Artificial Intelligence · Cross-listed from cs.MA
Exact Cut Complexity of Equal-Length Proportional Cake Cutting
Yasushi Kawase, Bodhayan Roy and Mohammad Azharuddin Sanpui
We study proportional cake cutting under an equal-length constraint, where each of $n$
agents must receive a bundle of length exactly $1/n$ that is worth at least $1/n$ to that
agent. Our main result determines the exact worst-case number of cuts needed to guarantee such an allocation, namely $2n-2$ for every $n$. This improves on the previously known quadratic upper bound. The proof combines the constrained necklace-splitting
theorem with a recursive assignment argument based on Hall's
theorem. The same bound extends to the stronger requirement of envy-freeness when $n$ is a
prime power, and an $O(n^{1.525})$ upper bound holds for arbitrary $n$. We then ask whether such allocations can be computed. We first show that no deterministic protocol in the Robertson–Webb model terminates after finitely many queries on every instance and always returns an exact equal-length proportional allocation, even for two
agents with identical valuations. For every $\varepsilon>0$, however, $O(n^2/\varepsilon)$ queries suffice to produce an allocation in which every
agent receives a bundle of length exactly $1/n$ and value at least $1/n-\varepsilon$, again using at most $2n-2$ cuts. Finally, we augment the Robertson–Webb model with two-knife queries. We show that recursive balanced halving attains the optimal bound of $2n-2$ cuts when $n$ is a power of two. For arbitrary $n$, we give a procedure using $O(n\log n)$ cuts.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.LG
What Happens to the Goal? Distinct Failures of Policy Alignment in Goal Misgeneralization
Julia Barth, Armin Sommer, Kunvar Thaman et al. (+1 more)
Goal misgeneralization is a common failure mode in which an
agent behaves competently out of distribution but does not pursue the intended goal. However, we still have a weak understanding of what happens to the intended goal in misgeneralizing
agents. Across three Procgen environments and five
robot tasks, we find three distinct forms of policy-goal misalignment: (1) functional target substitution, where behavior follows an alternative goal, (2) a policy shortcut, where behavior follows a learned action strategy, and (3) cue competition between intended and proxy goal cues. We distinguish these regimes by tracing where goal information remains available internally, how strongly it influences the policy, and what role it plays in action selection, and find that the goal is lost at different depths. Where the goal reaches the decision, as in cue competition, steering redirects the policy to the goal's location, raising intended-goal reach from 16.0% to 95.3%. Where it reaches the policy but not the decision, only new downstream wiring recovers goal reach, from 31.6% to 84.3% in the environment with the action shortcut. Where it is inert, neither works. Our results show that goal misgeneralization is not a single failure of goal representation, but distinct failures of policy
alignment at different depths, tightly connected to which recovery works.
Read the full abstract ▾
All authors Julia Barth, Armin Sommer, Kunvar Thaman, Jannik Schilling
Artificial Intelligence · Cross-listed from cs.CV
Zhixin Cai, Ruoqi Yuan, Xinchen Yang et al. (+4 more)
Video large
language models (
Video LLMs) often generate responses unsupported by the input
video. Contrastive decoding (CD) can mitigate these
hallucinations, but its effectiveness depends on how the negative branch weakens visual evidence. Existing methods rely on predefined perturbations or masking guided by question reconstruction, offering limited control over the model's visual reliance during answer generation. We introduce
Attention-guided Representation Perturbation for Contrastive Decoding (ARP-CD), a training-free framework for constructing contrastive negatives directly in representation space. ARP-CD uses the
attention mass assigned to visual
tokens at the answer-prediction position to guide bounded gradient updates of the
language model's input visual hidden states. These updates reduce visual
attention and produce a negative input, whose predictions are contrasted with those of the original branch throughout generation. Experiments across four
Video LLMs and four
benchmarks show that ARP-CD outperforms representative training-free baselines in most model–
benchmark settings, reducing
hallucinations while improving general
video understanding. Further analyses show that
attention-guided perturbation directions improve negative quality and that the resulting negatives provide effective contrastive references for correcting the original predictions.
