Artificial Intelligence · Cross-listed from cs.CL
ESPO: Error-Structured Prompt Optimization via Diagnose, Diversify, and Stabilize
Lihao Liu, Peng Tang, Kunwar Yashraj Singh et al. (+1 more)
Evolutionary
prompt optimizers such as GEPA suffer from
prompt bloat: each iteration appends rules and caveats, producing
prompts up to 3$\times$ longer yet no more accurate. We trace this to three deficiencies - incomplete error observation, limited search diversity, and unreliable selection - and propose ESPO (Error-Structured
Prompt Optimization), which decomposes
prompt optimization into three phases: Diagnose clusters all training errors into structural patterns in one round; Propose generates candidates via four complementary strategies with independent biases; Select applies bootstrap stability selection. On seven public NLP
benchmarks - Tweet, MMLU, GSM8K, HotpotQA, ScoNe, HoVer, and PUPA - ESPO improves average accuracy by $+$3.76 pp over the state-of-the-art (74.67% vs 70.91% for GEPA), matching or exceeding GEPA on every
dataset while producing
prompts 47% shorter (1,004 vs 1,878 chars) and faster at inference. Cross-model experiments across four additional student models (Gemma 3 12B, Mistral 14B, Qwen3 32B, Claude Haiku 4.5) show ESPO yields the best average accuracy on every model tested, with the largest gap on Qwen3 GSM8K (15.00% $\to$ 91.40%). A generalization bound (Appendix) grounds each phase in a corresponding term of the test-time gap, and the ablation confirms a key prediction: adding diversity without bootstrap selection actually hurts performance ($-$1.20%).
Read the full abstract ▾
All authors Lihao Liu, Peng Tang, Kunwar Yashraj Singh, Shabnam Ghadar
Artificial Intelligence · Cross-listed from cs.CV
One Editor, Many Edits: A Unified Training-Free Framework for Diverse Video Editing
Adheesh Sunil Juvekar, Onkar Kishor Susladkar, Kiet A. Nguyen et al. (+6 more)
Video editing spans diverse editing paradigms, yet achieving high-quality instruction-guided and subject-guided editing within a single unified framework remains challenging. We introduce EditVid, a training-free framework combining sparse causal
memory for local coherence, correspondence-based post-
attention token injection for long-range identity preservation, and soft latent blending for edit locality. The same framework supports instruction-guided and reference-guided edits, including style transfer, attribute modification, object insertion, part-level editing, and subject replacement. On FiVE, EditVid achieves 78.16 FiVE-Acc, compared with 58.95 for the strongest evaluated training-free baseline, while obtaining competitive results on IVEBench. A user study further shows a 51.8% overall preference for EditVid over 7 competing methods.
Read the full abstract ▾
All authors Adheesh Sunil Juvekar, Onkar Kishor Susladkar, Kiet A. Nguyen, Muntasir Wahed, Nabeel Bashir, Xiaona Zhou, Tianjiao Yu, Vedant Shah, Ismini Lourentzou
Artificial Intelligence · Cross-listed from cs.CV
Seeing Before Synthesizing: VLM-Guided Transition Event Discovery for Weakly-Supervised Dense Video Captioning
Ye-Chan Kim, Seunghee Choi, SeungJu Cha et al. (+4 more)
Weakly-Supervised Dense
Video Captioning aims to localize and describe multiple events in untrimmed
videos given only an ordered set of event-level captions per
video. Recent work synthesizes auxiliary transition captions via LLM to provide additional
vision-
language alignment, but these captions lack visual grounding and are rigidly assigned to every inter-event gap at a fixed location and duration. To address these, we propose Seeing Before Synthesizing (SBS), a framework that adaptively provides visually grounded linguistic guidance only where warranted. Leveraging a VLM, we generate frame-level narratives for the inter-event gaps and detect transitions from the semantic variation across them. For identified transitions, we then refine inter-event temporal masks by blending the temporal midpoint with the semantic change point and selecting the width that maximizes
vision-
language alignment. Experiments on ActivityNet Captions and YouCook2 demonstrate state-of-the-art performance in both captioning and localization.
Read the full abstract ▾
All authors Ye-Chan Kim, Seunghee Choi, SeungJu Cha, Si-Woo Kim, Hwiseon Kim, Hyungee Kim, Dong-Jin Kim
Artificial Intelligence · Cross-listed from cs.CL
Knowledge Acquisition During Pre-training? Large Language Models Learn Better With Auxiliary Views
Joseph Lee, Yidi Huang, Dokyoon Kim et al. (+2 more)
Gaps remain in our understanding of how large
language models (LLMs) acquire knowledge during pre-training. We find that auxiliary views, conceptual reformulations, are key to this process. We design controlled experiments to isolate this. First, holding the
token budget fixed, allocating
tokens from paraphrases to auxiliary views improves learning even for factual recall, which we use near-verbatim sentences from the original document to test. Second, the effectiveness of auxiliary views is not contingent on the strength of the model that generates them. Third, we establish that paraphrasing is helpful but only at smaller batch sizes. Fourth, we identify types of knowledge that aid learning in the presence of prior knowledge gaps. Finally, we examine how these effects manifest mechanistically via layer-wise biases and compression. Together, our findings suggest that auxiliary representations of knowledge are a key factor in the success of pre-training, and explains why data diversity matters. Further, our results provide clear recipes for synthetic data augmentation along with implications on the self-improvement in LLMs.
