The paper introduces checkpoint handoff, an evaluation protocol that separates an agent’s ability to reach useful states from its ability to complete tasks in reinforcement learning. By using one checkpoint as a reacher up to a handoff point and another as a solver from the same replayed history, the authors can measure Reach (how often states within a fixed number of actions from success are achieved) and Solve (how often the task is completed from those states). Experiments on TravelPlanner and ALFWorld show that switching the solver from supervised fine‑tuning to RL yields larger gains when RL is used as the reacher, indicating that RL more effectively finds solvable states.
By Xuan Liu, Jingbin Qian
FRUC is a feedforward 3D Gaussian Splatting framework that reconstructs dynamic scenes from uncalibrated collaborative driving views. It uses a visual‑grounded geometric Transformer backbone for one‑shot, calibration‑free inference and introduces an ego‑centric causal occlusion field to model occlusion evolution across agents. The method performs cross‑agent integration as a deterministic residual denoising process, achieving state‑of‑the‑art rendering quality and efficiency on V2X‑Real and UrbanIng‑V2X datasets.
By Yihang Tao, Yu Guo, Zhengru Fang, Haonan An, Yuguang Fang
The paper introduces AI Theorist, a system of AI agents that autonomously discovers physical models by generating hypotheses, performing first‑principles calculations, and refining them based on evidence. Applied to the quantum material α‑RuCl₃, the system interprets optical and photocurrent data, revealing distinct excitonic states with different optical selection rules and spatial distributions. This marks the first demonstration of an AI system autonomously developing a physical model to explain previously unpublished experimental observations in a quantum material using first‑principles and many‑body calculations.
By Hongjian Zhou, Xianfan Nie, Sean Wu, Tarun Patel, Jinge Wu, Andrew Liu, Adam Wei Tsen, David A. Clifton
The paper introduces GraphMemory, a lightweight graph-based memory system designed to improve token efficiency in test-time continual learning for large language models. By retrieving only relevant subgraphs for each query, GraphMemory keeps the amount of retrieved memory constant as more examples are processed, avoiding the token cost and performance degradation of traditional shared-context approaches. Experiments demonstrate that GraphMemory achieves competitive downstream performance while using roughly 81‑85% fewer memory‑construction tokens than baseline methods.
By Yehya Farhat, Michael Desmond, Anastasios Kyrillidis
The paper introduces Ansatz, a mathematical research agent that uses Continual Graph Memory to organize and reuse intermediate proof results across multiple problems. The system represents facts, plans, and counterexamples in a unified graph, enabling dependency-aware retrieval, evidence-sensitive curation, and scoped recall to guide long-horizon proof searches. Experiments show Ansatz solves all ten First Proof Second Batch problems, tackles the Jamison caterpillar conjecture, and makes progress on several Erdős problems without human help.
By Junyi Zhang, Jinxi Yu, Eric Hanchen Jiang, Jiachen Lu, Zhi Zhang, Xinjie He, Hyunsik Chae, Ethan Ji, Alexander K Taylor, Vigyan Sahai, Yiwen Kou, Kai-Wei Chang, Raghu Meka, Nanyun Peng, Amit Sahai, Terence Tao, Wei Wang
DyadMem introduces a new benchmark for evaluating how long‑term agents remember user‑specific relational information, called User‑conditioned Relational Agent Memory (URAM). The dataset contains 3,065 episodes, 50,961 sessions, and 61,210 QA pairs, with detailed annotations for memory capture, update, and recall across multi‑session trajectories. Experiments on 20 models show strong performance in a gold‑memory setting but a significant drop in full‑pipeline QA, highlighting gaps in current LLM memory capabilities.
By Yifei Tao, Xinyu Zhong, Henry Hengyuan Zhao, Fanyi Wang, Tengda Guo, Wentao Qiu, Ying Wang, Liujian Tang
The paper introduces ComInsight, a method for generating analytical reports from relational tables by composing verifiable atomic insights. It defines atomic insights as minimal executable analytical units, enumerates them from the database schema, and organizes them into a multi-relational insight graph. Composition operators then fuse these atomic nodes into higher-order conclusions, each accompanied by executable SQL and fine-grained provenance, achieving superior factual correctness, novelty, and structural completeness on three benchmarks.