Read the full abstract ▾
All authors Zhixin Cai, Ruoqi Yuan, Xinchen Yang, Zhuofan Chen, Jun Bai, Chuantao Yin, Wenge Rong
Artificial Intelligence · Cross-listed from cs.CL
Recognizing Dialogue Ambiguity via Candidate Set Visual Grounding
Shun Inadumi, Lee Sangmyeong and Koichiro Yoshino
Interpreting an ambiguous utterance in real-world interactions often requires context beyond a single utterance. When the utterance refers to objects in a visual scene, it is necessary to maintain and update the set of plausible referents as context accumulates, without assuming that the available information identifies a unique object. However, prior work on interactive visual grounding, which localizes objects referred to by linguistic expressions, has focused on identifying a unique object once sufficient dialogue context becomes available. To address this gap, we propose Candidate Set Visual Grounding (CSVG), a task for estimating the set of objects consistent with the given dialogue context. We further introduce CandVG, a
benchmark that evaluates how the candidate set changes across dialogue turns. Our evaluation of
vision-
language models shows that stronger visual grounding capability does not necessarily yield better CSVG performance. In particular, models have difficulty predicting the complete candidate set, owing to challenges in candidate generation and premature commitment to a small set of candidates in early turns. Nevertheless, we find that this limitation can be partially mitigated in the evaluated large-scale models using instructions designed for CSVG.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.SD
ONCship: A Large-Scale Underwater Acoustic Corpus for Ship Recognition
Zhe Cao, Jichao Zhang and Xiao-Lei Zhang
Recent advances in deep learning have significantly improved underwater acoustic vessel recognition. However, existing publicly available
datasets are typically limited in scale, hindering large-scale representation learning and downstream task evaluation. To address this limitation, we introduce ONCship, a large-scale underwater acoustic
dataset comprising 4521 hours of curated recordings from Ocean Networks Canada (ONC) hydrophones and Automatic Identification System (AIS) data. We evaluate the proposed
dataset across three tasks: self-supervised representation learning, vessel-type classification, and MMSI-Level Vessel Classification. Experiments on DeepShip and ShipsEar demonstrate the effectiveness of ONCship for acoustic representation learning, with joint pre-training on ONCship and AudioSet achieving a classification accuracy of 62.45% on DeepShip through linear probing. Furthermore, incorporating ONCship as auxiliary training data improves downstream vessel-type classification performance. Beyond conventional vessel-type classification, we further investigate MMSI-Level Vessel Classification, treating each vessel as a distinct identity. Experimental results show that models fine-tuned with different loss functions achieve Top-1 accuracies exceeding 53% and Top-5 accuracies approaching 69%, demonstrating the feasibility of distinguishing individual vessels through MMSI-Level Vessel Classification. Overall, ONCship provides a valuable resource for underwater acoustic representation learning and vessel recognition, while its rich vessel-level metadata enables further exploration of MMSI-Level Vessel Classification.
Read the full abstract ▾
Artificial Intelligence
Articulation Upper Bounds for Language Models
Alexander Spangher, Daniel E. Ho, Diyi Yang et al. (+2 more)
Language captures only a subset of the perceptions, intuitions and intents that form meaning between speakers. What, then, are the limits of
language? We take steps towards measuring this in LLMs as follows: for a set of concepts, we measure how well each concept can be transmitted between two LLMs as their capabilities scale. This requires novel measurement tools: (1) optimal messages: we introduce a
prompt optimization
algorithm that beats existing
algorithms by up to 14% on
benchmarks and accurately estimates
prompt upper bounds. (2) A transmission measure: the sender is asked to label text; the receiver then tries to recover the sender's
prompt, and recovery is measured; we find this correlates strongly with human label error. With these measures, we use observational scaling laws to study how transmissibility of a concept, conveyed with optimal messages, increases as transmitter and receiver capacity grows: does it asymptote below or above a threshold? Measuring 1.2k concepts in eight domains, we find concepts that (a) can be fully articulated; these concepts usually depend on local patterns, e.g. "joke ends with surprise"; (b) might be articulated by future, stronger models; these rely on whole-text structural patterns, e.g. "story's worldbuilding coherence"; (c) concepts that face articulability limits; these concepts' meaning, we find, is tied to identity and social-group awareness, e.g. "comic voice". Interesting, these same concepts are not all challenging for humans: humans have moderate-to-high levels of agreement in 76% of concepts that LLMs struggle with; articulation limits, we find, are executor relative. Finally, we characterize the nature of improvement in each case: while recoverable concepts can be articulated through definitions and explanations, irrecoverable concepts cannot be transmitted, even with examples, and might require novel learning mechanisms.
Read the full abstract ▾
All authors Alexander Spangher, Daniel E. Ho, Diyi Yang, Noah Goodman, Sanmi Koyejo
Artificial Intelligence
Learning Individual Scientific Taste with Privileged Hindsight Distillation
Hanwei Fan, Yanqiao Wang, Yiqi Zhu et al. (+3 more)
Scientific taste shapes which research directions researchers pursue, and it varies across individuals. Existing work evaluates research directions along multiple evaluation criteria or models scientific taste using community feedback signals such as citations and reviews, but neither directly captures how individuals translate assessments under the same criteria into different preferences. We model scientific taste as a researcher-specific mapping from criterion-level assessments in a shared, evidence-grounded evaluation space with proposal-visible evidence, to relative preferences. A population-level mapping learned from retrospective supervision provides a cold start when individual feedback is scarce. We introduce Privileged Hindsight
Distillation (PHD), which uses later-emerging scientific evidence during training to improve proposal-time criterion assessment and the population mapping, while exposing only proposal-visible information at inference. We evaluate our approach primarily in
quantum research, where structured public reviews are largely unavailable, and use pairwise proposal comparison as a direct interface for observing individual taste. With only 15 comparisons per researcher, our method captures sharply different tastes, including opposing preferences over the same research-direction pairs when they trade off across evaluation criteria. In an interactive study, personalized rankings also surface proposals associated with greater subsequent user engagement, connecting learned taste to downstream research exploration.
