The paper investigates how an informed adversary can influence the optimal signal in a constrained signalling channel. It finds that the adversary‑robust optimum aligns with the salience pole on most items, differing only on a small subset where the salience‑to‑Bayes coordinate is undefined. The study demonstrates that as the adversary’s persuasion budget increases, the optimal signal shifts from a posterior‑maximizing to a margin‑maximizing strategy, and provides a diagnostic check for evaluating adversary‑awareness.
By Cris Huynh
JevSpawn is a new compositional policy that links natural language task specifications to finite probabilistic exploration, enabling LLM agents to generate actions more efficiently. It uses parallel action spawning, feedback‑driven branch selection, representation revision, and recovery from retained alternatives to adapt actions during interaction. Evaluations on eight benchmark tasks show that JevSpawn outperforms seven agent baselines and a TypeSafe Jev variant, improving task performance and speeding navigation.
By Haoyang Su, Weiran Huang
CompMat-Bench is a new benchmark comprising 94 tasks drawn from recent computational materials science studies, designed to evaluate AI agents on realistic research steps without requiring costly simulations during testing. The benchmark pre‑reproduces inputs and outputs to provide ground truth, allowing agents to be graded with fixed rules rather than an LLM judge. It supports both single tasks and multi‑step workflows, with varying levels of methodological guidance, and shows that while agents can achieve high pass rates on individual tasks, performance drops in longer workflows or with reduced guidance, often due to scientific rather than software errors.
By Chenmu Zhang, Levi Felix, Jun-Jie Zhang, Xingfu Li, Xuelian Jiang, Tao Jiang, Subhendu Mishra, Xixi Qin, Boris Yakobson
Kepler is an open‑source harness that represents hypotheses as executable world models and validates them through retrospective transition checks and conditional prediction checks. In the ARC‑AGI‑3 benchmark, a frozen Claude Opus 5 configuration achieved a perfect 100.00 RHAE on all 25 public games without per‑game model selection or score‑conditioned reruns, and matched or outperformed median‑human action counts on 181 of 183 levels. The study also identified three evaluation failures and highlighted that public‑set score alone has limited discriminative value, advocating for first‑attempt, cost‑conditioned, and verification‑aware reporting.
whyItMatters":"The results demonstrate that a purely score‑based evaluation can be misleading, underscoring the need for more rigorous, cost‑aware, and verification‑aware metrics in AI benchmark assessments."
By Wensen Wu
The paper introduces OSCAR, an LLM‑based framework that translates business descriptions into accurate optimization models while verifying and improving them through a simulator, coder, and reviewer. OSCAR uses a cost‑ordered escalation strategy to select among LLMs of varying price and capability, achieving 95–100% accuracy on benchmark problems with local, open‑weight models. The framework also provides competitive guarantees and token‑cost advantages over existing LLMs like Codex and Claude Code.
By Jinzhi Bu, Haixin Tang, Huanan Zhang
ABDA-NL is a natural‑language interface for the ABDA argument‑based reasoning system, which uses ASPIC knowledge bases under grounded semantics. It lets users view accepted, rejected, or undecided conclusions, interactively explore the grounded discussion game, and experiment with what‑if scenarios by suspending assumptions, rules, or preferences. A large language model bridges natural language and formalism, answering questions from reference documents and translating plain‑English edits into formal statements, while the deterministic ABDA engine remains the sole source of arguments and acceptance labels, with all model proposals validated by the user before acceptance.
By Shawn Bowers, Martin Caminada, Haoyang Liu, Bertram Lud\"ascher
RISED introduces a framework that uses rubric-based textual feedback to improve training of a single large language model (LLM) agent across multiple interactive environments. By having an LLM judge tag rollouts with a shared rubric vocabulary, the system guides both online data selection and policy supervision, enabling richer cross‑environment relationships and within‑group reward contrast. Experiments show that RISED achieves the highest mean pass rate and ranks first or second in every individual environment, with rubric analysis revealing behavioural changes behind these gains.