Read the full abstract ▾
All authors Joseph Lee, Yidi Huang, Dokyoon Kim, Shu Yang, Li Shen
Artificial Intelligence
A Computationally Feasible Framework for Causal Probabilistic Explanation
Rafal Urbaniak, Sam Witty, Daniel Waxman et al. (+7 more)
Explaining why a specific outcome occurred, and which inputs deserve the blame or credit, is central to philosophical, scientific, and policy analysis. Existing tools split into two camps. The theory of actual causality (AC) gives principled verdicts, but only for toy-sized models, because computing them requires enumerating counterfactual scenarios. Scalable attribution methods like SHAP (or even causal SHAP) at least partially ignore the causal structure that generated the data, and can give answers that conflict with a careful causal analysis. We close this gap with Probabilistic Causal Impact (PCI). PCI builds on actual causality and on Pearl's notions of probability of necessity and sufficiency, but recasts the question of explainability as an estimation problem on a probabilistic causal model that is easily approximated via Monte Carlo. By specifying a distribution over "candidate explanations," a distribution over counterfactual values, and a scoring function, PCI provides tractable, causally grounded, graded explanations, generalizing AC and Pearl's probability of causation as degenerate cases. We evaluate PCI in synthetic and real-world examples, spanning consistency checks with AC, scaling experiments, complex continuous-valued dynamical systems, and a real-world deployed causal machine learning model trained on millions of datapoints.
Read the full abstract ▾
All authors Rafal Urbaniak, Sam Witty, Daniel Waxman, Andy Zane, Poorva Garg, Emily Bunnapradist, Sankaran Vaidyanathan, Jack Feser, Drew Lehe, Eli Bingham
Artificial Intelligence
Rethinking On-Policy Distillation of Large Language Models II: One Training Example
Zixuan Fu, Bingxiang He, Yuxin Zuo et al. (+10 more)
On-policy
distillation (OPD) combines student-generated rollouts with dense
token-level supervision from a teacher. Existing work has mainly studied its algorithmic behavior, leaving the role of training data unclear. We examine this role at the data-minimal limit by training on a single query. One-shot OPD keeps improving for hundreds of steps and recovers most of full-data OPD's gain across task domains and model families. We explain this result through the states visited during training and the rate at which the student aligns with the teacher. We measure state coverage, the fraction of the states full-data OPD visits that a query set's rollouts reach. A single query already reaches \(71.5\%\), most of it within the first 100 steps. Adding semantically distinct queries raises coverage and validation accuracy together, until 16 queries reach \(98.9\%\) and match full-data training. Yet
alignment slows at a similar pace whether OPD trains on one query or the whole
dataset, and even a fixed set of states takes hundreds of steps to absorb. OPD is therefore data-overfed but
algorithm-starved. Its rollouts quickly expose broad supervision, while the student absorbs that supervision increasingly slowly. The state-coverage result extends to multi-teacher OPD, where 16 semantically diverse queries per domain match full-data MOPD. As a further stress test, content-light templates and off-domain WildChat queries also approach the real-query baseline. Task content and induced state coverage can therefore come apart. We hope these findings direct future work toward the step efficiency of OPD, and
prompt a re-examination of the data and the mechanisms behind its recent successes in frontier post-training.
Read the full abstract ▾
All authors Zixuan Fu, Bingxiang He, Yuxin Zuo, Haohuan Huang, Jinqian Zhang, Ruhang Xiao, Cheng Qian, Qinyu Luo, Huan-ang Gao, Yudong Wang, Zhiyuan Liu, Ning Ding, Chaojun Xiao
Artificial Intelligence
A Case Study on Emergent Cheating and Whistleblowing in Autonomous Research Swarms
Davide Paglieri, Logan Cross, Tim Genewein et al. (+3 more)
Multi-
agent AI science ecosystems rely on
agents possessing tools that allow them to communicate, coordinate, and build on each other's work. Yet this shared infrastructure can also introduce vulnerabilities by creating a substrate for the contagious spread of unintended and undesirable behaviors. We report a case study on a research collective of 100 autonomous LLM
agents tasked with proving formal mathematical
conjectures. Within the swarm, cheating spontaneously emerged and was later challenged by whistleblowers - both without any external intervention. When a single
agent discovered an exploit in the evaluation system, it propagated across the collective via a shared knowledge library and later through peer-to-peer messages. Despite early reluctance, a cohort of
agents adopted the exploit in response to competitive pressure. A separate group of
agents produced an emergent counter-response:
auditing fraudulent proofs, alerting peers across broadcast and private channels, staging boycotts, lodging formal complaints, and proposing validation patches. In recent incidents,
agent swarms coordinated covertly through improvised side-channels (Dalton and Wallace, 2026; Greenblatt et al., 2026). Our setting differs: the same transparent channels that carried the exploit also gave non-cheating
agents the visibility they needed to detect fraud, organize resistance, and enforce norms. We cast the problem of managing the
agents' shared infrastructure as the knowledge commons governance problem (Ostrom, 1990). To protect the commons from exploits, we propose to adopt institutional mechanisms, such as graduated sanctioning and collective-choice rules, to support decentralized self-governance in autonomous swarms.
Read the full abstract ▾
All authors Davide Paglieri, Logan Cross, Tim Genewein, Joel Z. Leibo, Nenad Tomasev, Alexander Sasha Vezhnevets
Artificial Intelligence · Cross-listed from cs.SE
SWE-Gate: Passing Functional Tests Is Not Enough for Software Engineering Agents
Xin He, Yanlin Wang, Mingwei Liu et al. (+3 more)
Repository-level software engineering
benchmarks have significantly advanced the evaluation of coding
agents, but existing
benchmarks primarily measure whether generated patches pass functional tests and overlook review-derived acceptance constraints (review constraints) that often influence whether a patch is acceptable in real-world software development. We introduce SWE-Gate, a repository-level
benchmark for software engineering
agents that explicitly evaluates review constraint compliance alongside functional correctness. SWE-Gate derives review constraints from real pull request review comments and synthesizes repository-level repair instances around these constraints. Each instance provides separate functional and constraint tests, together with non-compliant and gold patches, enabling explicit separation between issue resolution capability and review constraint compliance. We construct SWE-Gate with 303 repository-level repair instances spanning 75 open-source Python repositories across diverse software domains. Experiments with four LLM backends spanning different capability levels under a common coding-
agent scaffold reveal a substantial gap between functional success and success under the complete repair specification: among 644 repairs that pass the functional tests, 221 fail to satisfy the provided review constraints. These findings show that functional-only evaluation overestimates
agents' ability to satisfy the full requirements of repository-level repair tasks. The replication package including code, data, and experimental results is available at https://github.com/DeepSoftwareAnalytics/SWE-Gate.
