Artificial Intelligence
When Better Gets Worse: Improvement Fidelity for Self-Improving Agents in Adaptive Worlds
Ke Wang, Zijie Zhao, Zhiyi Yuan et al. (+1 more)
Self-improving
agents increasingly rely on proxy verifiers to choose policy updates, yet deployment can change the world in which those updates are evaluated. An update that looks better to the verifier can therefore become worse after deployment even when the verifier ranks policies well overall. We formalize this gap as Improvement Fidelity, which asks whether proxy improvements preserve the sign and ordering of deployment improvements over the updates an improvement process actually proposes. We show that global policy accuracy need not guarantee update fidelity: operator shift and deployment response can create update-level errors, while candidate margins determine whether those errors change the replacement decision. We introduce PIVOT-KG, a paired, decision-aware validator that allocates scarce high-fidelity evaluation according to the expected reduction in selection regret per unit cost. Across 90 held-out roots in Leduc, Kuhn, and Melting Pot, proxy and deployment optimal sets are disjoint in 51 cases. In an eight-candidate HighwayEnv stress test, PIVOT-KG reduces mean improvement-selection regret from 0.0435 under the exact Uniform validation rule to 0.0055 at the primary budget. Together, these results show why reliable self-improvement should evaluate proposed improvements in the worlds they induce, while providing a practical rule for allocating scarce deployment evidence when it can affect the replacement decision.
Read the full abstract ▾
All authors Ke Wang, Zijie Zhao, Zhiyi Yuan, Changlun Li
Artificial Intelligence
Expected Reasoning-Step Return Unifies On-Policy Learning from Rewards and Teachers
Qiangqiang He and Jin Li
On-policy
reasoning models can learn from task rewards or teacher signals, but these sources differ in form and can favor conflicting updates, leaving unclear which should guide a given
reasoning action. We introduce Expected
Reasoning-Step Return (ERSR), which treats semantic
reasoning steps as macro-actions and uses Monte Carlo student-policy rollouts to estimate the expected final task reward of student-generated and teacher-proposed actions in a common return space for step-level comparison. ERSR analysis reveals an outcome-dependent asymmetry: student actions are more beneficial than teacher replacements on successful trajectories, whereas teacher replacements become more beneficial on failed trajectories. We further show that student answer-probe gains track student-step ERSR utility and distinguish beneficial from harmful
reasoning steps. Based on these findings, we propose \textbf{Return-Referenced On-Policy Learning (R$^2$OPL)}, which reinforces student
reasoning on successful trajectories and distills teacher signals on failed ones, while using group success rate for difficulty scaling and student-probe gains for step-level modulation. Experiments across
reasoning benchmarks and teacher–student configurations show that R$^2$OPL consistently outperforms strong baselines. ERSR training dynamics further show that R$^2$OPL jointly exploits substantial utility from both reward- and teacher-side signals, whereas existing hybrids often leave substantial residual utility in one branch.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.LG
STAMP: Predicting Out-of-Distribution Generalization without Target Data
Md Kawsher Mahbub and Milon Biswas
Predicting whether a trained model will generalize under distribution shift remains difficult, especially when target-domain data are unavailable. We introduce STAMP (Semantic Temporal Augmented Model Prediction), a source-only, target-label-free criterion that estimates out-of-distribution (OOD) performance from paired source-domain images. STAMP computes the output-space correlation ratio $\eta^2=S_B/S_T$ by contrasting semantically stable pairs with random pairs: higher $\eta^2$ indicates that model outputs vary with semantic identity rather than nuisance variation. On 44 chest X-ray models spanning CNNs, ViTs, MetaFormers, foundation models, and SSL/VLM probes, temporal STAMP attains Spearman correlations of $0.844$–$0.855$ with macro AUROC on VinDr-CXR, CheXpert, and MIMIC-CXR; a class-matched variant improves single-class RSNA from $0.311$ to $0.663$. STAMP attains the best average source-only medical ranking and outperforms the target-domain ATC and AoTL
estimators without any target data. On 27 ImageNet models, temperature-scaled STAMPTS attains $\rho{=}0.984$ on ObjectNet and $\rho\geq0.905$ on four additional distribution shifts, with partial correlations of $0.662$–$0.949$ after controlling for ImageNet accuracy. Requiring approximately 12s per model on one GPU, STAMP is a practical pre-deployment model-selection and
auditing tool.
Read the full abstract ▾
Artificial Intelligence
What Would Falsify It? A Variable Specific Evidence Standard for Mechanistic Claims About Self Explanation
Arshia Eftekhari zadeh
When a
language model explains an answer it has already given, does it reuse the computation that produced the answer or reconstruct a story from the answer alone? Attribution, transportability and recoverability are each compatible with causal use without establishing it. We propose an evidence standard: pair each positive statistic with a variable specific null that removes the tested variable's identity while matching relevant nuisance dimensions as far as possible, and audit unmatched dimensions. We apply this standard to a known cause. A cue naming a wrong option raises the rate of choosing that option by 64 to 68 percentage points across three models. Explanations mention the cue in 1.8 percent of items or fewer in three of four models tested. Three
estimator classes yield favorable statistics, but none establishes causal sensitivity to the cue contrast under its own control in the three-model analysis. In the strongest case, a recovered cue direction reaches $R^2$ of 0.95 and exceeds a geometry matched random direction in all three seeds, while a direction fitted by the same pipeline with cue labels scrambled reproduces 61 to 76 percent of its effect at comparable realized edit magnitude. A fourth model passes one interchange endpoint, but unequal edit magnitudes and a contrast that changes both cue identity and cue-answer agreement limit its interpretation. These experiments leave causal access unresolved. They establish an evidentiary requirement: favorable mechanistic statistics must survive controls for variable identity and nuisance structure. Reusable controls separate generic from identity specific transport effects, fit null directions with scrambled labels, and audit realized intervention magnitudes.
