Graph Hierarchical Recurrence (GHR) is a new framework that enhances Graph Neural Networks and Graph Transformers by jointly processing the input graph and a pooled hierarchical abstraction. It addresses the limitation of existing models in handling predictions that depend on correlations between distant graph regions, especially under out-of-range generalization where test instances require interactions beyond training distances. Across many long-range benchmarks, GHR consistently improves performance, achieving state‑of‑the‑art or competitive results on multiple tasks.
By Stefano Carotti, Marco Pacini, Alessio Gravina, Davide Bacciu, Bruno Lepri, Sebastiano Bontorin
Large language model agents depend on external harnesses to exchange information with their environment and to recover from execution errors, but recovery is typically evaluated only by overall task success, masking a key trade‑off. The authors treat recovery as a causal decision problem, comparing outcomes with and without recovery from the same execution state to separate rescue from harm and analyze how its value evolves over time. They propose the Causal Intervention Router (CIR), a lightweight policy that uses pre‑recovery information to decide when intervention is beneficial, achieving a 3‑point increase in success on long‑horizon ALFWorld tasks with Qwen3‑14B while preserving correct observations and demonstrating that recovery’s benefit is not solely due to new observations.
By Shuyao Xiao, Shengling Wang, Xuan Chen, Ke Chao, Ming Cui, Feifei Qian, Chaoyang Mei, Fanlin Meng, Ziming Yu, Junxi Yin
arXiv:2610. 00416v1 Announce Type: new Abstract: Evaluating large language models becomes increasingly challenging as their capabilities advance: benchmarks can saturate, public test sets risk contamination, and assessing harder tasks can require expensive grading or execution infrastructure.
By Timoth\'ee Lesort, Alejandra L\'opez de Aberasturi G\'omez, Tristan Karch, Tom Veniat, Philippe Modard, Karl Tuyls, Ludovic Denoyer
The paper "Science or Slop?: Benchmarking and Mitigating Scientific Slop in AI-Generated Papers" introduces SciSlopBench, a dataset of 390 AI‑generated papers paired with human‑written counterparts, and defines six measures across Structure, Argument, and Artifacts to detect scientific slop. The authors show that these measures can identify AI papers with 85.9% accuracy and that higher slop correlates with lower ICLR ratings and distinguishes rejected from accepted papers. They also propose SciSlopHarness, a framework that guides a fixed LLM to revise only evidence‑supported sections, reducing the AI‑human gap by 63% without human reference targets.
By Yerim Oh, Young-Jun Lee, Jaewoo Ahn, Gunhee Kim, Dongyeop Kang
Legal Research Bench (LRB) is a new benchmark comprising 413 open-ended U.S. legal research questions, each paired with a gold answer, supporting authorities, and a binary grading rubric. The study evaluates thirteen advanced language‑model agents using web search, case‑law search, page parsing, and retrieval tools, scoring responses only when all required criteria are met and cited authorities verify. Results show that even the best model, Claude Opus 4.8, achieves full correctness on only 42.9% of questions, with performance varying by legal area and task complexity, and no clear link between more tool calls or inference cost and higher accuracy.
By Katrina Drozdov, Oliver Chen, Langston Nashold, Rayan Krishnan
The paper introduces Quarantined Expert Shutdown (QES), a new backdoor containment strategy for large language models. QES allows backdoor learning to occur during training but routes it into a designated, quarantined expert that can be disabled at deployment. The method achieves significant reductions in attack success rates while largely preserving model utility.
By Jianwei Li, Min-Seon Kim, Jung-Eun Kim
The paper introduces a pipeline that automatically creates ontology‑grounded multiple‑choice question benchmarks for evaluating large language models (LLMs) on logical reasoning tasks in scientific AI. By using OWL 2 ontologies, correct answers are guaranteed by design and distractors are generated and formally verified as incorrect through an OWL reasoner. Experiments on three ontologies—Pizza, PMDco, and DOID—yielded 112, 2,491, and 15,216 MCQs, respectively, with high natural‑language quality and challenging zero‑shot performance for six LLMs.