Read the full abstract ▾
All authors Hanwei Fan, Yanqiao Wang, Yiqi Zhu, Xuanyu Lei, Peng Li, Yang Liu
Artificial Intelligence · Cross-listed from cs.RO
Uncertainty-Driven Self-Play for Robust Multi-Agent Driving Policies
Sajad Marvi, Julian Schmidt, Alessandro Canevaro et al. (+2 more)
Learning robust driving policies that generalize beyond their training domain remains a central challenge in motion planning. We propose an uncertainty-driven self-play scheme, in which half of the
agents are rewarded for increasing their neighbors' epistemic uncertainty, while the other half learn to drive safely as the exploring
agents continuously seek out their weaknesses. Epistemic uncertainty indicates where the policy is least confident and serves as an automatic proxy for scenario difficulty. Exploring
agents use this signal to seek out hard cases, generating a challenging curriculum without manual scenario design. The resulting policy outperforms standard self-play, achieving best-in-class zero-shot transfer to nuplan Val14 (99.12% vs. 97.97%) and Argoverse 2 (82.39% vs. 78.03%) without fine-tuning, while also improving performance over standard self-play on Waymo. Our diversity-driven approach achieves 85% higher LSTM hidden-state coverage than the baseline, indicating a much richer set of behaviors. Further analysis shows that epistemic uncertainty serves as a calibrated difficulty detector, with highest-uncertain
agents exhibiting 14.8 times the combined failure rate across collision, off-road, and DNF, of lowest-uncertain
agents, enabling automatic prioritization of challenging scenarios without ground-truth labels.
Read the full abstract ▾
All authors Sajad Marvi, Julian Schmidt, Alessandro Canevaro, Julian Jordan, Abhinav Valada
Artificial Intelligence · Cross-listed from cs.LG
New Model, Old Habits: Behavior Transfer under Model Swapping in Multi-Session LLM Agents
Youngbin Choi, Sehyun Hwang, Suhyeon Jun et al. (+4 more)
Multi-session
agents can switch between LLMs to balance performance and inference cost. Such switches require transferring a history for continuity, yet their effects on the recipient remain underexplored. Through controlled experiments with multi-session tasks, we uncover behavior transfer: recipients tend to adopt
reasoning and action patterns from the models that generated their histories. This effect is most evident with raw-history transfer but is substantially reduced by summarization. Based on these findings, we propose Direction- and Authorship-aware Summarization of History (DASH) that preserves stronger-model behavior while minimizing weak-to-strong transfer via summarization. Experiments with repeated swaps show that DASH outperforms raw-history transfer and naive summarization baselines. These results suggest that effective multi-model orchestration requires considering not only which model to use, but also which behavioral patterns to carry forward.
Read the full abstract ▾
All authors Youngbin Choi, Sehyun Hwang, Suhyeon Jun, Seoyeon Lee, Sunghyun Choi, MoonJeong Park, Dongwoo Kim
Artificial Intelligence · Cross-listed from cs.CV
SceneAE: Scene Generation and Reconstruction in Queryable 3D-Anchored Latent Space
Shuofeng Sun, Wenzhao Zheng, Yunpeng Zhang et al. (+3 more)
Recent
video world models have increasingly adopted 3D
memory mechanisms to integrate historical observations into a lightweight and persistent scene representation. This naturally raises a complementary question: if 3D representations can serve as an effective mechanism for memorizing observed scenes, can they also be directly used as the latent space for reconstructing and generating scenes? Motivated by this idea, we represent a scene as a compact and unstructured 3D-anchored latent space (SceneAE). Each latent combines an explicit 3D position with an implicit content feature and is spatially grounded to describe its local scene region, forming a sparse latent point cloud. Unlike conventional
video-VAE latents that describe how a scene appears from particular viewpoints, our representation directly describes the scene itself, making it naturally applicable to both reconstruction and generation. For reconstruction, once the scene has been generated, our persistent 3D representation can be projected and decoded into RGB-D observations by different target cameras, without the need to regenerate a
video for each new camera trajectory. For generation, we leverage the geometry-content separation to first generate camera-controlled 3D geometry and then synthesize content conditioned on it, reducing camera-appearance
entanglement and improving camera controllability. Experiments show that this 3D latent achieves superior generation quality, computational cost, and camera controllability.
Read the full abstract ▾
All authors Shuofeng Sun, Wenzhao Zheng, Yunpeng Zhang, Yi Wu, Linqing Zhao, Haibin Yan
Artificial Intelligence
Runtime Monitoring of Supermartingale Certificates
Mirco Giacobbe, Thomas A. Henzinger, Konstantin Kueffner et al. (+2 more)
Supermartingale certificates formally guarantee temporal properties of discrete and continuous-time
stochastic dynamical systems. However, these guarantees rely on a mathematical model of the world, leaving a sim-to-real gap that can invalidate them for the deployed system. We formulate the runtime monitoring problem for supermartingale certificates, in which a monitor observes a single system trajectory and raises an alarm when there is sufficient statistical evidence that the supermartingale certificate has been violated during execution. We present an
algorithm to automatically construct a monitor using betting-based sequential tests that bound the probability of ever raising a false alarm at a user-specified level. Within this betting framework, we formulate strategies that allow the monitor to exploit spatial regularity to improve detection power while preserving this statistical guarantee. We demonstrate the efficacy of our approach on supermartingale certificate
benchmarks from the literature.