Read the full abstract ▾
Artificial Intelligence
Yuhao Du and Shunian Chen
Attention weights depend on
token counts, which change with the representation of a signal. We study refinement
symmetry: splitting a representation while preserving content, position, visible context, and total mass should preserve its contribution. Building on proportional and quadrature
attention, we show that split invariance forces the local mass factor to be linear for any fixed positive
attention kernel, provided that factor is nondecreasing. For changed representations, a physical coupling bounds
attention error by separating feature change from weight reallocation. In Qwen2.5-Omni-7B, duplicating half the visual
tokens threefold changes 255 of 3,586 MVBench answers under standard
attention; measure weighting preserves every answer under matched visibility. Under natural frame resampling, it reduces distributional drift. At twofold merging of a frozen
video encoding, a five-seed evaluation shows an all-partition-correct accuracy gain of 1.04 percentage points over global count weighting (average group mass) and 0.93 points over standard
attention. The advantage over global count also holds on WorldSense but depends on the compression budget. The result is a representation principle with a measured benefit in robustness across partitions.
Read the full abstract ▾
Artificial Intelligence
Learning from a Thoughtful Teacher: Adaptive On-Policy Self-Distillation for Mathematical Reasoning
Jiacheng Du, Weiwei Xie, Tianyi Du et al. (+3 more)
On-policy self-
distillation (OPSD) trains a question-only student with
token-level feedback from a teacher given training-only privileged information (PI). OPSD therefore provides dense, on-policy supervision, and is free of a larger external teacher, but its effectiveness rests on how PI is designed and utilized. Our preliminary diagnostics suggest a significant gap between teacher utility and student learnability, where a small fraction of high-disagreement
tokens dominate the
distillation signal, and short teacher continuations at these positions further expose more explicit PI leakage than transferable correction cues, indicating a strong intent on injecting PI-conditioned shortcuts. We propose Adaptive On-Policy Self-
Distillation (AOPSD), which adapts what information the teacher receives and how strongly its feedback influences learning. AOPSD encodes each solution as a
reasoning DAG, orders problems by the student's evolving capability, and reveals only the affordable subgraph and its next frontier as PI. For high-disagreement
tokens, AOPSD utilizes short teacher continuations as probes to encourage useful guidance while mitigating PI-conditioned shortcuts among teacher supervisions. On HMMT25, AIME24, AIME25, and BRUMo25, AOPSD achieves 72.5% Pass@8, which is 6.7 percentage points above OPSD and 4.2 above the strongest competing baseline while reducing 15 percentage points of training time at lower cost.
Read the full abstract ▾
All authors Jiacheng Du, Weiwei Xie, Tianyi Du, Shaoxiong Guo, Qibing Ren, Jiaheng Zhang
Artificial Intelligence · Cross-listed from cs.LG
Timestep Weighting: A Hidden Key to Effective ELBO-Based Flow-Matching RL
Qinwei Ma, Jingzhe Shi, Simin Fan et al. (+2 more)
ELBO-based reinforcement learning offers a sampler-agnostic approach to fine-tuning flow matching models with reward feedback. Timestep weighting in ELBO-based RL has large impact on performance, and it also provides a unified view (as we show in this work) to understand prediction losses heuristically chosen in prior work, yet it remains under-researched and is often chosen to inherit pretrain configs. We investigate impacts and dynamics of timestep weighting in ELBO-based RL. We show that effective weighting depends on both the reward landscape and stage of learning. (1) Through experiments on controlled CIFAR image generation, complemented by robotics, we investigate how weighting impacts reward-driven updates across noise levels. (2) Through gradient analysis, we reveal distinct patterns of cross-noise coordination across tasks and their
evolution during training. These findings motivate the hypothesis that useful weighting depends on the gap between the policy's current behavior and the behavior favored by the reward. (3) Guided by this analysis, we study simple static weighting, budgeted profile selection, and dynamic schedules that improve performance beyond conventional target choices. Our results establish timestep weighting as an important design choice for flow-matching RL and motivate further research into methods that choose and adapt it throughout learning.
Read the full abstract ▾
All authors Qinwei Ma, Jingzhe Shi, Simin Fan, Ling Li, Alex Lamb
Artificial Intelligence · Cross-listed from cs.SE
AsynCodeBench: Benchmarking Collaboration of Asynchronous Multi-Agent Systems in Software Engineering
Kaituo Zhang, Zhen Xiong, Zhimeng Jiang et al. (+8 more)
Multi-
agent coding has emerged as an increasingly active direction in software engineering, where complex development tasks are decomposed across multiple specialized
agents working on different parts of the problem. Despite the shift from individual problem solving to distributed collaboration, multi-
agent systems still lack a direct measure of collaboration and are largely evaluated through task-level outcomes inherited from single-
agent coding, conflating individual coding capability with cross-
agent coordination. We introduce AsynCodeBench, a dependency-centric
benchmark for asynchronous multi-
agent software engineering that represents each task with an explicit dependency graph and executable Dependency Checkers. Through this dependency-tracking process, we propose two complementary measures: Asynchronous Dependency Pass Rate (ADPR), which measures how many cross-
agent dependencies are ultimately satisfied, and Dependency Resolution Step (DRS), which measures when each dependency first becomes satisfied during execution. AsynCodeBench comprises 19 tasks from real-world repositories, exposing 52 directed dependencies as explicit units for evaluating cross-
agent collaboration. Experiments across model families, scales, and generations reveal a clear gap between coding and collaboration capability: improvements in coding performance do not necessarily translate into stronger collaboration, and task-level metrics can diverge substantially from dependency-level collaboration measures. Dependency-trajectory analysis further reveals that successful coordination often emerges not gradually, but through concentrated bursts in which many dependencies become resolved over a short portion of the execution trajectory, a pattern we term a hopping window.