By Nishtha N. Vaidya, Stephan Grimm, Thomas Hubauer, Thomas A. Runkler
ReLiveGym is a diagnostic environment that evaluates long‑lived language‑model agents over weeks of chronologically replayed real‑world streams such as news, market data, and social media. The tasks vary in time sensitivity, reasoning depth, and recurrence, and the study tests eight base language models to see how model choice and harness design—especially action timing—affect performance. Continuous learning from hindsight feedback is also examined to address failure modes in these long‑term tasks.
By Xisen Jin, Jingheng Li, Zhenglun Chen, Junyi Du, Xiang Ren
Robust Nash Alignment introduces a game-theoretic framework that seeks a policy with a high worst-case win rate against both an adversarial competitor and any preference kernel within an ambiguity set around a nominal preference. The authors propose a four-player primal-dual proxy game and an optimistic mirror descent-ascent algorithm to efficiently optimize this robust objective, proving convergence guarantees and demonstrating improved performance in controlled tabular games and LLM alignment experiments.
By Shihab Ahmed, Debamita Ghosh, David Tang, Yudan Wang, Alvaro Velasquez, Yue Wang
ActiveSaddler introduces automated curriculum learning for harness optimization, treating the evolving training curriculum as a non‑stationary bandit problem. It identifies reusable failure patterns, estimates learning progress for each, and balances revisiting known weaknesses with exploring new scenarios, allowing the curriculum to co‑evolve with the harness. Experiments on GAIA2 and Terminal‑Bench 2.0 show consistent improvements in harness performance, with Pass@1 gains of 4.4 and 7.5 percentage points over fixed‑order baselines.
By Sungho Park, Wonjoong Kim, Jue Zhang, Wook-Shin Han, Pengfei Gao, Chanyoung Park, Yongqiang Yao, Rao Fu, Elsie Nallipogu, Qingwei Lin, Victor R\"uhle
The study evaluates 66 combinations of four configurable harnesses and five language models across three benchmark suites, revealing that model rankings and best harnesses vary significantly with the task. Notably, the openJiuwen harness consistently yields the highest scores for the Kimi model, while GPT performs best with the lean PI scaffold on Terminal‑Bench 4. The findings demonstrate that a model’s performance is highly dependent on the harness it is paired with, and that higher cost or a vendor’s own harness does not guarantee superior results.
By Yixuan Li, Yiyun Zhou, Yao Long Teng, Fuchao Yang, Yanchen Deng, Zhiyi Lyu, Xuyu Dong, Feng Chen, Bo An
The paper evaluates how Large Language Models generate preference distributions for air travel, restaurants, and consumer products. It finds that while each model produces self-coherent outcomes that stabilize quickly, there is significant disagreement across different model families and scales, with little consensus even on the most probable preferences. These discrepancies persist across various decoding strategies, temperature settings, and prompt variations, indicating that the model choice itself has a larger impact than prompt wording.
By Fan Huang, Minsuk Kim, C. Tyler Diggans, Filippo Radicchi
The paper introduces InFlowOp, a label‑free optimization framework that assigns costs to each decision in a multi‑agent workflow, balancing agent competence against execution time. It determines task granularity and agent assignment before execution and corrects faults during execution using the same cost metric. The authors also present Braid, a benchmark for multi‑agent coordination, and show that InFlowOp outperforms single‑agent baselines by up to 11.97% across various domains.
By Xuehang Guo, Haoyu Wang, Shengyu Chen, Zach Chen, Wei Cheng, Qingyun Wang, Haifeng Chen
The paper introduces Independent–Communicate–Revise (ICR), a framework that isolates communication effects in large language model multi‑agent systems by fixing initial reasoning and measuring how messages influence answer revision. ICR evaluates correction, preservation, and selectivity across four reasoning benchmarks, revealing that similar overall accuracy can mask divergent revision behaviors. The study shows that richer messages can both improve and harm outcomes, and that receiver policies can shift preservation and correction dynamics differently across tasks.