Read the full abstract ▾
All authors Mirco Giacobbe, Thomas A. Henzinger, Konstantin Kueffner, Emily Yu, \DJ{}or\dj{}e Žikelić
Artificial Intelligence
RuleTrek: Benchmarking Agentic Rule Reasoning in Complex Scenarios
Chenhao Yuan, Bohan Yu, Yinhao Xu et al. (+10 more)
Large
language models (LLMs) increasingly tackle complex real-world tasks in specialized domains. However, identifying and correctly applying domain-specific rules remains challenging when scenario information is distributed across multiple files. Existing rule-
reasoning benchmarks typically represent scenarios using only a few factual statements, simplifying the identification and application of relevant rules. To address this gap, this paper introduces RuleTrek, a multi-domain
benchmark for agentic rule
reasoning in complex scenarios. Its rule-grounded construction pipeline extracts structured rule graphs, generates and incrementally composes rule-specific sub-scenarios while ensuring consistency and solvability. To systematically evaluate agentic rule
reasoning in complex scenarios, RuleTrek assesses three capabilities in interactive workspaces: Rule Identification (RI), Rule Deduction (RD), and End-to-End Rule
Reasoning (E2E). Experiments on 11 frontier LLMs show that the highest RI and RD scores are only 62.47% and 60.43%, respectively, while E2E scores range from 26.97% to 55.29%. These results demonstrate that current LLM
agents face substantial challenges in rule
reasoning over complex scenarios. We make our code and
dataset publicly available at \href{https://github.com/yuan247/RuleTrek}{RuleTrek}.
Read the full abstract ▾
All authors Chenhao Yuan, Bohan Yu, Yinhao Xu, Chao Yin, Chenxi Zhou, Zhaoxuan Wang, Shuwen Xu, Shaoping Huang, Haolin Ren, Jiaxiang Liu, Yao Xu, Jun Zhao, Kang Liu
Artificial Intelligence
C3: Rethinking Process Supervision via Confidence-Guided Credit Correction in Multi-Turn Reinforcement Learning
Ai Jian, Haoran Pan, Eryu Guo et al. (+5 more)
Large
language models are increasingly trained as multi-turn
agents that interact with external tools. However, outcome-only reinforcement learning can produce a form of misguided reinforcement: even on successful trajectories, undesirable local behaviors may receive positive
token-level advantages and be favored by the policy update. To address this issue, we propose Confidence-Guided Credit Correction (C$^3$), a plug-in method for local credit correction. C$^3$ identifies spans corresponding to undesirable behaviors and selectively corrects positive credit after advantage estimation, with the correction strength adaptively controlled by the behavior policy's confidence in the corresponding behavior, while leaving the task reward and original credit estimation unchanged. Across multiple multi-turn
benchmarks, C$^3$ improves performance under both {critic-based and critic-free reinforcement learning methods}. Injecting the same behavioral signals as turn-level or outcome rewards does not consistently improve performance. Our results show that local credit correction provides an effective form of process supervision for outcome-driven RL.
Read the full abstract ▾
All authors Ai Jian, Haoran Pan, Eryu Guo, Haojin Yang, Jinghan He, Xiaoyun Zhang, Jiangbo Pei, Peiyu Liu
Artificial Intelligence
ReFormBench: Benchmarking the Stability of Response-Conditioned Format Correction in Large Language Models
Tianxiang Gao, Yahan Li, Chenlu Guo et al. (+3 more)
Reliable use of large
language models requires responses to satisfy formatting requirements across changing instructions. Standard compliance scores do not distinguish preserving a model's observed format from correcting it, or reveal whether that correction holds across variants. We introduce ReFormBench, a
benchmark that uses each model's unconstrained response to the same question as its formatting baseline. It links targets by feature and require/forbid mode, evaluating their instantiated requirements across variants. ReFormBench comprises 5,000 difficulty-screened three-constraint test instances derived from 910 source questions and covering 66 formatting features. TCPR measures complete instruction compliance, while EMCR measures individual and joint correction of targets opposed to the annotated baseline state. Across ten models, EMCR ranges from 34.04% to 64.72%, and the highest three-target correction estimate is 50.02%. Compliance and correction scores yield different model rankings and task-level profiles. A prompting experiment on Qwen3.5-9B improves both metrics, and the catalog covers over 95% of extracted instances on four additional models. ReFormBench makes response-conditioned correction across instruction variants a measurable dimension of format following. The code and data are available at https://anonymous.4open.science/r/ReFormBench/.