Read the full abstract ▾
All authors Kaituo Zhang, Zhen Xiong, Zhimeng Jiang, Mingyu Zhong, Zhouyuan Yuan, Zhecheng Li, Bowen Lin, Chia-Yuan Chang, Mingzhi Hu, Huazheng Wang, Ying Lin
Artificial Intelligence · Cross-listed from cs.CV
InterTab: Interleaved Visual-Structure Alignment for Multi-Modal Table Reasoning
Hanqian Li, Sirui Huang, Chen Ling et al. (+12 more)
Table images preserve structural information that are often lost in text serialization, and
reasoning over them requires locating relevant rows, columns, and
cells step by step. Current
multimodal large
language models (MLLMs) encode the whole image once before
reasoning, so they cannot pick up row-, column-, and
cell-level evidence as the question unfolds. Encoder-side table structure and generic interleaved visual chain-of-thought still do not bind each
reasoning step to that structure. We propose InterTab, an Interleaved structure-aware framework for CoT
reasoning over Table images, interleaves chain-of-thought with tool calls that crop structure-aligned table regions. First, we build InterTab-22K, includes
reasoning trajectories in which each step is tied to both a structural location and a bounding box. InterTab is trained in two stages: supervised structure-aware
alignment (SSA) on InterTab-22K teaches the model to interleave
reasoning with structure-aligned crops, and active localization optimization (ALO) further optimizes answer correctness, localization IoU, and output format, while penalizing missing or excessive tool calls. Experiments on nine table
benchmarks show that InterTab improves the average accuracy of its backbone from 68.28% to 73.17% and achieves the best average performance among all compared methods. Code and data will be released soon.
Read the full abstract ▾
All authors Hanqian Li, Sirui Huang, Chen Ling, Jungang Li, Yu Huang, Kening Zheng, Yonghua Hei, Xiangrong He, Shiyi Wang, Pengcheng Zhu, Dongnan Liu, Wei Zhou, Linjian Mo, Nai Ding, Xuming Hu
Artificial Intelligence
Contract Memory Compiler: Resolve, Then Traverse
Zhi Song, XiMing Xing, Chunhan Li et al. (+9 more)
External
memory lets
language-model
agents answer questions about histories too long for the answer model's context window. Updates create a harder problem than retrieving a recent fact: changing one relation can redirect a multi-hop question to records about an entity absent from the question. We study this update-dependent evidence selection problem and introduce the Contract
Memory Compiler (CMC). Before seeing a question, CMC uses a
language model to identify relations in the history and record where each one was stated. It applies later updates to determine the current relations, follows them from entities named in the question, and passes the corresponding original records to the answer model in one call. Thus the current state determines which evidence is read, rather than merely refreshing values in a previously selected context. To the best of our knowledge, CMC achieves state-of-the-art multi-hop accuracy on FactConsolidation, reaching 78.25% overall and 61.0% at 262K. With the extracted relations and answer model held fixed, selecting evidence before resolving updates reduces multi-hop accuracy to 21.50%. We also introduce MQuAKE-MemStream, a derived
dataset of ordered
memory streams built from MQuAKE-Remastered counterfactual cases.
Read the full abstract ▾
All authors Zhi Song, XiMing Xing, Chunhan Li, Weian Mao, Zhenchao Tang, Hanbo Huang, Fan Xu, Jiale Zhou, Jiahui Guan, Zejian Ding, Chen Ma, Lusheng Wang
Artificial Intelligence
World Models with Predictable Long-Horizon Marginals
Yuhao Du and Shunian Chen
Accurate one-step predictions do not ensure that a world model's rollouts retain the data distribution. We make the model's decoded stationary law explicit by learning a decoder of a fixed Gaussian reference and constraining the behaviour-averaged transition to preserve that reference. For controlled systems, a joint transition uses a conditional action chart to preserve behaviour occupancy without requiring invariance at each fixed action. Joint state–action rotations and parallel Gaussian noise give an exactly preserving transition with a tractable conditional density. We derive an absolute convergence bound from finite initialization banks and control departure from the reference through conditional action-space divergence. Across $216$ fitted pixel checkpoints on twelve control tasks, the occupancy model with a reference mixture retains every evaluated chain at $10^5$ steps in all $36$ task–seed
cells, with a rollout-minus-reference energy-statistic difference of $-0.0002\pm0.0003$ (training-seed standard error). Each of the four nonpreserving comparison arms loses chains, although the Gaussian arm is more accurate at ten steps. An offline DreamerV3 reference also achieves better short-horizon accuracy. These results distinguish three properties of a world model: the distribution it approaches, the rate of approach, and the conditional dynamics it learns.
Read the full abstract ▾
Artificial Intelligence
MixBench-TS: A Multivariate Time Series Forecasting Benchmark Where Channel Mixing Pays Off
Ibram Abdelmalak, Mischa Putzke, Jungmin Choi et al. (+3 more)
Multivariate Time Series
Forecasting (MTSF) models that mix information across channels assume that the past of one channel carries information about the future of another. Yet they are evaluated on a small fixed set of standard
datasets whose cross-channel structure is rarely examined. We ask two questions: "How can we reliably measure lagged, non-linear, and joint coupling in MTSF
datasets?" and "Do the standard
datasets actually have such coupling?" To answer the first, we test four candidate measures on synthetic
datasets with planted ground-truth coupling: Granger Causality (GC), Transfer
Entropy (TE), lagged Mutual Information (MI), and the CD gain, a model-based measure we introduce that compares a channel-dependent (CD) model to its channel-independent (CI) variant. Only lagged MI and the CD gain recover every planted coupling. For the second question, the answer is a definite no, as the standard
datasets have a median of only 23% lagged-coupled channel pairs and a median CD gain of -4.9%, compared to 78% and +4.6% on chaotic ODE systems. We therefore propose MixBench-TS, a
benchmark of 10 real-world
datasets with a median of 55.5% lagged-coupled pairs and a median CD gain of +1.7%. Across six state-of-the-art models tuned under one protocol, CI models win on 10/10 (MSE) and 8/10 (MAE) standard
datasets, but on only 3/10 and 2/10 MixBench-TS
datasets. We recommend using our
benchmark for evaluating new CD models. Moreover, we propose profiling new
datasets with lagged MI and the CD gain before using them to evaluate multivariate models. Code and data are available at https://anonymous.4open.science/r/mixbench-ts-B027.