By Jingtan Wang, Sirajul Salekin, Young mok Jung, Javier Movellan, Bryan Kian Hsiang Low, Manjot Bilkhu
The paper studies how voting over multiple large language model (LLM) responses can be optimized under a fixed call budget. It introduces a recoverability threshold that quantifies the gap between discovering a correct answer and ensuring it wins the plurality vote, showing that the candidate set can only grow while the set of reachable winners can only shrink. The authors also present a gold‑free locking certificate that identifies the earliest prefix where all remaining continuations produce the same fixed‑budget output, and demonstrate empirical gains in accuracy and call efficiency through input permutation and exact locking.
By Shaoang Li, Jian Li
AbsorbEvo is an agentic framework that autonomously designs microwave absorbers by translating natural‑language performance goals into full‑wave‑simulated designs. It combines language reasoning, physics‑based prediction, and historical feedback to guide a candidate evolution strategy, using a low‑cost predictive model to rank designs before simulation. In tests on AbsorbBench‑36, AbsorbEvo achieved a 79.17% task success rate, outperforming generic agents and random search.
By Zhicheng Feng, Yubo Zhao, Xuefeng Yao
The paper introduces Dependency‑Aware Reward Shaping (DARS), a method that assigns step‑level credit in reinforcement learning by modeling task progress as a graph of predicates with prerequisite relations. Annotators mark each step’s effect on predicates, and DARS discounts verified predicates based on distance from broken prerequisites while preserving independent ones, converting these annotations into signed per‑step rewards. Experiments on five task families with models ranging from 1.5B to 8B show that DARS improves success rates by up to 10 points over GiGPO, boosts WebShop and Search‑R1 QA scores, complements AEPO on AIME24/25, and outperforms OmniOPD in tool‑free reasoning, with ablations confirming the contribution of step‑level credit, dependency attenuation, and graph topology.
By Ziyi Chen, Yan Zhang, Jianhui Wei, Daoan Zhang, Zuozhu Liu
The study investigates how reputation, strategy, and emotional signals influence cooperation in generative AI models using the iterated prisoner's dilemma. Non‑reasoning models (Claude 3.5, Gemini 2.0 Flash, GPT‑4o) showed cooperation shaped by all three factors, while reasoning models (Claude 4.6, Gemini 3, GPT‑5.2) relied more on strategy and reputation, displayed reduced emotional influence, and exhibited varied end‑game behaviors. These results highlight the growing sophistication and heterogeneity of AI social behavior, suggesting the need for standardized cooperation benchmarks.
By Celso de Melo, Zishan Feng, James Hale, Kazunori Terada, Giorgio Coricelli, Jonathan Gratch
ITC-MoE introduces an Importance-guided Token-aware Compression framework for Mixture-of-Experts Diffusion Language Models. It combines Adaptive Tucker Compression, which uses activation and gradient importance to jointly factorize expert weights and allocate ranks, with Token-aware Compensation and Routing that applies low‑rank adjustments to hot tokens and limits expert candidates for cold tokens. The method achieves significant reductions in computation and storage while maintaining generation quality, exemplified by a 30% compression budget that preserves 96.33% accuracy on MultiArith and delivers up to a 7.22× speedup.
By Lianjun Liu, Shipeng Li, You Huang, Weiqi Yan, Mingte Qiu, Huazhong Liu, Xiaofeng Zhu, Yunshan Zhong
DAYJOB is a new benchmark comprising 130 long‑horizon professional tasks created by experts in healthcare (50 tasks) and finance (80 tasks). Each task is packaged as a containerized Harbor environment and evaluated against a detailed binary rubric, requiring agents to meet every criterion to pass. In tests across 30 model configurations, the best model (Claude Opus 5.5) achieves about 24% success in both domains, while the median model scores below 3%.
By Stephanie Finley, Liudas Panavas, Thomas Mikkelson, Cam Hinton, Stacey Ganss, Bradley Monton, Emily Kendall, Michelle Spradlin, Lydia Bye, Michael O'Brien, Lauren Ylvisaker, Derek Ray, Suhaas Garre, Sushant Mehta, Edwin Chen
Gacha Decoding is an inference-time method that elicits diverse language model generations by treating diversity as an instruction-following problem. It combines a model’s instruction-following ability with randomness from an external RNG to identify and realize distinct response modes, outperforming existing diversity approaches across open-ended domains. The method scales with model capability, achieving higher diversity at equal quality and discovering novel modes with far fewer samples.