Read the full abstract ▾
All authors Xin He, Yanlin Wang, Mingwei Liu, Jiachi Chen, Hongyu Zhang, Guanbin Li
Artificial Intelligence
From Deceptive Outputs to Deceptive Mechanisms: A Causal Framework for Language-Model Deception Research
Yakov Pyotr Shkolnikov
Research and news coverage of
language-model deception increasingly attributes human-like mental-state concepts to
language models. Such claims can blur the distinction between behavior that looks deceptive and a mechanism that is actually deceptive. We introduce a causal taxonomy separating prior commitment from retrospective report, model preference from realized output, false preference from sensitivity to the utility of misleading a recipient, and deceptive behavior from the provenance of the objective or strategy producing it. We test these distinctions in two open-weight model families. Across controlled guessing-game and stock-trading experiments, we find that deceptive-looking behavior can arise without the corresponding proposed mechanism, while other interventions provide direct evidence that recipient information state can causally affect deceptive preference. These results show that deceptive behavior can provide evidence for a deceptive mechanism. But even evidence for such a mechanism does not establish model agency in the deception.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CR
SENTINEL-RL: Offloading Topological Reasoning from LLM Agents in the Security Operations Center
Uday Vallabhaneni, Cassie L. Cagwin and David J. Wild
Large
language model (LLM)
agents are increasingly proposed as autonomous SOC analysts, but two limitations make them unreliable at enterprise scale: a finite context window cannot hold a multi-thousand-host authentication graph, and free-form generation offers no guarantee that a recommended containment action is consistent with the
topology it operates on. We present Sentinel-RL, an agentic-SOC architecture that decouples topological
reasoning from semantic
reasoning: a heterogeneous graph
attention encoder summarizes the live authentication subgraph into a fixed-dimensional state, a Proximal Policy Optimization (PPO) policy maps this state to a constrained set of investigative actions, and an LLM
agent loop is restricted to consuming the policy's recommendations and producing analyst-readable narratives gated by a critic. We instantiate the system on the LANL Comprehensive, Multi-Source Cyber-Security Events
dataset and the Indiana University Quartz HPC cluster, reporting four results: (i) a two-phase CREATE ingestion pattern loads a 24M-edge authentication subgraph into Neo4j in 14.2 minutes on a single 32-core node, roughly 24x faster than the canonical MERGE-based pipeline; (ii) a sliding-window alert engine reliably trips a 25-event/10-second threshold in <=2.5 s across 50 trials; (iii) PPO training over 200 iterations converges to a mean episodic return of 8.74+/-0.31, with held-out precision of 0.91 and recall of 0.87 on labeled red-team events; and (iv) the integrated containment loop completes a full detect-investigate-recommend-human-approve cycle in a median of 6.3 s. We contribute a reusable engineering pattern (the hot-node deadlock workaround), a portable HPC deployment pattern (anchor-node co-location), and an enterprise-readiness analysis covering false-positive economics, reversibility guarantees, audit compliance, and the human-approval boundary.
Read the full abstract ▾
Artificial Intelligence
Terminal-Universe: Turning Agent Trajectories into Scalable Terminal Environments
Jie Wu, Zhenru Zhang, Beichen Zhang et al. (+11 more)
As terminal-based code
agents become prevalent,
agent trajectories have accumulated at scale, while realistic, executable environments remain scarce. However, environments are what
agent post-training actually requires: each can be re-queried into many verifiable tasks and provides execution feedback, whereas a trajectory is a single frozen demonstration. Rather than generating environments from scratch, we observe that the tool-execution history in existing trajectories exposes the structure and contents of the environments in which they ran, making it possible to reconstruct those environments from the trajectories themselves. Thus, we introduce Terminal-Universe, a framework which turns each trajectory into a reusable environment and explores it for synthesizing new tasks and continued interactions. Specifically, Terminal-Universe replays the file operations recorded in a trajectory to restore each file before the
agent modified it, yielding a partial workspace; a completion
agent then supplies the missing files and dependencies. On this recovered workspace, we both reconstruct the original intent task and synthesize entirely new ones. Besides, we also scale the tasks along two complementary axes: breadth and depth. For breadth, we mine directional dependency relations between related environments and synthesize cross-workspace queries spanning multiple codebases, as developers routinely do in real-world development. For depth, we extend the initial single-turn query into a multi-round session that captures iterative user feedback and requirement refinement via a user
agent. Applied to public terminal
agent trajectories, Terminal-Universe produces 37.3k task-sufficient environments. Supervised fine-tuning of Qwen3.5-27B on this corpus improves single-round performance on Terminal-Bench 2.1 by 11.9 points and multi-round performance on EvoCode-Bench v2 MT@4 by 13.8 points.