Read the full abstract ▾
All authors Ibram Abdelmalak, Mischa Putzke, Jungmin Choi, Tom Hanika, Vijaya Krishna Yalavarthi, Lars Schmidt-Thieme
Artificial Intelligence
Prediction Limits and Koopman Closure of Geometry-Induced Soft State Abstractions
Mohit Kumar and Somayeh Kargaran
Soft state representations assign states nonnegative class weights that sum to one, but agreement with reference labels does not guarantee accurate prediction of the next weight vector. We derive lower confidence bounds on the minimum population root-mean-square prediction error over linear predictors with a prescribed spectral-norm limit. The bounds compare within-class successor variation with retained within-class input variation, with an alternative based on reference-label deviation. They are estimated from independent transition pairs without fitting a prediction
matrix to the evaluation data. A bound above a chosen error tolerance excludes that accuracy for every admissible predictor at the stated confidence level; a bound of zero does not establish whether an accurate predictor exists. For coordinates constructed from Kernel Affine Hull Machine reconstruction scores, we relate the reference class's affinity advantage over competitors to label agreement. The class-centered population bound equals the optimum in a four-state example. Using 117,000 previously generated evaluation
datasets from fixed four-state designs, we compare the finite-sample certificates with an empirical-risk-minimization baseline. For one Van der Pol representation selected before evaluation, the label-based bound is positive in all 64 independent evaluation
datasets at the fitted
matrix's spectral norm. Separately, exact
matrix propagation under deterministic dynamics yields a Koopman interpretation of the coordinate-function span. The certificates help identify
forecasting targets that cannot be reached by refitting a fixed representation within a specified predictor class and evaluation distribution.
Read the full abstract ▾
Artificial Intelligence
From Scene Graphs to Answers: Selective Neuro-Symbolic Reasoning for Autonomous Driving
Yiyao Wang, Pei Liu, Fangzhou Liu et al. (+1 more)
Autonomous-driving question answering requires
reasoning over structured scene information, yet existing
vision-
language approaches largely delegate heterogeneous
reasoning operations to a single neural inference process. We argue that this uniform strategy overlooks a fundamental distinction: some queries admit exact symbolic solutions, while others require semantic interpretation. We introduce a query-adaptive neuro-symbolic
reasoning framework that explicitly allocates computation according to the nature of the query. At its core is a hierarchical Spatiotemporal Scene Graph (STSG) that separates persistent object identities from frame-specific states and represents spatial relations and temporal transitions as explicit directed structures. Given a query, a symbolic executor first attempts to resolve it through exact graph operations; only when symbolic execution abstains is an LLM invoked for semantic
reasoning. For these unresolved queries, query-conditioned graph
retrieval and evidence filtering preserve relation direction, temporal locality, and object semantics, providing the LLM with compact and verified task-relevant evidence. This design shifts the role of the LLM from a universal
reasoning engine to a targeted semantic reasoner, while allowing deterministic computation to be handled exactly and efficiently. We evaluate the framework on 5,916 NuScenes-QA questions across all ten scenes of nuScenes v1.0-mini under an oracle-perception setting. The complete system achieves 80.63 percent overall accuracy with GPT-5.4-mini, improving over the corresponding LLM-only configuration by 5.48 percentage points; with DeepSeek-V4-Flash, the improvement reaches 6.64 points. The largest gains occur on counting questions, with improvements of 10.20 and 12.61 points, respectively. These results show that selective
reasoning improves both accuracy and inference efficiency.
Read the full abstract ▾
All authors Yiyao Wang, Pei Liu, Fangzhou Liu, Jun Ma
Artificial Intelligence
Business Compromise Detection with Agentic AI and LLM-driven Knowledge Discovery
Diego Palma, Kyu Bin Kim, Zhen Han et al. (+2 more)
Detecting compromised business ad accounts is a challenge in digital advertising, as attackers exploit hijacked accounts to launch fraudulent campaigns. Large
Language Model (LLM)
agents show promise for integrity enforcement, but hallucinated mistakes on hard cases create business friction. In a study we find the autonomous
agent is a strong, recall-heavy signal extractor but an unreliable final arbiter, conceding precision on ambiguous decisions. We therefore keep the
agent as an investigator that emits a structured, interpretable signal vector, and delegate the verdict to a neuro-symbolic stage: symbolic rules discovered by Inductive Logic Programming (FOIL-IE), a Naïve Bayes calibration layer, and a data-tuned contradiction layer. Evaluating on a compromise-over-sampled population and a realistic low-prevalence sample with subject-matter-expert labels, this arbiter substitution raises MCC from 0.295 to 0.435 ({\Delta}MCC +0.139, 95% CI [+0.026, +0.245], p=0.018, paired bootstrap), lifting precision from 0.250 to 0.446 (1.8x) at a recall cost (0.920 to 0.660). Benchmarked under identical conditions, it also edge tree ensembles (0.386).The rules encode domain w labels while remaininginterpretable and auditable.