Read the full abstract ▾
All authors Tianxiang Gao, Yahan Li, Chenlu Guo, Diana Inkpen, Yi Chang, Yuan Wu
Artificial Intelligence · Cross-listed from cs.GT
PPAD-Completeness of Contiguous Envy-Free Cake Cutting with Additive Valuations
Yasushi Kawase, Bodhayan Roy and Mohammad Azharuddin Sanpui
We prove that computing a complete contiguous $\varepsilon$-envy-free cake allocation is PPAD-complete for normalized rational piecewise-constant additive valuations. The hardness holds even when $\varepsilon$ is given in unary, and even when every density takes only two values, which are the same for all
agents, and is piecewise constant with at most six breakpoints. As a consequence, computing an exact contiguous envy-free allocation is also PPAD-complete, and the hardness holds under the same restrictions on the densities. Our key ingredient is to assign prices to the pieces so that, in every approximately envy-free allocation, all prices are nearly equal, regardless of how the pieces are assigned to the
agents. We further show that, for every fixed integer $c\ge1$, computing a contiguous EF$c$ allocation of indivisible goods on a path is PPAD-complete for additive valuations, and the hardness holds even for binary valuations in which each good is valued by exactly one
agent and all
agents value the same number of goods.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.LG
Function-Space Temporal Self-Distillation for Policy Optimization
Aryan Das, Arnab Bhattacharya and Vinay Kumar Verma
Reinforcement Learning with Verifiable Rewards (RLVR) improves
reasoning in
language models, but scalar outcomes provide coarse supervision over response trajectories. Self-
distillation offers denser
token-level guidance by comparing an unassisted policy with a feedback-informed self-teacher, yet the teacher evolves with the student, creating unstable targets and motivating additional regularization. We introduce Function-Space Policy Optimization (FSPO), a single-policy framework that combines current privileged adaptation with function-space temporal consolidation. FSPO stores sparse historical next-
token distributions as fixed temporal targets, providing temporal separation without maintaining a persistent teacher model. It further introduces privileged disagreement correction to explicitly suppress locally overvalued actions, reliability-adaptive grounding that strengthens reference supervision when self-generated evidence repeatedly fails, and quality and coverage-aware temporal
memory that retains verified behaviors and improves privileged demonstrations. Across
reasoning and tool-use
benchmarks, FSPO achieves the highest average accuracy under a 5-hour training budget, improving over the strongest baseline by approximately 4% points on average while reducing peak
memory from about 70 GB to 56 GB on Olmo3-7B-Instruct.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CL
Interlock: From Local Correctness to Task Completion in Long-Horizon Agents
Linji Hao, Yanji He, Zihan Wang et al. (+6 more)
Large
language model
agents increasingly undertake long-horizon tasks in complex environments characterized by fragmented evidence, partially completed states, and dependencies across resources and artifacts. Existing
agents may satisfy individual requirements while failing to maintain these relationships, producing locally correct but incomplete outcomes. These failures arise because task completion depends on relationships among environmental evidence, consequential decisions, and required effects. To address this completion gap, we propose Interlock, a framework for task synthesis that represents each task as a typed completion graph. Grounding edges connect public evidence to decisions, coupling hyperedges impose joint constraints across components, and realization edges connect decisions to all required downstream effects. Interlock compiles this graph into a resettable workspace, a public request, and an evaluation rubric. A source-coverage review checks whether the original requirements survive generation, while a public-input review checks whether the rubric is supported by the materials available to the solver. An
agent-as-judge inspects execution artifacts and runs verification scripts, retaining trajectories judged to satisfy all mandatory requirements. To evaluate training utility, we fine-tune two Qwen3.6 backbones on their own accepted trajectories. Across the two backbones, training improves AutomationBench task pass rates by 4.00-4.50 percentage points, JobBench weighted scores by 3.20-6.64 points, and Harvey LAB criterion pass rates by 3.89-4.16 percentage points. These results demonstrate the training utility of the synthesized experience across external task environments.
Read the full abstract ▾
All authors Linji Hao, Yanji He, Zihan Wang, Hansi Yang, Jiayuan Zhang, Hongyan Hao, Qi Gu, Yan Feng, Han Wu
Artificial Intelligence
MCAIR: Monitoring and Correcting Agent Unfaithfulness via Internal Representations
Yan Xu, Dandan Song, Luan Zhang et al. (+8 more)
Large
Language Model (LLM)-based
agents have demonstrated remarkable capabilities in completing complex tasks through multi-step
reasoning and tool interactions. However, recent studies have revealed that LLM-based
agents can exhibit unfaithful behaviors, where their final reports fail to faithfully reflect their actual execution trajectories. Specifically, when
agents fail to accomplish tasks through the intended sources or procedures, they may resort to alternative sources or strategies while failing to disclose such deviations, leading users to incorrectly believe that the tasks have been completed according to the original requirements. We refer to this specific form of
agent unfaithfulness as
Agent Completion Unfaithfulness. Detecting and mitigating
agent completion unfaithfulness is critical yet remains largely unexplored. In this work, we propose MCAIR, a runtime monitoring and correction framework that leverages internal representations of LLM-based
agents. MCAIR uses multi-step internal representations as inputs to train a risk-aware probe, enabling online detection of potential completion unfaithfulness during execution. Furthermore, MCAIR introduces a risk-guided correction loop that
prompts agents to review their execution history and mitigate potential inconsistencies between their execution trajectories and final reports. Additionally, we construct ACUD, a
dataset for
Agent Completion Unfaithfulness detection that provides step-level execution traces, step-level internal representations, and consistency annotations for training and evaluating runtime detection probes. Experiments demonstrate that MCAIR outperforms LLM-as-a-judge baselines, generalizes across
prompts and tasks, and effectively reduces
agent completion unfaithfulness.