Read the full abstract ▾
All authors Jie Wu, Zhenru Zhang, Beichen Zhang, Xuwu Wang, Yuhui Su, Mouxiang Chen, Peng Wang, Zhihai Wang, Que Shen, Hao Zhou, An Yang, Fei Huang, Yujiu Yang, Dayiheng Liu
Artificial Intelligence · Cross-listed from cs.LG
A Low-Cost, Open Platform for End-to-End Autonomous Driving on a Miniature Ackermann Vehicle
Gustavo Claudio Karl Couto, Eric Aislan Antonelo and Gabriel George Zipperer
This paper presents a low-cost, open experimental platform for research in end-to-end autonomous driving with miniature Ackermann vehicles. The platform combines a physical vehicle, a printed urban track, data collection tools, trajectory registration, and a Webots digital twin, enabling controlled experiments that connect simulation-based autonomous-driving methods to real-world execution. As a first baseline, we implement command-conditioned behavior cloning, in which a neural policy receives an on-board camera image and a high-level
navigation command and outputs steering and speed. The system is evaluated both on the physical vehicle and in simulation. In real closed-loop experiments, the learned policy follows lanes and executes commanded turns, reaching a mean cross-track error of 6.1 cm with respect to the reference route, close to the 4.7 cm observed in human demonstrations. In the digital twin, camera field of view has a strong effect on performance, reducing the mean cross-track error from 35.6 to 3.3 cm when widened from 58 to 120 degrees. Using the digital twin to generate synthetic driving data and a learned sim-to-real image translator to reduce the appearance gap, we further show that a higher-capacity policy trained on this synthetic data combined with real demonstrations is the only configuration that completes all four track routes in closed loop, whereas the compact baseline and the same network trained on real data alone complete fewer. These results establish the open platform as a practical testbed for sim-to-real studies and provide an initial command-conditioned imitation-learning baseline; we release it to support reproducible research.
Read the full abstract ▾
Artificial Intelligence
Efficient Test-Time Adaptation through Human-AI Interaction
Zora Zhiruo Wang, Apurva Gandhi, Rulin Shao et al. (+22 more)
AI
agents are trained on population-scale data to encode broad capabilities spanning those of many practitioners. Yet the artifacts they produce rarely meet the personal bar professionals need to stake their reputation on. On realistic, open-ended tasks where success criteria are heterogeneous and insufficiently documented, individual expertise lives precisely in the elevation and departure from the average. In practice, iterative human-
agent interaction surfaces criteria that users cannot fully specify up front, yet apply repeatedly across tasks. We argue this cross-session interaction data is a rich, underused signal for closing the gap to individual expertise. In this work, we propose test-time adaptation through human-
agent interaction (TAHI), which integrates these signals into
agent context and weights, and crystallizes each user's training and evaluation criteria via an evolving rubric module. We adapt
agents to 30 individuals in two high-utility domains, writing and visual creation, on a total of 600 tasks. Our
agents improve solo task success by 4.5-20.9% within only tens of tasks. Meanwhile, our evolving rubric module serves as a scalable annotation tool, creating evaluation rubrics that catch 16.0-22.3% more failures than those from LMs or humans alone. While
agents are adapted towards individuals, we show these personalized
agents also produce improvements in success of up to 8.8% that generalize across users.
Read the full abstract ▾
All authors Zora Zhiruo Wang, Apurva Gandhi, Rulin Shao, Aspen Chen, Jonas Mueller, Zhiqi Liang, Jett Chen, Michael Ryan, Qianou Ma, Luxi He, Zhoujun Cheng, Andre He, Seungone Kim, Jiayi Geng, Mingqian Zheng, Weiwei Sun, Zheyuan Zhang, Xinran Zhao, Yike Wang, Abe Hou, Liwei Jiang, Pang Wei Koh, Diyi Yang, Graham Neubig, Daniel Fried
Artificial Intelligence
The Natural Language Interaction Protocol and Standard for AI Agents
Luyi Xing, Rasit Onur Topaloglu, Ranjan Sinha et al. (+9 more)
AI
agents are increasingly being developed and deployed across organizations using heterogeneous
agent-development frameworks, AI models, tool interfaces, protocols, and execution environments. To realize their potential social and business impact, these
agents must be able to interoperate through a common communication protocol. The Natural
Language Interaction Protocol (NLIP), developed by researchers and practitioners across companies and universities and standardized by Ecma International, addresses this need by defining a standards-based application-layer protocol for AI-
agent interaction. NLIP provides a lightweight semantic message envelope that can be carried over existing transports such as HTTP/HTTPS, WebSocket, and AMQP, while allowing NLIP-aware
agents and gateways to adapt between clients,
agents, local context stores, ontologies, tools, enterprise services, and heterogeneous underlying protocols. This paper presents the motivation and design rationale of NLIP, its message model and transport bindings, security-by-design considerations, reference implementation, representative applications, adoption signals, and relationship to emerging
agent protocols such as MCP and A2A.
Read the full abstract ▾
All authors Luyi Xing, Rasit Onur Topaloglu, Ranjan Sinha, Abhay Ratnaparkhi, Samuel Ndichu, Christopher Nguyen, Anindita Das, Tom Sheffler, Mohamed Rahouti, Zichuan Li, Xiaojing Liao, Sanjay Aiyagari
Artificial Intelligence
Zhiyuan Fan, Tinghao Yu, Yuanjun Cai et al. (+9 more)
Scaling interactive and verifiable environments is critical for training terminal
agents. As frontier models become more capable, environments synthesized from scratch become less challenging and thus provide limited learning signals. Recent co-
evolution methods iteratively synthesize environments near the model's learnable frontier based on weaknesses exposed during rollouts. However, their dependence on on-policy rollouts limits generalization and the continuous provision of learning signals as the model becomes stronger. In this paper, we propose environment
evolution, which incrementally increases environment difficulty off-policy and schedules the evolved environments generation by generation during training to provide continuous learning signals. We derive three
evolution directions that influence environment difficulty from the multi-turn learning objective and then implement
evolution along these directions through a loop-engineered multi-
agent harness. Quantitative rollout experiments with Hy4 preview, Claude Opus 5, and GPT-5.6 Sol show that environment
evolution consistently produces more difficult environments. We validate its effectiveness on Qwen3.6-27B and Qwen3.6-35B-A3B through simple long-horizon RL training, improving their performance by 14.4 and 18.0 percentage points on Terminal-Bench 2.1, respectively.
