d$. For $s=2$, both the optimal radius and the associated minimum expected distortion admit exact…

  PDF

  Summarize this
• arXiv cs.CVOct 8

  From Video Clips to Creation Trajectory: Sora100K for AI-Native Video Creation

  Sicong Yang, Ruihuan Yang, Jian Lu, Jianfei Yuan, Xiaodong Cun +1

  AI-Native video creation is shifting from isolated video clips toward iterative video creation workflows. However, existing datasets remain largely video clips, representing video generation and editing as separate tasks rather than connected stages of a video creation workflow. In this paper, we introduce Sora100K, a dataset that represents the AI-Native video creation workflow as a structured video creation trajectory. Specifically, we first identify video creation trajectories and decompose them into three subsets according to their structural roles: text-to-video generation records as roots, single-turn video editing records as editing edges, and multi-turn video editing records as complete trajectories. Then, we use a VLM to assign semantic annotations for generation roots and editing-operation annotations for editing edges. A strict construction pipeline further reconstructs source-to-edit lineage, editing order, and intermediate video states while ensuring data quality. Finally, we perform lightweight adaptation on LTX-2 models to assess the supervision value of Sora100K. The results show improvements in visual quality, multi-shot generation, and cross-shot consistency,…

  PDF

  Summarize this
• arXiv eess.SYOct 8

  Narrow and Deep: An Ontology Tower as the Knowledge of an LLM Agent for an Industrial Equipment System

  Younghwan Joo, Sung-il Kim

  Large language model (LLM) agents are beginning to operate industrial energy equipment, and what they get right depends on what they are told about the plant. Established building ontologies name many kinds of points across many sites, whereas an industrial equipment system needs few entities with much knowledge about each. This study proposes the ontology tower, a narrow-and-deep ontology of a single equipment system whose knowledge deepens in two ways: through quantities derived from the measured points by physical relations, and through lessons from the operating journal incorporated as knowledge nodes. On a real low-humidity air-handling test plant operated daily through a programmable logic controller, agents received a text projected from its tower in a preregistered evaluation of nine tasks replayed from the plant's records, using four open-weight models from 9 to about 750 billion parameters. This knowledge raised the rate at which the agents avoided the most plausible misjudgment of each task by about 20 percentage points, and the overall task score of the 9-billion-parameter model as much as that of the largest. Operating lessons were used when incorporated into the…

  PDF

  Summarize this
• arXiv cs.CLOct 8

  Same Outcome, Different Evidence: Intent Recovery in LLM Safety Evaluation

  Haitong Jiang, Chunlin Liu, Sihan Tang, Chan Wu, Xiaoqing Su +1

  Safety evaluations of large language models commonly summarize harmful-output behavior with attack success rate (ASR). Yet the same non-harmful outcome can arise for very different reasons. A model may recover a harmful task and refuse it, fail to recover the task, or respond to something else entirely. Distinguishing these cases becomes especially important under intent-obscuring prompts, where a low ASR does not reveal whether the evaluated task was actually engaged. To make this distinction explicit, we pair ASR with operative understanding rate (UR), which measures whether a response both identifies the evaluated task and treats it as the task to be answered. Across interfaces, this paired view reveals substantial variation hidden by ASR: similar ASR values can correspond to sharply different recovery rates. Controlled English reconstructions show that recovery consistently improves as compressed prompts become more explicit, whereas ASR does not follow the same pattern. A complementary contrast comes from FormalLogic, where high recovery can still coincide with frequent harmful assistance. Together, these results show that non-harmful outcomes are not equally informative…

  PDF

  Summarize this
• arXiv cs.CLOct 8▲ 250

  Thinking Inertia: LLMs Keep Thinking When Told Not To

  Dianqiao Lei, Kevin Qinghong Lin, Pan Lu, Philip Torr, James Zou

  Large Language Models (LLMs) increasingly ship with explicit "thinking modes", yet their counterpart, "no-thinking", has received far less attention. We study LLMs' no-thinking behavior along two axes. a. How to measure no-thinking? Prior work typically defines no-thinking through proxies such as a disabled thinking mode or the absence of long traces. These proxies are unreliable: disabled thinking modes may still emit reasoning, while long traces may contain filler rather than genuine inference. We instead normalize each response into a pre-answer trace and final answer, and evaluate it at three levels: (i) Empty-Thinking Rate for strict answer-only compliance; (ii) instruction-aware Question-Pre-answer Relevance for similarity between the question and pre-answer trace; and (iii) LLM-as-judge Explicit Inference Rate for visible explicit inference. Together, these metrics distinguish answer-only output, relevant but non-inferential text, and explicit inference. b. How does no-thinking vary across tasks and models? We evaluate six prompting interventions on six LLMs across Boolean, multiple-choice, and open-ended questions. We find that explicit no-think controls cannot reliably…

  Code
• arXiv cs.LGOct 8

  RAGenome: Scaling Retrieval-Based Genomic Language Models to Long Contexts

  Frederikke Isa Marin, Panagiotis Antoniadis, Dionysia Danai Brilli, Andreas Bjerregaard, Rachael DeVries +3

  The genome holds the blueprint that governs the biological properties of the cell. Consequently, advancing our knowledge of genomic function is crucial both for a broader understanding of biology and for continued biomedical advances. The success of large language models on natural language and protein sequences has motivated similar efforts on genomic data. However, standard genomic language models (gLMs) often require extremely large computational resources and still fall behind traditional methods on some downstream tasks. Recently, MSA-based pretraining has been proposed as an efficient alternative, but existing models are limited to short input contexts, restricting their use to short-range tasks, such as variant effect prediction. In this work, we present RAGenome, the first retrieval-based gLM that scales pretraining to longer contexts (100$\times$ longer than existing MSA-based gLMs), allowing it to capture both across-species evolutionary relationships and within-species longer-range interactions. Trained on whole-genome alignments from 100 vertebrates, RAGenome substantially improves the long-range capabilities of MSA-based gLMs, raising gene finding performance from…

  PDF

  Summarize this
• arXiv quant-phOct 8

  Beyond QAOA: A Review of AI and Quantum Computing for Adaptive Combinatorial Optimization

  Hoong Chuin Lau

  Near-term quantum approaches to combinatorial optimization are limited by qubit counts, circuit fidelity, sampling cost, and the difficulty of encoding constraints, while machine learning is increasingly used to configure and control quantum optimization workflows. We call such workflows adaptive: decisions conventionally fixed in advance, from formulation and penalties to shot budgets, backends, and whether to invoke a quantum processor at all, are made by learned policies that respond to the instance, the progress of the solve, or the hardware. This review examines three paradigms, AI for quantum optimization, quantum for AI-driven optimization, and AI-quantum co-optimization, and organizes the literature by the decision being learned rather than by application. A structured search identified a 119-paper corpus, of which 67 papers form an evidence core coded in detail. The evidence is considerably stronger for AI-assisted quantum optimization than for the reverse direction: learning already reduces quantum evaluations, improves initialization, supports decomposition and penalty control, and mitigates noise, whereas evidence that quantum computation improves learned optimizers…

  PDF

  Summarize this

• Channel state information15+66.7%
• Anomaly detectors22+37.5%
• Multimodal emotion8+14.3%
• AI tutors130.0%
• Character recognition OCR10−9.1%
• Physics informed neural124−15.6%
• Machine learned interatomic35−22.2%
• Medical image segmentation137−25.5%