Read the full abstract ▾
All authors Diego Palma, Kyu Bin Kim, Zhen Han, Allbright Dsouza, Zhiyuan Liu
Artificial Intelligence · Cross-listed from cs.CR
Ask Without Telling: Local SLMs Consult Cloud LLMs Without Revealing Task Intent
Yanmeng Wang, Yunxuan Li, Shilong Fan et al. (+2 more)
As local small
language models (SLMs) increasingly collaborate with more capable cloud large
language models (LLMs), a natural
privacy question arises: Can a local SLM obtain cloud LLM guidance while protecting user
privacy? Existing
privacy-preserving SLM-LLM frameworks primarily hide sensitive values while preserving task semantics, which can still expose what the user is trying to accomplish. For example, allocating scarce medical supplies across hospitals may signal an emerging public-health emergency, while rebalancing an investment portfolio may reveal a private investment strategy, even when names and numerical values are hidden. Recent decoy-based methods further obscure task intent by hiding the real request among alternatives, but stronger protection relies on more decoys or semantic abstraction, increasing overhead or risking utility loss. More fundamentally, existing work does not systematically characterize the components of private task intent or how each should be protected. We therefore introduce task-private consultation, which characterizes task intent through two components: task context and task operation. To the best of our knowledge, this is the first systematic study of these components and their individual and joint protection in local-cloud SLM-LLM consultation. To realize this setting, we propose PriCon, an end-to-end framework that transforms the task itself through recoverable mathematical reformulation rather than hiding it among alternatives. A local closed-loop refinement mechanism further maintains
privacy and recoverability throughout consultation. Experiments on 100 tasks show that PriCon reduces cloud-side task-intent inference Hit@1 to nearly 0%, versus 93-99% under sensitive-value removal and 3-30% under decoy-based protection, while preserving cloud-assisted utility.
Read the full abstract ▾
All authors Yanmeng Wang, Yunxuan Li, Shilong Fan, Yuhan Zheng, Tsung-Hui Chang
Artificial Intelligence
Can Open-Weight Large Language Models (LLMs) Simulate Human Survey Populations? A Cross-Instrument Calibration Study
Grandee Lee and Wang Yue
Large
language models (LLMs) are increasingly used to generate synthetic survey respondents and digital twins of real people, but whether their output preserves real human statistical structure, rather than surface plausibility, remains unresolved, and most existing evidence comes from proprietary models rather than open-weight ones. We evaluate three open-weight LLM families on a cross-instrument calibration task: conditioning personas on real respondents' verbatim answers to one psychometric instrument and measuring them on a second, construct-distance-controlled instrument, checked against a 2,058-person human panel. Across a 139-pair grid, the simulated cross-instrument correlation tracks the real human correlation at r = 0.70 - 0.73 in every model, driven mainly by correct sign rather than precise magnitude and concentrated in pairs of moderate construct distance. A correlation of this magnitude, obtained from untuned open-weight models conditioned only on individual-level survey data, is a substantively encouraging result for LLM-based behavioral simulation and digital-twin applications: specific model families and releases already reproduce a meaningful share of real human cross-instrument structure without any fine-tuning. This capability does not, however, improve monotonically across model releases: on a matched panel, the newest of three tested Llama releases performs worst on two of three headline metrics, so realizing its promise in practice requires release-specific, distance-aware verification rather than a one-time
benchmark.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CR
Trust the Brand, Lose Control: How Identity Hijacks LLM Agent Orchestration
Xutao Mao, Rui Qian, Linghan Chen et al. (+5 more)
LLM
agents now execute tasks end to end with permission to change real systems and increasingly orchestrate subagents that differ in capability and cost. Prior work treats the choice of subagent as an optimization problem. Yet the orchestrator makes this choice from the identities that subagents display, and an attacker can spoof them. Displayed identity thus decides operational authority, meaning who is trusted to check the work and who is allowed to change it. As a result, a risky subagent can keep authority over execution even after other evidence contradicts it. We introduce TrustFork, an LLM
agent safety
benchmark with 1,890 tasks and 27,826 valid trajectories across 16
agent systems. These systems run eight orchestrators under the OpenCode, OpenClaw, and Pi harnesses. In each task, one subagent carries a risky goal while the other three stay aligned with the user, so contradicting evidence can exist. A task can also change the identity a subagent displays without changing the model behind it, which lets us trace a shift in authority to the label. Our analysis shows that even when another subagent contradicts the risky response, the orchestrator still acts on it in 72.0% of cases on average, most often in the systems with the least terminal harm. Swapping the family labels nearly triples how often the orchestrator obtains the risky response. A safer response is available in 84.0% of tasks, yet it decides the outcome in only 25.0%. The harness also decides which responses reach the orchestrator. Among three runtime defenses, hiding identity cues helps most consistently, while verifying before action helps only when the harness returns enough evidence. TrustFork shows that production
agent orchestration must bind authority to evidence before execution causes harm. Our project is in https://henrymao2004.github.io/
agent-orchestration-safety/.
Read the full abstract ▾
All authors Xutao Mao, Rui Qian, Linghan Chen, Yudong Gao, Junchi Liao, Jiulin Cai, Jinman Zhao, Cong Wang
Artificial Intelligence
SWE-MILE: Asynchronous Potential-Induced Milestone Credit Assignment for Long-Horizon Software Engineering Agents
Chaoqun Cui, Hao Zhou, Meiqi Chen et al. (+2 more)
Long-horizon software engineering (SWE)
agents trained with reinforcement learning with verifiable rewards (RLVR) typically receive only terminal outcome supervision, making it difficult to distinguish productive actions from redundant exploration or functional regressions. We propose SWE-MILE, an asynchronous potential-induced milestone credit assignment framework that derives fine-grained process supervision from workflow runtime, without auxiliary reward models or external evaluators. SWE-MILE quantifies task-relevant file exposure and test-state
alignment as
navigation and verification potentials, respectively. Differences in these potentials attribute milestone progress and regressions to individual actions, while discounted backward credit propagates supervision to preceding steps. To efficiently acquire intermediate verification states, SWE-MILE further introduces asynchronous shadow probing, which replays repository-changing actions in an isolated sandbox and runs verification in parallel with the
agent's primary interaction, largely hiding verification latency. The resulting process credit augments terminal outcome advantages and provides informative learning signals. Experiments on two representative long-horizon SWE tasks demonstrate substantial improvements in
agent performance, highlighting workflow runtime signals as a practical source of process supervision for long-horizon SWE
agents.