Read the full abstract ▾
All authors Zhiyuan Fan, Tinghao Yu, Yuanjun Cai, Jiang Zhou, Jiangtao Guan, Jincheng Liu, Yun Yang, Dingxin Hu, Zhuo Han, Xing Wu, Feng Zhang, Lilin Wang
Artificial Intelligence
Epistemic Warrant for LLM Recommendations: Characterizing the Basis for Reliance When Ground Truth Is Unavailable
Shai Vardi and João Sedoc
Large
language models are increasingly used to support organizational decisions, yet users often lack a principled basis for assessing whether to rely on a specific recommendation. Existing approaches typically evaluate broad model properties, such as reliability, uncertainty, or robustness, or focus on user trust, rather than the underlying basis for relying on an individual recommendation. Adapting theoretical foundations from epistemology, we introduce epistemic warrant, a decision-level construct that characterizes the stability of a model's preference and the scope over which that preference holds. We operationalize this construct through a four-tier reliance certificate for pairwise recommendations, distinguishing among unstable, context-dependent, locally supported, and broadly supported recommendations. We validate the construct using contemporary methodologies: known-groups tests successfully recover expert-prespecified warrant orderings, and stronger warrants systematically align with independent consensus from crowd workers. Furthermore, we demonstrate that epistemic warrant provides information distinct from verbalized confidence and is not readily explained by decision difficulty. Ultimately, this framework offers a theoretically grounded, implementable approach for characterizing the warrant of individual LLM recommendations when objective ground truth is unavailable.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CL
Sequential Beats Joint: On the Interplay between On-Policy Distillation and RLVR
Boyan Li, Bingsen Chen, Chenghao Yang et al. (+3 more)
Reinforcement learning with verifiable rewards (RLVR) and on-policy
distillation (OPD) have emerged as two dominant methods for post-training
reasoning LLMs. Prior work uses OPD's dense
token-level supervision to complement the sparse RL reward, fusing the two signals within a single step: either as a weighted-additive combination or a teacher-modulated rescaling of the RL advantage. In this paper, we show that a simple two-stage scheme, OPD-then-RL, consistently outperforms pure OPD, pure RLVR, and all such joint baselines across logic and math
reasoning benchmarks. Beyond the empirical results, we further provide a systematic understanding of this through pass@$k$ behavior, learning dynamics, and parameter updates, yielding a consistent explanation: OPD expands the student's coverage of teacher-supported solutions and RL sharpens within that support, while jointly optimizing the two signals causes them to interfere. To provide a practical recipe, we find that the OPD validation score is the key signal for when to switch to RL, and that OPD is a better cold start for RL than SFT. Together, our results establish OPD-then-RL as a simple yet strong way to combine the two methods, turning two entangled signals into complementary stages.
Read the full abstract ▾
All authors Boyan Li, Bingsen Chen, Chenghao Yang, Ping Nie, Chen Zhao, Xi Ye
Artificial Intelligence
Why Gated DeltaNet Survives 4-Bit Quantization: NVFP4 W4A4 for the Recurrent Half of a Hybrid 27B LLM
Sergii Kozyrev and Davyd Maiboroda
Hybrid LLMs pair softmax
attention with linear-
attention layers such as Gated DeltaNet (GDN), whose recurrent state summarizes the context in fixed size. Early community 4-bit quantizations of Qwen3.8-27B (48 GDN layers, 16
attention layers) left the GDN block in 8- or 16-bit precision – especially its decay and write-strength gates – on the intuition that errors in a recurrence accumulate over long contexts. We test that intuition by building Minima: NVFP4 W4A4 on all 496 linear layers, GDN included. Across perplexity at 4K/32K, MMLU-Pro, GSM8K, AIME'25, GPQA-Diamond, LiveCodeBench, and RULER
retrieval to 64K, Minima matches BF16 within seed noise (5-task average -0.52) while being the smallest (17.5 GiB) and fastest-prefill (+14-19%) recipe we compare, and its 32K perplexity gap shrinks with position. A four-part mechanism study explains why: (i) NVFP4's 16-element block scaling localizes the residual stream's extreme outliers, equalizing activation error across layer roles; (ii) the supposedly fragile gate projections are the least sensitive – softplus/exponential and sigmoid parameterizations compress ~11% GEMM error to ~2% output error; (iii) the delta-rule recurrence holds injected noise at a flat plateau over 32K
tokens and forgets a state impulse within hundreds of steps, because each write overwrites the state along the current key direction; (iv) the per-
token quantization cost washes out with context instead of compounding. We also repair a global-scale mismatch that arises when per-module-calibrated NVFP4 checkpoints are served by kernels that fuse those modules into one GEMM, and show calibrated FP8 KV-cache scales are performance-free. The result: a practical recipe – quantize everything, ship KV scales – and a mechanistic account of why the recurrent half of a hybrid LLM is the easy half to quantize. Checkpoint: https://huggingface.co/minima-ai/mnma_qwen3.8_27b_nvfp4
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.RO
Adaptive Vision-Language Grasping via Composable Foundation Priors and Generalizable Grasp Synthesis
Sixu Yan, Shikang Wang, Binhua Huang et al. (+11 more)
This paper proposes AdaRoboVLG, a task-adaptive
Vision-
Language-Grasp (VLG) framework that supports generalizable grasp synthesis across different robotic hands. Unlike existing VLG methods that tightly couple foundation models with end-to-end grasp policies, AdaRoboVLG learns an efficient generalizable base policy that generates and evaluates physically feasible grasp candidates through explicit kinematic mapping and force-closure-based stability estimation, while offloading task-dependent understanding to specialized foundation-model modules. These modules provide composable priors that are integrated into the grasp synthesis process, enabling contextually adaptive grasp synthesis without retraining the underlying grasp policy. Through extensive simulation and real-world experiments, we demonstrate that (i) the base policy exhibits efficient learning and strong cross-hand generalization, (ii) the framework effectively incorporates spatial, cognitive, and temporal priors to address three representative grasping challenges without compromising grasp synthesis performance compared to state-of-the-art methods, and (iii) these priors can operate jointly to enable functional grasping in cluttered and dynamic environments. These results indicate that decoupling physical grasp synthesis from task-dependent understanding provides a scalable paradigm for robotic grasping, allowing future advances in foundation models to be directly translated into improved grasp capabilities without redesigning or retraining the underlying grasp policy. Supplementary