By Scott Geng, Yufei Zhang, Joseph Lee, Jerry Li, Marjan Ghazvininejad, Pang Wei Koh
AiSearch is a flexible multimodal retrieval framework that uses Vision Language Models (VLMs) to enable natural language search over images and videos. It supports interactive search refinement through user feedback, allowing results to be tailored to the user's intent in real time. The system also provides visual benchmarking across multiple VLMs, enabling users to choose the most suitable model for their specific task.
By Ali Koksal, Mei Chee Leong, Vicky Sintunata, Ching Ling Chin, Wee Teck Fong
Beyond Memory: Harnessing Long-Horizon Agents with Explicit Belief States introduces PoS, an inference-time framework that builds and maintains explicit belief states to guide large language model agents. Each belief state combines an estimate of the current world with unresolved task requirements, making clear what the agent still needs to learn and accomplish. PoS validates consistency, monitors task progress to detect Belief Trapping, and tailors recovery to the trapping pattern and unresolved requirements, achieving top performance across four benchmarks with all three LLM backbones.
By Yu Luo, Jiamin Jiang, Yimin Zuo, Xidao Wen, Rongchen Gao, Yongqian Sun, Shenglin Zhang, Guiyang Liu, Cheng Zhang, Fang Situ, Qi Zhou, Dan Pei
The paper introduces MCRI, a four‑dimensional framework for analyzing and evaluating agent skills, and implements it as MCRI‑Eval, a large‑language‑model‑based evaluation method. Using 63,812 public skills from OpenClaw and 58,275 skill‑conditioned executions across BigCodeBench, BFCL‑Fundamental, and Mind2Web, MCRI‑Eval’s scores correlate with community popularity and outperform other methods in downstream ranking agreement. The evaluation also shows that MCRI‑Eval improves top‑1 skill selection by 17.7, 22.8, and 19.6 percentile points on the three benchmarks, offering a valuable pre‑execution signal for prioritizing promising skills before costly evaluation.
By Zongrui Yang, Li Xintong, Runchen Xu, Zhongsheng Wang, Zhedong Lin, Haoyuan Li, Jiamou Liu
The paper argues that evaluating agents as fixed models is insufficient, proposing instead to treat them as configurable systems. Using a new benchmark of four scientific tasks, the authors analyze how five configuration aspects—task information, reasoning, self‑verification, time budget, and backbone model—affect performance, noting that about 54% of outcome variance arises from run‑to‑run differences even with the same settings. The study finds that providing more task information has the strongest impact, while interactions among settings (e.g., extra time only helps with adequate information or model capability) and the choice of verification tools significantly shape agent behavior.
By Luis Wiedmann, Leander Girrbach, Cordelia Schmid, Zeynep Akata
ScholarCatalyst is a new benchmark that evaluates how well AI systems can retrieve research papers that inspire new work. The dataset was created by having 184 lead authors of 207 recent computer science papers annotate which earlier papers helped their projects, providing detailed rationales. The benchmark tests retrieval from the literature available at the start of a project, revealing that current agentic search and even advanced models like Claude Fable 5.1 perform only modestly better than simple embedding retrieval.
By Sohyeon Kim, Yoonho Lee, Bo Liu, Dayoon Ko, Rulin Shao, Seungone Kim, Graham Neubig, Pang Wei Koh, Aakanksha Chowdhery, Akari Asai, Omar Khattab, Yejin Choi, Gunhee Kim, Chelsea Finn
The paper introduces a bounded‑fidelity sim‑as‑demo‑stage design pattern that suppresses contact physics during object handoffs in simulators, using MuJoCo’s mocap‑body primitive and a lightweight Python adapter. This approach ensures audit‑chain stability, producing identical event‑log hashes across 1,000 replays per posture, whereas a contact‑force baseline yields significant divergence. The authors demonstrate that the pattern maintains reproducibility across various timesteps and sequential handoffs with minimal overhead, and they identify contexts where it should not be applied.
By Xue Qin, Simin Luan, Cong Yang, Zhijun Li