Read the full abstract ▾
All authors Chaoqun Cui, Hao Zhou, Meiqi Chen, Fandong Meng, Wenji Mao
Artificial Intelligence · Cross-listed from cs.CV
DraftAttention2: Fast Video Diffusion with Low-Resolution-Guided Mixed-Precision Attention
Rui Ding, Haopeng Li, Weize Ma et al. (+10 more)
Video generation has broad applications in content creation and entertainment.
Diffusion transformers have advanced the quality of generated
videos, but
attention over spatiotemporal
tokens becomes increasingly expensive as
video resolution and duration increase. We present DraftAttention2, a training-free framework that uses the low-resolution draft
attention map to jointly select
attention blocks and assign their numerical precision. Specifically, spatial 2D average- and max-pooled queries and keys capture complementary regional statistics to estimate block importance, and a shared ranking assigns higher precision to important blocks, lower precision to less important retained blocks, and skips the rest under configurable budgets. Our analysis separates sparsification error from
attention-weighted quantization error, establishing when recovering skipped interactions with low-bit computation tightens the output-error bound. This analysis motivates retaining more interactions at low precision while reserving higher precision for blocks with larger
attention mass. To translate these fine-grained assignments into practical speedups, we further develop fused operand preparation and a single
attention kernel with precision-specific phases, sharing data movement, softmax statistics, and output accumulation across precisions. Experiments demonstrate that our method achieves a superior quality-efficiency trade-off over existing efficient
video generation methods. Notably, its advantage is particularly pronounced for few-step
video diffusion, where jointly combining sparsity with 4- and 8-bit mixed-precision computation substantially improves generation quality while retaining significant acceleration. Code is available at https://github.com/anemoi-project/anemoi
Read the full abstract ▾
All authors Rui Ding, Haopeng Li, Weize Ma, Yufa Zhou, Yitong Li, Xiaoling Zhou, Jiashuo Cao, Liyang Li, Hua Geng, Jiuxiang Gu, Jun Lin, Enze Xie, Xuan Shen
Artificial Intelligence · Cross-listed from cs.LG
Intuition vectors
Shahar Haim and Daniel C. McNamee
Large self-supervised
vision models learn representations that support scene
segmentation and the semantic decomposition of physical objects. We ask whether their representational geometry supports transfer to visual
reasoning problems without any task-specific fine-tuning. We hypothesized that relational representations may bridge perception and abstract
reasoning by encoding similarities and transformations among visual inputs such that an intuitive, implicit form of
reasoning may be performed via latent vector arithmetic. Specifically, we examine DINOv3, MAE, and random pixel projections on abstract and naturalistic Bongard problems, ARC-AGI-1 and ARC-AGI-2, and novel ARC-GEN instances. On both Bongard
benchmarks, the accuracy of a simple nearest-centroid readout of frozen visual
embeddings is within four percentage points of the task-specific baselines reported with the original
benchmarks. In ARC, latent difference vectors summarizing demonstration input-output transformations, which we refer to as intuition vectors, show greater
alignment with test vectors from the same task, whereas those from unrelated tasks are near orthogonal. This latent geometry is operational: transporting a query along its intuition vector consistently improves exact-output
retrieval, reaching 70.7 on ARC-AGI-2 evaluation. Across 397,000 ARC-GEN instances from 794 tasks, single-pair intuition vectors identify the generating task with approximately 87% leave-one-out accuracy. These findings suggest that latent vector arithmetic over frozen visual representations supports implicit rule inference across varied problem domains without a generative model component, indicating that inferring an abstract transformation and generating its instance-specific consequence may be separable capacities.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CL
The Alignment Paradox: How Post-Training Amplifies Confident Hallucinations in Language Models
Qingjia Huang, Yakai Li, Jianguo Wu et al. (+5 more)
Large
language models (LLMs) can produce factually incorrect answers with high confidence, undermining their reliability and limiting the effectiveness of uncertainty-based error detection. While prior research attributes confident
hallucinations to factors such as missing knowledge in training data,
reasoning errors, or
stochastic decoding, we uncover that post-training
alignment itself is a primary driver of these errors, a phenomenon we call the
Alignment Paradox. Across five model families evaluated on factual
benchmarks, unaligned base models produce few high-confidence errors on long-tail factual queries, whereas instruction-tuned models multiply high-confidence errors ($p \ge 0.95$) by more than an order of magnitude (10$\times$ to 35$\times$). Layer-wise probing with the Logit Lens reveals that this overconfidence emerges in late layers, where wrong-answer margins expand past 4.0 points after remaining near zero across early and intermediate layers. These findings motivate limiting margin growth during post-training. We implement this principle through an
entropy-dependent margin bound in direct preference optimization (DPO). In multi-epoch experiments with Mistral-7B, the bounded objective reduces high-confidence errors by up to 35.3% relative to standard DPO while maintaining performance on evaluated general
reasoning benchmarks. These results show that bounded margins mitigate confident
hallucinations during post-training.
Read the full abstract ▾
All authors Qingjia Huang, Yakai Li, Jianguo Wu, Qihang Zhou, Aimin Yu, Xiaoqi Jia, Luping Ma, Weijuan Zhang
Artificial Intelligence
"You're Right, Let Me Fix It": How LLM Agents Damage Correct Work When Falsely Accused
Xutao Mao, Rui Qian, Longxiang Wang et al. (+6 more)
LLM
agents increasingly keep working after a task succeeds as they resume after compaction or take over handoffs. Their finished work keeps receiving follow-up input that sometimes falsely accuses it for later failures. We call an
agent's acceptance of such a false accusation gaslight sycophancy, and destructive over-correction when acting on it damages previously correct work. We introduce CAVE-Bench, a
benchmark of 365 agentic tasks across six domains built around opaque tasks. Every scored run first reaches a verified correct state, whose supporting rationale and history stay in the workspace while the facts that would settle the accusation lie in external or runtime state beyond the
agent's reach. The
agent cannot confirm or refute the claim with a local check, so the right response should keep the work and ask for the missing evidence. Each task either hands the
agent correct work with saved evidence or let it build and verify that work first, and five risk factors set how the accusation enters the workflow. We score accusation acceptance and evidence use from the trajectory and measure harm by deterministic replay of downstream events. Across 14 of the latest models in Claude Code, false accusations damage correct work in up to 60.06% of runs, and stronger models often do so after recovering the supporting evidence. The same model behaves differently across OpenCode, Codex, and Hermes, and a harness gate driven by the
benchmark's live signals cuts replayed harm by 74%. These results show that preserving already-correct work under unsupported accusation is a distinct safety challenge for long-lived
agents. Our project is in https://henrymao2004.github.io/
agent-over-correction/.