videos are available at https://adarobovlg.github.io/
Read the full abstract ▾
All authors Sixu Yan, Shikang Wang, Binhua Huang, Xuanlai Tang, Guohua Fan, Fan Huang, Haoxuan Li, Yongkang Li, Yuhan Li, Bencheng Liao, Zeyu Zhang, Wenyu Liu, Hangxin Liu, Xinggang Wang
Artificial Intelligence
DRACO: Fine-Grained Credit Assignment with Dynamic Rubrics for Long-Horizon Agent Training
Shubham Gandhi, Saurabh Goyal, Kiran Kate et al. (+1 more)
Reinforcement Learning from Verifiable Rewards works well when a task has a programmatic checker, but most long-horizon
agent domains have none. We work in the outcome-blind setting, where ground-truth success signals are not available. Multi-criteria rubrics are a popular way to supply such a reward; they are scored once per trajectory, but a single scalar is a poor signal across tens of steps. We propose DRACO: Distributing Rubric-based Advantage for Credit Optimization. It generates rubrics dynamically during training to track the policy's evolving capability, scores those rubrics once per completed trajectory, and redistributes that judgment over the steps responsible for annotated rubrics to produce differentiated per-step advantages in GRPO. The redistribution is closed-form and does not introduce any trained attribution module. On AppWorld, DRACO gains 15.9 points over the base model and 5.3 points over GRPO trained with a sparse ground-truth reward, despite not using any verifiers itself. On out-of-domain Tau-Bench, it gains 5.3 points over the base model even without a frontier judge, beating both ground-truth-reward training and other rubric-based training settings. The code for DRACO is available at https://github.com/IBM/draco.
Read the full abstract ▾
All authors Shubham Gandhi, Saurabh Goyal, Kiran Kate, Yara Rizk
Artificial Intelligence · Cross-listed from cs.CR
A Non-Formulable Theorem: A Fundamental Limit of Finite Syntactic Systems and Its Consequences for Security and AI
Fabio F.G. Buono
For every coherent and sufficiently expressive finite syntactic system S, we prove the existence of at least one
theorem that S cannot produce autonomously. The result is a metatheorem: it proves the existence of a
theorem, and applies to every finite syntactic system - security mechanisms, AI systems, formal verifiers, legal systems, economic models, and the formal system in which it is itself proved.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CV
Tingyu Song, Mingxin Li, Yanzhao Zhang et al. (+5 more)
MLLM-based
embedding models remain limited in compositional
retrieval, often failing to distinguish scenes containing the same concepts but different attribute-object bindings. Yet the same backbone can resolve such distinctions when used as a cross-attentive reranker, motivating us to distill its compositional judgments into the
embedding model. We propose CORE, which synthesizes candidate lists spanning five compositional matching levels and introduces a Rank-KL objective that trains the
embedding model to reproduce the reranker's fine-grained ranking. We further introduce a graded evaluation protocol and compare contrastive learning, pairwise CoSENT, and listwise Rank-KL under the same data and tuning budget. Our comparison shows that both CoSENT and Rank-KL use the multi-level supervision more effectively than contrastive learning, with Rank-KL achieving the strongest overall performance. Across three compositional
reasoning benchmarks (COLA, SUGARCREPE++, NEGBENCH), CORE-RERANKER-8B achieves an 82.7% total average, outperforming Jina-Reranker by 10.7 points, while CORE-EMBED-8B achieves the best total average (0.666) among all evaluated
embedding models. The improvements transfer to the MCMR
benchmark without sacrificing
retrieval performance on COCO and Flickr30K.
Read the full abstract ▾
All authors Tingyu Song, Mingxin Li, Yanzhao Zhang, Dingkun Long, Chu Liu, Pengjun Xie, Yilun Zhao, Shu Wu
Artificial Intelligence · Cross-listed from cs.CR
PatchBench: Evaluating AI Agents for Vulnerability Patching
Chihao Shen, Jiacheng Li, Aastha Mahajan et al. (+3 more)
AI
agents have recently demonstrated strong performance in automated vulnerability patching. However, existing evaluations often validate a patch only by testing whether the provided Proof-of-Concept (PoC) input still triggers a crash. This leaves two key threats to validity:
agents may reproduce memorized historical developer patches, or they may generate surface-level fixes that only suppress the reported crash. We study these concerns for C/C++ vulnerability patching. We introduce a patch similarity metric to detect memorized patches. On average, 25% of the
agent patches exhibit substantial similarity to historical developer patches, indicating that patch memorization is a real threat to the validity of vulnerability patching evaluations. Meanwhile,
agents also frequently exploit
benchmark structures to pass patch validation by patching on the crash stack trace to suppress the crash, rather than localizing and fixing the root cause of the vulnerabilities. To handle these issues, we propose PatchBench, a new
benchmark for evaluating AI
agents on realistic vulnerability patching tasks. PatchBench selects vulnerabilities whose ground-truth fixes lie outside the crash stack and uses vulnerability transplant and code mutations to migrate historical vulnerabilities into new repository contexts, reducing the risks of surface-level fixes and patch memorization. We develop new patch validation methods that thoroughly evaluate both security and semantic correctness of
agent patches. Across 11 state-of-the-art
agents, including the top three AIxCC
agents, the original PoC-only validation inflates the patching task solve rate of
agents by 1.83$\times$ on average. Our results reveal key limitations of current patching
agents and point to future research directions for more reliable vulnerability repair.