Read the full abstract ▾
All authors Yan Xu, Dandan Song, Luan Zhang, Jun Yang, Ke Duan, Yuhang Tian, Yading Li, Xudong Li, Xing Pei, Guangyuan Feng, Chenhao Li
Artificial Intelligence
Learning When to Trust Medical Knowledge: Regression-Safe Routing for Clinical Reasoning
Hui Zhang, Yujia Zeng and Yuhao Xin
Clinical
reasoning LLMs need external medical knowledge, but retrieved evidence and
reasoning chains can be outdated, poisoned, or hallucinated. Harmful knowledge can cause regression: changing a correct answer into an incorrect one. We construct a medical knowledge-poisoning
benchmark covering retrieved evidence and
reasoning chains, with seven attack families filtered by a three-judge "subtle-but-wrong" vote and paired clean exams that separate poisoning effects from question difficulty. No fixed knowledge-use strategy is robust across these settings: strong RAG methods trade robustness to poisoned evidence against accuracy when evidence is useful. We formulate knowledge use as per-instance routing and introduce Med-TrustRouter, a lightweight controller that keeps the solver frozen. From leakage-free runtime signals, it estimates each action's expected correctness gain and uncertainty, preserving the base answer unless another action is confidently better. Across seven medical
reasoning settings, Med-TrustRouter achieves 78.9 macro and 69.2 worst-case accuracy, matching the strongest competitor on macro accuracy while substantially improving the worst-case floor. Its gains transfer across solvers and evidence judges, unlike a hand-coded router using the same signals. Similar performance across linear, tree, and neural action-value heads suggests that the benefit comes from routing rather than
estimator complexity. These results support learning when to trust external knowledge for robust clinical
reasoning.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CL
Measuring and Reducing Unusable Replies of LLM Agents
Yilin Jiang, Fei Tan, Xuanyu Yin et al. (+3 more)
People delegate multi-step work to LLM
agents and read only the reply that the
agent hands back. Current evaluation scores task completion and the faithfulness of reports, and it leaves open whether the requester can understand and use the reply. We call this property reply usability and measure it with a reader model that takes the requester's position and tests whether the reply can be interpreted from what the requester has seen, is in the requester's
language and answers the request. Its agreement with the majority of five annotators lies within the range of the individual annotators. Across eight models from seven families, 54% of 480 replies fail, and the best model still fails on 30%. Failed replies mostly point to material the requester has not seen or use labels that the
agent coined during its work. Stating explicit requirements for the reply reduces the failure rate from 0.52 to 0.43 together with errors and omissions, and a secondary model that rewrites the reply reduces it to 0.36, which human annotators confirm in a blind comparison. Reply usability can thus be scored alongside task success and improved with one appended message or one call to a secondary model.
Read the full abstract ▾
All authors Yilin Jiang, Fei Tan, Xuanyu Yin, Guanchu Wang, Xia Hu, Yutao Yue
Artificial Intelligence · Cross-listed from cs.CL
HACHIMI-II: From Role-Play to Learner Behavior Modeling for Faithful Student Simulation
Yilin Jiang, Fei Tan, Xuanyu Yin et al. (+2 more)
Simulated students let researchers test tutoring systems and teaching strategies before real learners are available, but only if the simulation reproduces where a particular learner succeeds and fails. The common approach asks a large
language model to role-play a student, but a role does not model what this learner knows or will do next, so the model's own competence fills the gap. Simulated students perform at a level set by the model, differ little from one another, and seldom make the real learners' errors. We model the learner's behavior and recast student simulation as third-person prediction of the learner's next action. HACHIMI-II builds a student model from the learner's history, infers the learner's state for the current item or tutor turn, and compiles it into a behavior harness that constrains the next action. On three item-response
datasets, the Wasserstein-1 distance between simulated and real student ability is 2.4–8.4$\times$ smaller than that of the strongest baseline. On two dialogue
datasets, HACHIMI-II reproduces real student errors with the same knowledge type, locus, and mechanism 1.8–5.1$\times$ more often than the strongest baseline, and ablations trace the gains mainly to the explicit learner state. Predicting the learner makes capable models usable as simulated students.
Read the full abstract ▾
All authors Yilin Jiang, Fei Tan, Xuanyu Yin, Jing Leng, Aimin Zhou
Artificial Intelligence · Cross-listed from cs.CR
AWARE-RG: Abstraction Aware Explanation of Resiliency Graphs for Cyber Physical Systems
Shadaab Kawnain Bashir, Rakesh Podder, Philip D. Hopkins et al. (+3 more)
Understanding the security posture of cyber physical systems (CPS) requires
reasoning across both information technology (IT) and operational technology (OT). However, a security analyst often holds an incomplete, role-specific view of the underlying system which has most likely resulted from their knowledge limited by a need-to-know framework. Such an incomplete view can potentially lead them to incorrectly assess if a cyber attack produces an untoward physical consequence resulting in making uninformed decisions about system resilience. In this work, we present AWARE-RG (Abstraction Aware Explanation of Resiliency Graphs), a semi-automated, human-in-the-loop framework that provides an analyst with a role-bounded, need-to-know explanations of resiliency paths in a CPS. The AWARE-RG abstraction structure is derived using Formal Concept Analysis over MITRE ATT&CK for ICS tactics, ordered by the ICS Cyber Kill Chain. For valid attack-fault queries, plan repair and backward means-end analysis identify the missing dependencies, explain why the physical hazard is reachable, and suggest defensive strategies. For invalid attack-fault queries, AWARE-RG localizes the first abstraction level at which the path fails, and reports confirmed blocking conditions as hardening pointers.
Read the full abstract ▾
All authors Shadaab Kawnain Bashir, Rakesh Podder, Philip D. Hopkins, Sarath Sreedharan, Indrakshi Ray, Indrajit Ray
Artificial Intelligence
Model What Matters: Decision-Guided Selective World Modeling for Language Agents
Maolin Ran, Minda Chen, Di Huang et al. (+3 more)
Reinforcement learning provides a direct mechanism for optimizing task objectives in large
language model-driven
agents, but task rewards are typically sparse trajectory-level signals that only evaluate task success, without directly supervising action-conditioned environment transitions, leaving the model with limited explicit understanding of action consequences and environment dynamics. Recent work introduces auxiliary supervision through policy and world modeling co-training, yet typically treats complete environmental observations uniformly as world modeling targets, overlooking the varying decision relevance of observation content. We propose DGS-WM (Decision-Guided Selective World Modeling), a decision-guided policy-world modeling co-training approach for
language agents. DGS-WM employs a Decision-Guided Observation Selection component that filters observation units with decision value as world modeling targets based on their support for subsequent policy responses, and a Confidence-Adaptive Weighting component that adaptively adjusts supervision strength according to the model's prediction confidence on selected targets. Together, these components form a decision-aware auxiliary world modeling loss, jointly optimized with the RL loss on the same policy model. Across multiple
benchmarks covering single-hop/multi-hop question answering and interactive web tasks, DGS-WM achieves consistent improvements under different model scales and RL
algorithms, demonstrating more stable and effective performance compared to full-observation world modeling methods.