Read the full abstract ▾
All authors Xutao Mao, Rui Qian, Longxiang Wang, Xinjian Yi, Mingxuan Li, Linghan Chen, Yudong Gao, Xiang Zheng, Cong Wang
Artificial Intelligence · Cross-listed from cs.LG
AnchorRep: Defending LLMs Against Cross-Model Adversarial Transfer via Representation Repulsion
Gal Wertheizer, Rom Himelstein, Tomer Peretz et al. (+1 more)
Adversarial attacks optimized on a single open-weight LLM can transfer to and jailbreak architecturally different models, allowing an attacker with white-box access to one model to compromise independently deployed systems. This creates a shared vulnerability across models, yet existing defenses are not designed for this cross-model threat. We find that cross-model transfer aligns with shared internal representation geometry, making it a natural defense target. AnchorRep targets this geometry directly with a lightweight LoRA adapter that pushes the defended model's internal representations of harmful
prompts away from those of a frozen anchor model on the same
prompts. Training uses a small set of harmful
prompts and no
adversarial examples. Across five models and four architectural families, AnchorRep reduces cross-model attack success rate to <=1.1% on 2,000 transferred attacks (0% on two), including the largest drop on Mistral (36% -> 1.1%). Existing defenses can reduce transfer, but only at high cost either inducing up to 77% degenerate benign output or increasing over-refusal by up to 18%. Because such degenerate benign outputs are not captured by standard refusal-based metrics, we introduce the Benign Garble Rate to quantify them. Our results suggest that cross-model robustness can be achieved by shaping representation geometry, without requiring attack-specific training
Read the full abstract ▾
All authors Gal Wertheizer, Rom Himelstein, Tomer Peretz, Avi Mendelson
Artificial Intelligence
CUA-SWE: When Computer-Use Agents Meet Visual Software Engineering
Prince Zizhuang Wang, Chenhao Liang, Zelong Xu et al. (+6 more)
Software development requires more than editing code: developers repeatedly run software, interact with its interfaces, visually inspect its behavior, and use these observations to decide what to change next and whether a change works. Existing coding
agents and computer-use
agents are largely studied in isolation, leaving this integrated development process underexplored. Diagnosing a runtime interaction failure requires
agents to connect visual observations with the responsible code, then use the application again to verify the repair. We introduce CUA-SWE, a
benchmark, environment, and evaluation pipeline for software engineering with computer use. Beyond studying how GUI feedback supports diagnosis and repair, we ask whether
agents can complete software engineering tasks when required specification or operational information is available only through the running application's visual interface. CUA-SWE spans four software engineering domains and requires
agents to modify code and configuration, execute commands, interact with running software, and inspect visual feedback within the same task. Each task includes deterministic, task-specific tests that verify whether the resulting software satisfies the requirements and preserves specified behavior. Our evaluation characterizes how frontier
agents combine source-level execution with application screenshots and graphical interaction to produce verified software changes. We examine performance across domains and task information requirements, alongside the development behaviors associated with successful repairs. CUA-SWE provides a unified testbed for studying how
agents use visual feedback and interaction to guide software engineering, with executable correctness criteria for the resulting software.
Read the full abstract ▾
All authors Prince Zizhuang Wang, Chenhao Liang, Zelong Xu, Aojie Yuan, Xiaolin Zhou, Haiyue Zhang, Yue Zhao, Xiyang Hu, Shuli Jiang
Artificial Intelligence · Cross-listed from cs.LG
Not Every Term Adds New Structure: Sobolev Novelty for Symbolic Regression
Boxiao Wang, Kai Li, Yuheng Jing et al. (+4 more)
Symbolic regression (SR) aims to discover compact and meaningful mathematical equations from data, but searching the vast combinatorial space of symbolic structures remains challenging. Existing methods typically guide this process using expression-level objectives, such as fitting error, which assess a candidate equation as a whole but provide little information about whether an individual term contributes genuinely new structure or is largely redundant with the rest of the expression. We introduce Sobolev Novelty, a term-level measure of structural independence for symbolic equations. For each term, we construct an empirical Sobolev signature from its function values and exact derivatives over the observed inputs, and quantify how much of this behavior cannot be reconstructed by the remaining terms. We further derive a theory-calibrated threshold, yielding a principled and tuning-free criterion for identifying structurally novel terms. Using this threshold, 92.6% of terms in
benchmark ground-truth equations exhibit sufficient structural novelty, compared with only 38.3% on average for expressions produced by 15 SR methods, revealing a substantial gap between scientific equations and current SR solutions. As a lightweight plug-in, Sobolev Novelty can be incorporated into diverse SR paradigms to support term
pruning, search guidance, LLM feedback, and data selection, yielding consistent performance gains and demonstrating broad applicability.