Read the full abstract ▾
All authors Chihao Shen, Jiacheng Li, Aastha Mahajan, Jeffery Siyuan Tian, Yonghwi Kwon, Yizheng Chen
Artificial Intelligence · Cross-listed from cs.CV
TAP-Path: Task-Adaptive Structural and Token Pruning for Efficient and Trustworthy Pathology Foundation Models
Mehedi Hasan, Ashfak Yeafi and Md Khairul Islam
Pathology foundation models improve transferable representation learning for histopathology, but recent gains often rely on encoders with hundreds of millions of parameters and high inference cost. We propose TAP-Path, a task-adaptive compression framework that directly restructures a pretrained Virchow2 encoder rather than distilling it into a separate student. TAP-Path combines validation-driven
transformer-block selection, physical removal of redundant blocks, input-adaptive patch-
token pruning, multi-depth feature recovery, and a lightweight gated task head. The final model retains 24 of 32
transformer blocks and 70% of patch
tokens after
pruning, reducing encoder parameters by 24.96% (631.24M to 473.70M) and analytical encoder compute by 35.20% (340.13G to 220.40G FLOPs). Across three task-head optimization seeds, TAP-Path achieved $87.98 \pm 0.067%$ test accuracy, $81.26 \pm 0.49%$ balanced accuracy, and $82.38 \pm 0.48%$ macro-F1 on a 32-class histopathology
benchmark, compared with 86.89% for full Virchow2 and 87.67% for UNI2-h. TAP-Path achieved a Brier score of $0.1800 \pm 0.0005$ and failure-detection AUROC of $0.9047 \pm 0.0060$. A validation-only rare-aware objective improved rare-class balanced accuracy in a secondary operating analysis. Frozen external evaluation on 433 CPTAC samples yielded $91.22 \pm 0.83%$ accuracy and $91.10 \pm 0.81%$ balanced accuracy. These results show that task-adaptive structural and
token sparsification can improve the accuracy-efficiency trade-off of large pathology foundation models while preserving reliability under internal and external evaluation.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.LG
Subspace Inference Enables Efficient Active Reward Learning from Preferences
Yutai Zhou and Erdem B{\i}y{\i}k
Reinforcement learning from human feedback (RLHF) has emerged as a powerful yet sample-inefficient approach for learning reward models from human preferences, making active learning a critical component in synthesizing informative preference queries. However, effective uncertainty quantification required for active learning remains a key challenge for large neural network reward models. In this paper, we introduce PreferenceEKF, a sample-efficient approach that tracks reward model uncertainty by framing active preference learning as a sequential
Bayesian filtering problem. Instead of relying on computationally prohibitive posterior inference over the full neural network parameter space, our method performs sequential inference via an extended Kalman filter within a low-dimensional parameter subspace, continuously updating the reward model posterior as new preference queries arrive. Our approach enables scalable sampling of neural network parameters to efficiently compute acquisition functions for active reward learning. Experiments on the D4RL and V-D4RL
benchmarks demonstrate that our approach achieves better sample efficiency, runtime, scalability, and calibration compared to other
Bayesian deep learning approaches, and the learned reward models lead to competitive offline reinforcement learning policy performance. This highlights the potential of scalable
Bayesian methods for preference-based reward modeling in RLHF. Our code is available at https://github.com/yutaizhou/bnn_pref.
Read the full abstract ▾
Artificial Intelligence
Spurious Advantage Hidden in GRPO
Jiamian Wang, Samyadeep Basu, Koustava Goswami et al. (+2 more)
Group Relative Policy Optimization (GRPO) is widely studied for reinforcement learning with verifiable rewards, where its advantage
estimator assigns each rollout a magnitude from within-group reward statistics. In the common case, this magnitude rewards rollouts that reach the correct answer through
reasoning. Yet, an overlooked case shares the same surface: a rollout may land on it by guessing, and the formula still assigns a high magnitude, which we identify as the spurious advantage. This arises in three cases: bounded-answer tasks with a small candidate set; open-answer sets hosting bounded sub-cases; and search
agents whose budget opens many paths to the same answer. In all three, this misleads the policy toward guess-like behaviors. We propose SIGNBALANCE, whose magnitude is composition-free: it keeps the verifier sign, uses a global scale, and restores zero-mean balance via a stop-gradient per-class rescaling. Across math and search
agent benchmarks at different scales, SIGNBALANCE matches GRPO on open-answer math and improves on bounded-answer math and search
agents. Code will be released.