Read the full abstract ▾
All authors Maolin Ran, Minda Chen, Di Huang, Wei Xiong, Fei Huang, Weiwen Liu
Artificial Intelligence · Cross-listed from cs.LG
Sparse Autoencoders Are a Shared Coordinate System for Symbolic Matching
Xiaocong Yang, Xuanyu Meng, Yuji Zhang et al. (+2 more)
Large
language models (LLMs) hold broad knowledge in one set of weights, but lack interpretability and trustworthy
reasoning, especially in high-stakes use cases. A neuro-symbolic model, with its interpretable architecture and System 2
reasoning capacity, is a promising alternative if built at the scale of LLMs; however, its symbolic backbone is usually constructed with human effort, so existing neuro-symbolic models are bottlenecked by the scope of the symbol component and usually domain-specific. A data-driven method could instead build a larger symbolic system by aligning and merging existing ones. We target its first, foundational step: matching units across these heterogeneous systems. Our method, SAE-IDF, encodes a symbol in its native context into a sparse code with a sparse autoencoder (SAE), re-weights each dimension by its rarity and matches across systems. On 12 tasks across 6 kinds of symbolic system, SAE-IDF outperforms the same LLM's dense baseline on all tasks with Gemma-2-9B and all but one with Llama-3.1-8B, by up to 45 points, consistently across SAE layers and configurations. SAE-IDF is also interpretable: every dimension of the sparse code has a human-readable meaning, so each match decomposes into named concepts (features). Our work paves the way to a universal symbolic backbone.
Read the full abstract ▾
All authors Xiaocong Yang, Xuanyu Meng, Yuji Zhang, Jiawei Han, ChengXiang Zhai
Artificial Intelligence · Cross-listed from cs.RO
Eye, Robot: Learning Expressive Gaze Dynamics via a VLM-Guided Transformer-VAE
Yuhang Hu, Junlin Lyu, Yuan Fang et al. (+6 more)
Gaze coordinates
attention in human interaction through coupled eye, head, and eyelid motion. A humanoid
robot must choose where to look while generating a suitable movement toward that target; fixed tracking rules alone do not model the temporal structure of human gaze. We separate these tasks with an asynchronous
vision-
language model that selects a scene referent, a reactive perception module that maintains fixation, and a Realistic Gaze
Transformer (RGT) that generates target-conditioned motion. RGT is a
Transformer-VAE trained on markerless human recordings retargeted to the
robot's 11-DoF joint space: self-supervised pretraining encodes recent full-head history, and autoregressive fine-tuning exposes the model to its own predictions during rollout. At inference, a four-dimensional binocular-eye trajectory conditions coordinated neck and eye motion; an auxiliary blink predictor triggers eyelid templates during playback. On a two-second
benchmark in which all controllers receive the same ground-truth target, RGT-Base obtains the lowest reported overall seven-joint MSE, and physical demonstrations show the integrated targeting and control pipeline. The evidence establishes
robot-space kinematic fidelity and real-time RGT inference; perceived naturalness and open-vocabulary target-selection accuracy remain questions for controlled evaluation.
Read the full abstract ▾
All authors Yuhang Hu, Junlin Lyu, Yuan Fang, Xiaoying Shen, Lechen Zhang, Jiong Lin, Judah Goldfeder, Steven Tian, Hod Lipson
Artificial Intelligence · Cross-listed from cs.CL
DAGFormer: Global Topology Prediction for Transformer Cross-Layer Connections
Xiaocong Yang, Yuren Hao and ChengXiang Zhai
We propose DAGFormer, a
Transformer language model whose cross-layer connections are planned by a jointly trained
topology predictor. Beyond the residual connections in a standard
Transformer, DAGFormer adds direct connections from earlier layers to later ones, and the predictor controls the strength of every connection based on input
tokens. Unlike existing cross-layer routing architectures, which set each layer's connections separately, DAGFormer plans the routing of the whole model at once. On matched OLMo-2 pairs from 75M to 1B parameters, DAGFormer lowers WikiText-2 perplexity by 17% to 25% over the vanilla
Transformer, and a 1B DAGFormer trained on 5B
tokens outperforms the vanilla model trained on 10B. Against four routing baselines with the same data and budget, it reaches the lowest perplexity at 75M, 300M and 1B. The gain carries over to 13 commonsense, science, reading and math evaluation tasks (2.0 to 2.5 points higher mean accuracy at 300M and 1B) and to instruction finetuning (63% to 70% AlpacaEval win rate against the vanilla
Transformer, leading every routing baseline), and under structured
pruning DAGFormer degrades the least in five of six settings.