By Teng Lin, Xinyu Liu, Nan Tang
The paper introduces the Language Model Agent Machine (LAM), a framework that quantifies the computational resources consumed by language‑model agents’ harnesses—such as bounded context, memory, tools, and verification. It presents four main theoretical results: (1) communication costs mapped to pebbling lower bounds, (2) memory‑access separations revealing a linear gap between random and non‑speculative access, (3) recomputation bounds for bit‑reversal DAGs that show when storing intermediate state is beneficial, and (4) reliability bounds that yield optimal verification intervals. Experiments on GPT‑6 Astra validate the theory’s predictions for communication, reliability, and trade‑offs in practical tasks.
By Zelin Zhao (Georgia Institute of Technology), Xinyu Guo (Georgia Institute of Technology), Jingyuan Zhang (Georgia Institute of Technology), Yuxuan Zhang (Etude AI), Yongxin Chen (Georgia Institute of Technology)
The article reviews the challenges and opportunities of detecting social bots amid the rise of advanced AI chatbots. It highlights gaps in current detection methods, especially regarding AI-generated conversations, and identifies emerging trends such as synthetic data generation, multimodal cross‑platform detection, low‑resource language support, and federated learning approaches. The authors propose these directions as promising avenues for future research.
By Emilio Ferrara
The paper introduces GAMA, a guideline-augmented multi-agent framework designed to improve biomedical named entity recognition (BioNER) using large language models (LLMs). GAMA constructs dataset-specific guideline memory by inducing and verifying annotation rules from training data, then employs a planning component to generate span-type hypotheses with rationales, a coding component to produce schema-constrained entity objects, and a verification module for structural compliance and dual-loop refinement. Experiments across five BioNER datasets demonstrate that GAMA consistently outperforms strong LLM-based baselines, with ablation studies confirming the effectiveness of each component.
By Songtao Li, Yijia Zhang, Shidi Zhang, Jianyuan Yuan, Fengyu Zhang, Hongfei Lin
EditHero is presented as the first benchmark for long-horizon, part-level 3D editing, featuring natural-language instructions and target images for both geometry and texture. The benchmark uses a deterministic assembly engine that produces the exact target after each edit, and every sequence is manually reviewed. It compares non-agentic top‑down methods with LLM/VLM agent bottom‑up approaches, finding that the latter follow instructions more closely and preserve unedited parts better, though each edit takes minutes.
By Ruihan Yu, Yu-Ju Tsai, Muyao Niu, Runyi Li, Lian Fu, Hanqing Liu, Zheng-Hui Huang, Yonghao Yu, Sho Kuno, Ming-Hsuan Yang, Kaipeng Zhang, Zhixiang Wang
SimuVerity is a new benchmark that evaluates text-to-executable Simulink model-generation tasks across ten engineering domains, using 101 tasks that include executable-system profiles and native simulation scenarios. The benchmark employs a hierarchical evaluator that first checks artifact delivery, native executability, and engineering qualification, then scores qualified models on six dimensions such as accuracy, output quality, mechanistic fidelity, control and causal integrity, operating-domain robustness, and dynamic response. In tests of six agent systems, the best achieved only a 42.86 overall score, revealing that structural similarity is a poor proxy for engineering performance and that high-scoring models can still have severe visual-layout disorder.
By Ruiqi Zhang, Jiahao Wang, Mingxuan Li, Haichen Luo, Chaoting Wang, Guoyu Mou, Keyu Lai, Hanchao Lv, Jiaxu Wang, Yibo Zheng, Aijun Yang, Xiaohua Wang
MEA is a multi‑agent framework that automates the selection and configuration of explanation tools for machine learning models across tabular, text, and vision data. A Proposer agent chooses appropriate tools based on the question and modality, while an Actor agent is trained end‑to‑end for faithfulness, producing natural‑language explanations. Experiments show that MEA outperforms existing post‑hoc explainers and closed‑source baselines, achieving significant faithfulness gains on six datasets.