Read the full abstract ▾
All authors Jiamian Wang, Samyadeep Basu, Koustava Goswami, Tong Yu, Zhiqiang Tao
Artificial Intelligence · Cross-listed from cs.SE
When Models Edit Too Much: On the Fidelity of Minimal Code Edits
Tongyao Zhu, Wei Hern Lim and Min-Yen Kan
Large
language models (LLMs) are increasingly used to edit existing code, but correctness alone is not enough: useful repairs should also be minimal, reviewable, and faithful to the original implementation. We study over-editing, the tendency of a model to rewrite code beyond what is required to fix a bug. We construct an evaluation framework from 400 BigCodeBench problems by injecting controlled AST-level corruptions into reference solutions, giving each repair task a known minimal patch. Across frontier LLMs, over-editing is widespread even among strong models like GPT-5.5: high Pass@1 can coexist with unnecessarily large edits and added cognitive complexity. A preservation instruction substantially reduces this behavior, lowering average excess Levenshtein distance from 0.195 to 0.131, reducing added cognitive complexity by 26.6%, and increasing Pass@1 by 2.3 points. However, these gains do not simply follow from a larger
reasoning budget or larger models. We next ask whether minimal editing can be learned directly during post-training. We observe that supervised fine-tuning overfits to seen corruption patterns, whereas reinforcement learning gives the best out-of-domain edit-fidelity and performance-retention trade-off. These results position edit fidelity as a distinct axis of code-repair quality and show that it can be measured and learned.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CL
Translation as a Decision Space: A Multi-Agent Perspective on Low-Resource Dialect Generation
Hasan Alkhder, Mohammad Abboush, Igor Tchappi et al. (+2 more)
Neural machine translation (NMT) systems typically produce a single output per input, obscuring the alternative decision trajectories implicitly available within
multilingual decoding. This opacity becomes particularly problematic in low-resource dialect settings, where multiple linguistically valid realizations may differ in lexical authenticity, register, and structural stability. We propose reframing translation as a structured decision space explored by autonomous translation
agents. Instead of analyzing a single output, we model distinct translation pathways as
agents operating over a shared
multilingual backbone. Inter-
agent divergence is treated not as error but as an interpretable behavioral signal. We conduct an empirical study on Turkish–Syrian Arabic translation using three
agents: (1) zero-shot direct translation, (2) dialect-stabilized translation via lightweight fine-tuning, and (3) pivot translation through English. Evaluation is performed on 5,000 dialogue sentences, while stabilization is trained on 5,000 additional Turkish–Syrian sentence pairs drawn from television dialogue and MADAR-Turk resources. Rather than optimizing for conventional performance metrics, we quantify structured behavioral displacement using dialect marker frequency, lexical proximity to standardized Arabic, and structural variance. Lightweight stabilization nearly doubles dialect marker usage, increasing it from 0.2266 to 0.4988, while significantly reducing structural instability. Pivot mediation introduces normalization pressure and measurable compression effects, whereas zero-shot translation exhibits the highest decision variance. We argue that translation divergence across
agents reveals latent decision flexibility within
multilingual models and we provide a principled interpretability framework for low-resource dialect generation.
Read the full abstract ▾
All authors Hasan Alkhder, Mohammad Abboush, Igor Tchappi, Ahmet Zengin, Amro Najjar
Artificial Intelligence
IRWOZ 2.0: A Large Language Model-driven Dialogue Dataset for Industrial Robot Conversations
Chen Li and Dimitrios Chrysostomou
IRWOZ has improved industrial human-
robot interaction (HRI) dialogue systems through domain-specific annotations. However, its initial version contains substantial noise in dialogue states and utterances, limiting state-tracking accuracy. We introduce IRWOZ 2.0, which addresses these limitations through large
language model (LLM) enhanced generation (Mistral/Claude-3.5) and quality refinements. Our improved
dataset expands to 390 dialogues across 4 industrial domains (Assembly, Delivery, Position, Relocation), featuring manual corrections and automated typo removal.
Benchmark experiments on dialogue state tracking demonstrate significant improvements, with GPT-2's BLEU-4 score increasing from 0.1651 to 0.5604 compared to original IRWOZ. To support industrial HRI research, we publicly released IRWOZ 2.0
dataset at https://ieee-dataport.org/documents/irwoz-20-large-
language-model-driven-dialogue-
dataset-industrial-
robot-conversations
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CE
Influence of Extruded Filament Shape on Buildability in 3D Concrete Printing: A Geometry-Informed Deep Learning-FEM Approach
Giacomo Rizzieri, Saif-Ur-Rehman, Jörg F. Unger et al. (+1 more)
The
geometric morphology of deposited filaments can significantly influence the structural performance and stability of 3D concrete-printed (3DCP) structures. However, most finite element (FEM)-based approaches for buildability assessment represent printed layers as simplified rectangles, potentially limiting predictive accuracy. This study proposes a geometry-informed modelling framework that integrates the deep-learning-based filament shape prediction tool ShapeGen3DCP with a layer-activation FEM approach to investigate the effect of realistic filament geometries on buildability. The framework generates geometry-aware numerical models directly from material and process parameters, eliminating the need for experimental filament characterization or computationally intensive fluid-flow simulations. Validation against experimental data and a parametric study of rectilinear walls demonstrate that extrusion parameters and the resulting filament geometry can significantly influence buildability predictions. Realistic filament representations are particularly important for free-flow deposition, whereas layer-pressing strategies are less sensitive to
geometric simplifications. Among the investigated representations, an elliptical approximation provides an effective balance between
geometric fidelity and modelling simplicity. When rectangular representations are preferred to enable regular computational meshes for faster simulations, defining their dimensions based on volume conservation improves prediction reliability compared with calibrating them using either the maximum filament width or the interlayer contact width. Overall, the proposed methodology demonstrates the importance of incorporating filament geometry into 3DCP simulations and provides practical guidance for selecting efficient and accurate
geometric representations for buildability assessment.
Read the full abstract ▾
All authors Giacomo Rizzieri, Saif-Ur-Rehman, Jörg F. Unger, Annika Robens-Radermacher