By Shixuan Li, Wei Yang, Peiyu Zhang, Anzhe Cheng, Heng Ping, Paul Bogdan
The paper introduces APIVIS, a training-time framework that integrates finite-budget Gumbel search into reinforcement learning with verifiable rewards (RLVR) for mathematical reasoning. APIVIS combines direct and searched responses within each rollout group, uses selective supervision on search-improved tokens, and applies value-guided selection to improve verifier rewards at each searched state. Experiments on standard mathematical reasoning benchmarks and various model scales show significant performance gains over existing search-based methods.
By Shaohuai Liu, Yuning Wu, Haoran Liu, Enzo Jia, Devin Chen, Kai Wei
The paper introduces a typed snapshot‑settlement contract for auditing concurrent actions in large language model agent environments. It evaluates three properties—order sensitivity, useful progress, and replay consistency—across five settlement policies, using 28,800 exhaustive permutation trials and 2,160 scripted multistep episodes. Results show that joint policies are spatially order‑invariant with fixed priorities, but conservative rejection only completes 31.25% of agents in a six‑agent doorway task compared to 90.28% for random tickets, while a full‑state journal audit successfully replays 156 checkpoints and rejects 1,332 constructed corruptions.
By Haotian Chen, Bowen Ye, Yuning Zhang, Jingkun Yu
The paper explores how large language models (LLMs) can be grounded in dynamic stochastic general equilibrium (DSGE) simulators to generate and evaluate economic policy actions. By embedding an instruction‑tuned LLM within six Snowdrop‑backed DSGE models, the authors create a long‑horizon credit‑assignment problem where the model observes economic states, selects bounded policy actions, and receives simulated outcomes and rewards. They compare reinforcement learning methods—PPO, which uses a learned value function to propagate delayed rewards, and GRPO, a critic‑free baseline—to assess how well the LLM’s policy decisions align with simulated economic dynamics, testing factors such as semantic signals, reward horizons, and cross‑simulator transfer.
"whyItMatters":"The study demonstrates a method for evaluating LLM‑generated policy proposals based on their actual simulated economic consequences rather than merely their linguistic plausibility."
By Aditya Dubey, Namah Gupta, Vinti Agarwal
The paper introduces Federated Agent Optimization (FAO), a framework for enabling large language model agents to improve collaboratively while keeping raw data, trajectories, and private knowledge local. FAO treats agent capabilities—such as memory, tools, rewards, skills, and structured knowledge—as a multi‑objective optimization space that balances utility, privacy leakage, and communication cost. It outlines methods for abstracting, protecting, aggregating, and adapting private experience into transferable capabilities, and highlights key challenges and future research directions for trustworthy federated agent systems.
By Qiang Yang, Zhiqiang Kou, Xueyi Zhang, Dong-Dong Wu, Hanlin Gu, Jing Guo, Yang Liu, Di Jiang, Qian Xu
The paper introduces an educator‑guided large language model (LLM) pedagogical agent that provides scaffolded feedback for conceptual database design. Embedded in an entity–relationship diagram editor, the system bases its feedback on the student’s artifact, assignment requirements, educator‑authored rubrics, and instructional resources, using a four‑stage workflow that progresses from concept checks to low‑detail feedback and localized clarification. In a deployment across three ERD environments with 383 feedback episodes, 71.1% of target‑level changes incorporated the hidden diagnostic target, and qualitative analysis highlighted the benefits and challenges of staged disclosure.
By Sara Riazi, Pedram Rooshenas
DeFA is a dependency-guided framework that attributes failures in large language model agents by constructing an event dependency graph and a failure propagation graph from protocol relations and semantic dependencies. It identifies violating events, traces their sources and effects, and determines the decisive error, responsible agent, and error category. The method supports long trajectories through segmentation and has shown superior accuracy on text, image, and video tasks, while its diagnostic feedback can improve agent performance on subsequent tasks.
By Bo Deng, Xinlei Zheng, Yi Wei, Kang Zhou, Chongyang Tao, Renzhao Liang, Xuanren Chen, Lifan Guo, Chi Zhang