Read the full abstract ▾
Artificial Intelligence
Are AI Decision Models Biased? A Case Study of Jev
Ilaria Imperatrice, Taisia Kameneva, Adam Eric Greenberg et al. (+1 more)
Do AI models designed for fast, structured decisions exhibit the cognitive and social biases observed in human judgment? We evaluate Jev, a model described as a System One decision-maker, using 41,500 responses across cognitive reflection tasks, five classical cognitive-bias paradigms, and a pricing experiment testing ethnic and gender bias. At the level of selected answers, the results are largely encouraging. We confirm previous findings that Jev performs extremely well on cognitive reflection problems. We also observe that it generally avoids the characteristic choice patterns associated with several well-documented human biases, and exhibits only small differences among demographic groups in the tested pricing scenario. However, this apparent robustness conceals important vulnerabilities. Its judgments are sensitive to irrelevant numerical information and the ordering of response options. Moreover, several cognitive-bias manipulations substantially affect returned probabilities even when selected answers remain unchanged. Most strikingly, Jev answers a well-known probability problem correctly in every response but violates the same underlying probability rule in every response to an adapted version. We investigate this discrepancy using 15,000 additional responses across 30 conjunction tasks. Jev violates the rule in 54% of responses, with accuracy varying dramatically across formulations and answer orders. These findings suggest that evaluating decision models solely on familiar
benchmarks and selected answers may substantially overstate their reliability in practical applications. They also identify vulnerabilities for developers to address and practical considerations for users integrating such models into automated decision-making systems.
Read the full abstract ▾
All authors Ilaria Imperatrice, Taisia Kameneva, Adam Eric Greenberg, Alessandro Romano
Artificial Intelligence · Cross-listed from cs.RO
Instruction-Conditioned Motion Control for Robotic Arms: Language-to-Code Decomposition and Reinforcement Learning
Fan Huang, Dezhong Tong, Changyu Chen et al. (+2 more)
Instruction-Conditioned Motion Control (ICMC) separates parameter specification, instruction generation, and code synthesis for
language-driven
robot control, making execution outcomes traceable to instructions and programs. We compare one-shot generation with ICMC under o1 and o4-mini on cube pick-and-place and letter-reshaping tasks for a UR5e arm in MuJoCo. We then train an open-weight instruction policy by GRPO through a frozen code generator on cube placement onto two- and five-cube letter layouts, averaging the rewards of five programs per instruction. The logged positive-reward rate rose from 31.6% to 35.3% (253/800 to 282/800) between the first and last five training steps. A log audit identifies positive binary labels associated with
geometric-failure messages: at least 19 in that run, 18 in the dense-reward run, and 5 in the run with one program per instruction. In one case, all five rewards were 1.0 while the log reports a 0.9515 m miss against a 0.05 m tolerance; the verdict came from the program's own output stream. We distinguish logged reward rates from independently verified task success and report descriptive results for each configuration's single training trajectory. We introduce an independent evaluation protocol that checks task completion against fixed specifications, separating
robot control from success assessment to support reproducible evaluation.
Read the full abstract ▾
All authors Fan Huang, Dezhong Tong, Changyu Chen, Haewoon Kwak, Jisun An
Artificial Intelligence · Cross-listed from cs.LG
Divergent Paths: Learning an Outcome-Predictive Representation of LLM Agent Trajectories
Alexander Gill, Guram Gogia and Francisco Guzmán
In this work, we reframe agentic trajectories as paths through a shared
embedding space of actions and environmental observations. We show that successful and failed rollouts of the same task separate in this space, with simple per-task discriminators predicting held-out rollout outcomes at up to 0.95 AUROC across three
agent benchmarks and three policy models. To exploit this signal across tasks, we introduce Precog-RM, a
transformer-based model that meta-learns a representation in which outcome prediction can be performed in a few-shot setting. We show that Precog-RM generalizes to unseen tasks and models, and gives confident predictions of trajectory success long before termination. Deployed as an early stopping controller for Group Relative Policy Optimization (GRPO) on Tau2-Bench, Precog-RM cuts training FLOPs by up to 47.3% while maintaining performance comparable to baseline GRPO.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.LG
Beyond Static Positional Encoding: Bayesian Time-aware Attention for Non-Stationary Long-term Time Series Forecasting
Xinjie Lan, Yunbo Mei, Leheng Zhou et al. (+1 more)
Transformers have demonstrated strong performance in long-term time series forecasting (LTSF), yet modeling non-stationary temporal dependencies remains challenging. In this paper, we interpret self-
attention as a
Bayesian posterior over attended positions, combining a content-based prior induced by scaled dot-product similarity with a temporal-evidence likelihood induced by positional encoding. This formulation provides a probabilistic interpretation of how positional encoding shapes the temporal dependencies captured by self-
attention. Building on this perspective, we derive a population-level evidence lower bound (ELBO) that characterizes the role of positional encoding in forecasting weakly stationary time series. Our analysis further highlights a limitation of static positional encoding: when temporal dependence structures vary across input windows, a fixed temporal bias must accommodate heterogeneous dynamics and can therefore be suboptimal for non-stationary forecasting. Motivated by this analysis, we propose
Bayesian Time-aware
Attention (BTA), which employs a mixture-of-experts (MoE) router to adaptively combine temporal kernels and generate input-conditioned, head-specific positional biases. Extensive experiments on standard LTSF
benchmarks demonstrate that BTA consistently improves forecasting performance across multiple
Transformer backbones and achieves competitive overall performance with modest computational overhead and stable training.
Read the full abstract ▾
All authors Xinjie Lan, Yunbo Mei, Leheng Zhou, Hao Qi