By Yuyang Cheng, Raghav Kaushik Ravi, Srivarshinee Sridhar, Sriparna Saha, Akash Ghosh, Chirag Agarwal
The paper introduces a Mixture-of-Agents (MoA) approach to quantify the per-token compute required by large language models. By having a panel of fifteen models of varying sizes attempt to reproduce each token, the authors define the smallest successful agent’s inference cost as the token’s sufficient compute, providing an upper bound on necessary computation. Experiments on benchmarks show that a 0.5B model can reproduce most tokens, and that the MoA-derived compute map can reduce latency in model routing and drafting tasks while improving or maintaining accuracy.
By Zhixu Du, Weijia Han, Hai Helen Li, Yiran Chen
The paper introduces MIRA, a hierarchical architecture that separates meta-reasoning from execution for long-horizon research agents. An outer-loop meta-reasoner selects the next investigation based on a persistent research record, while an inner-loop executor carries out the chosen work order. The authors demonstrate that MIRA improves inference and compute allocation in theorem proving and neural-architecture research, and that a generative actor-critic variant (MIRA-AC) can be trained efficiently without directly optimizing long execution traces.
By Ankur Samanta, Yonathan Efroni, Paul Sajda, Kaveh Hassani, Anirudh Goyal
The study investigates how AI agents influence each other when they disagree, measuring persuasion as the change in an agent’s decision after a single exchange. Across seven open‑weight models and three language tasks, it finds that persuasion is strong—receivers often abandon their initial judgment after seeing a peer’s answer and explanation. Surprisingly, neither certainty nor model size reliably predicts persuasion dynamics; small models can persuade and resist larger ones just as effectively, and the shift depends more on the listener’s susceptibility than the speaker’s persuasiveness.
By Frida N{\o}hr Laustsen, Marie Haahr Petersen, Victoria Popa, Ariel Flint, Romualdo Pastor-Satorras, Andrea Baronchelli, Luca Maria Aiello
Inherit-MAS introduces explicit inheritance at both workflow and execution levels for multi‑agent systems built from large language models. A meta‑model generates a workflow of specialized agents, while a judge evaluates each candidate and diagnoses deficiencies. During refinement, workflow inheritance discards unhelpful nodes and applies validated edits, and execution inheritance reuses stored results only when the request and context match, reducing redundant computation.
By Songtao Wei, Yi Li, Zhichun Guo, Bingzhe Li
Pincer is a defense mechanism for coding agents that operates at the resource layer, complementing existing tool‑call defenses. It uses a digital twin—an isolated‑context model that learns and enforces dynamic, user‑specific least‑privilege policies—to act as a proxy for the agent’s permission requests. The authors introduce a user‑centric dataset to emulate the learning phase and demonstrate that Pincer outperforms several baselines in both security and utility, especially against adversarial attack types.
By Mayank Rathee, Alexander Stepanov, Shalin Madabhavi, Jinhao Zhu, Raluca Ada Popa, Ion Stoica
Dynamic Expert Pruning for Multi-Agent Systems introduces DEP, a method that generates a per-request mask of experts based on an agent’s system and task prompts. Unlike static pruning, DEP uses a lightweight predictor trained on workflow transcripts to activate only the experts needed for each specific request, requiring no per-configuration calibration. Experiments across various tasks, models, and MoE architectures show DEP outperforms static pruning and merging baselines, especially when few experts are retained, and it generalizes to unseen workflows.
By Jabin Koo, Soheil Abbasloo, Sungjae Lee, Jungseul Ok
Sentry is a failure‑management layer for large language model agents that learns from failures at test time. It retrieves relevant lessons from an external playbook when a failure occurs, verifies recovery without task rewards, and stores new lessons only if recovery succeeds, keeping the playbook out of the agent’s context. Across multiple benchmarks, Sentry outperforms both runtime‑intervention and context‑evolution baselines, and its lessons transfer to unseen tasks.
By Changxiu Ji, Amy Lu, Qizheng Zhang, Kunle Olukotun