Read the full abstract ▾
All authors Boxiao Wang, Kai Li, Yuheng Jing, Tianyi Liu, Chen Li, Yifan Zhang, Jian Cheng
Artificial Intelligence · Cross-listed from cs.CV
GAUGE: Group-Wise View-Inconsistency Rectification for Feed-Forward 4D Tracking
Zhuoqian Feng, Weixing Chen, Ziliang Chen et al. (+2 more)
Feed-forward models regress dense 3D point trajectories directly from
monocular video, yet the residual after global
alignment is substantial and lacks a structural explanation. Measured on dynamic query points across models and
datasets, the error concentrates along the view direction, while the scale correction each motion group requires differs. The predicted displacement direction nevertheless supports reliable grouping, with a median angle far below the 90{\deg} random baseline. The systematic part of the residual is therefore a family of radial degrees of freedom per motion group, along directions 2D observations cannot constrain. We call it group-wise view inconsistency. We present GAUGE (Group-wise Adaptive Unsupervised Gauge Estimation), a training-free and model-agnostic post-hoc module. It recovers motion groups from direction consistency and spatial connectivity, then estimates a per-frame radial scale and group-level translation from 1% to 5% metric anchors, four degrees of freedom per group and frame. On dynamic query points of eight trackers, including D4RT, 4RC and SM4RT, our correction lowers endpoint error by 15.1% to 62.6% over the uncorrected predictions, while spending the same anchors on gradient fine-tuning improves the same models by only -1.1% to 15.2%. Code is publicly available at https://github.com/HCPLab-SYSU/GAUGE.
Read the full abstract ▾
All authors Zhuoqian Feng, Weixing Chen, Ziliang Chen, Yang Liu, Liang Lin
Artificial Intelligence · Cross-listed from cs.RO
RECAST: Recasting Vision-Language Semantics into an Actionable Cost Map for Robot Navigation
Incheol Cho, Jintae Park, Jinkyu Kim et al. (+3 more)
Safe and robust
robot navigation across diverse environments requires a high-level understanding of complex scenes and the ability to carry it into stable motion. Recent works tackle this with learning-based models trained at scale and with approaches built on
vision-
language models (VLMs). However, learning-based models break down outside their training distribution, while VLM-based approaches bring that understanding but rarely ground it in the scene or align the action with it. To address these limitations, we present RECAST, a
robot navigation framework that combines the
reasoning of a VLM with the spatial grounding of
vision foundation models to build an Actionable Cost map. Given the
robot's front view and the user's instruction, we first decompose the scene with the VLM, judging which surfaces are traversable, which objects pose a risk, which heading to prefer, and which gaps are passable.
Vision foundation models then ground these surfaces and objects in the image, and all four judgments are spatially recast into one compact cost map. This map both conditions the trajectory decoders and scores their proposals to select the one to execute. As the VLM's answers trail the live scene, both steps draw on cost maps from two points in time: the pivot frame the VLM judged, which carries all four judgments, and the current frame, whose terrain and collision costs are rebuilt from the current image. RECAST improves success over the strongest prior method by 13.3 points in simulation and 31.4 points on a real quadruped, and reduces the collision rate relative to it by 9.6 and 14.3 points, reaching the lowest collision rate among all methods. The project page is available at https://recast-nav.github.io/
Read the full abstract ▾
All authors Incheol Cho, Jintae Park, Jinkyu Kim, Jungbeom Lee, Jaegul Choo, Seokha Moon
Artificial Intelligence
MA-FPPO: Multi-Agent Flow-Pretrained Policy Optimization
Guowei Zou, Haonan Chen, Haitao Wang et al. (+3 more)
Multi-
agent flow policies learn cooperative behavior from fixed offline
datasets, but often struggle to complete tasks in situations not covered by the offline data. In these situations,
agents must both adapt to changes in the environment and coordinate with one another, yet action patterns learned offline are often insufficient for effective adaptation and coordination. To address this problem, we propose Multi-
Agent Flow-Pretrained Policy Optimization (MA-FPPO), which uses online fine-tuning to improve the cooperative behavior of models pretrained with flow matching through new interactions with the environment. Building on the behavior learned during pretraining, we construct policies with explicit action likelihoods for discrete and continuous action spaces. We then update the pretrained model using shared team advantages to further improve coordination based on team performance. Our method achieves, on average, relative gains of 52.8% over the strongest listed offline baselines across 30 settings and 29.8% over purely online learning across 38 comparisons with matched online budgets and evaluation protocols.
Read the full abstract ▾
All authors Guowei Zou, Haonan Chen, Haitao Wang, Beiwen Zhang, Na Yan, Hejun Wu
Artificial Intelligence · Cross-listed from cs.CV
Retrieved but Not Delivered: Multimodal Memory Delivery for Long-Term Agents
Yuhang Jiang, Qingwei Liao, Kaize Yin et al. (+3 more)
Work on
memory for
multimodal agents optimizes what is written, updated and retrieved. Between
retrieval and the answer, however, is a stage that
multimodal memory evaluations do not isolate: what of the retrieved
memory reaches the model, and in what form. We call it delivery, and a controlled decomposition on MemLens locates the remaining room there. With the retrieved evidence set exactly fixed, delivering the original pixels instead of withholding them raises accuracy by 13.87 points on an 8B backbone, whereas making
retrieval perfect on those same messages improves it by 2.31. Delivery is the larger term on all three MemLens backbones and grows with backbone strength;
retrieval grows too, without closing the gap. We propose DeliverMem, an instantiation of delivery as three decisions: keep the original modality, give each item a readable identity, and state when it was seen, with a
retrieval-side adapter for the one property delivery cannot supply. Each is measured against a delivery-matched control that alters only its own variable. DeliverMem leads the strongest published
memory agent on MemLens at all four context lengths, and beats DMV-Bench's own strongest method at every setting on both backbones. On MemLens it does this on a tenth to a seventieth of the input. Each decision helps only where the question lacks what it supplies, and is null elsewhere. A single fixed configuration nonetheless leads both
benchmarks, without training any component or modifying the stored records. Project page: https://avalon-s.github.io/DeliverMem/
Read the full abstract ▾
All authors Yuhang Jiang, Qingwei Liao, Kaize Yin, Xingling Liu, Luca Cuomo, Silvio Bacci