KC-Bench is a dynamic interactive benchmark designed to evaluate how large language model agents reconcile user instructions, internal knowledge, and real‑time environmental observations. It consists of 238 manually curated multi‑turn tasks that test world‑knowledge conflicts, input inconsistencies, and multi‑source temporal conflicts, using a user simulator, stateful tools, deterministic environment assertions, an open‑source natural‑language evaluator, and human trajectory verification. Evaluation of nine models—including DeepSeek‑V4‑Flash, GLM‑5.2, and MiniMax‑M3—reveals significant cross‑domain variation, with no model reliably handling factual correction, identity consistency, and temporal conflict resolution across all settings, and shows that missed conflicts can propagate to tool calls or synthetic protected‑data flows.
arXiv:2607. 10059v1 Announce Type: new Abstract: Agent systems based on large language models (LLMs) are increasingly deployed for autonomous tasks, yet existing evaluations mostly focus on task success rather than whether agents know when to abstain.
By Xun Liu, Yi Evie Zhang, Vira Kasprova, Parisa Rabbani, Pardis Sadat Zahraei, Tianyu Zhang, Ali Ebrahimpour-Boroojeny, Varun Chandrasekaran
The paper introduces RUPA, a trajectory‑level uncertainty quantification framework for large language model agents. RUPA models an agent’s execution as a directed graph of reasoning states, tool interactions, and environment feedback, then propagates uncertainty across this graph to capture long‑range dependencies. Experiments on benchmarks such as τ‑2, Terminal‑Bench‑2, and GAIA show that RUPA outperforms existing methods, enabling earlier failure detection and more reliable agent execution.
By Zhengzhao Ma. Boxi Cao, Yaojie Lu, Hongyu Lin, Xianpei Han, Le Sun
The paper introduces DoublesEval, a diagnostic framework that uses professional doubles badminton to test visual‑language models’ ability to reason about dynamic multi‑agent interactions. It decomposes rallies into key moments and evaluates models across four dimensions—atomic recognition, intra‑segment composite understanding, cross‑segment causal reasoning, and high‑level tactical abstraction—highlighting specific reasoning failures. The authors also propose TacticCheck, a lightweight consistency checker that improves performance without retraining the models, yet significant gaps remain in tactical reasoning.
By Jintao Cheng, Weibin Li
Visual Language Models (VLMs) excel at describing visible scene content but struggle to reason about dynamic multi-agent interactions, where action semantics depend on coordinated roles and spatial-te...
arXiv:2604. 02478v2 Announce Type: replace Abstract: Deep learning models excel at detecting anomaly patterns in normal data.
By Jiyong Kwon, Ujin Jeon, Sooji Lee, Guang Lin
Large language model (LLM) agents increasingly operate over long-horizon interactions involving tool use, persistent state, evolving authorization, and external environment feedback. In such settings,...
The paper introduces the Agent-Editing World Model (AEWM), a new approach that models how reasoning and actions influence future task progress instead of simulating tool responses. AEWM includes an Action Judge that classifies decisions as Critical, Exploratory, or Noisy, and a State Revision mechanism that edits noisy reasoning–action continuations from the same observed history. The integrated system, EditAct, directly updates the underlying state during real execution, leading to significant performance gains across multiple benchmarks and agent backbones.
By Shuang Sun, Guoxin Chen, Fanzhe Meng, Jia Deng, Huatong Song, Jinhao Jiang, Wayne Xin Zhao, Hongteng Xu, Ji-Rong Wen
arXiv:2603. 00829v2 Announce Type: replace-cross Abstract: Safe deployment of Large Language Model (LLM) agents in autonomous settings requires reliable oversight mechanisms.
By Simon Storf, Rich Barton-Cooper, James Peters-Gill, Marius Hobbhahn
CivBench is an open‑source benchmark that evaluates language‑model agents in the long‑horizon, tool‑mediated game Civilization VI using the Model Context Protocol (MCP). Each episode lasts over 300 turns, generating thousands of tool calls across a 76‑tool action space, and includes a narration layer that translates visual game state into structured text. The study characterises agent behaviour across four model families, introducing Proactive Monitoring Rate (PMR) and RAG@10 as interface‑level metrics, and finds that agents often under‑monitor strategic state and fail to execute near‑term commitments despite tool access and explicit guidance.
By Austin Tudor David Andrews, Liam Wilkinson, Jamie Heagerty, Harry Coppock, Jakob Nicolaus Foerster, Rui Ponte Costa
arXiv:2606. 16307v1 Announce Type: new Abstract: Training tool-augmented LLM agents requires large corpora of multi-turn, tool-grounded conversational data that is expensive to annotate, privacy-constrained in production settings, and largely absent from public datasets.
By Rahul Khedar, Eshita, Sneha Teja Sree Reddy Thondapu, Mayank Malhotra, Arup Das, Jitesh Chandra, Yun-Shiuan Chuang, Chaitanya Kulkarni, Arun Menon, Linsey Pang, Avinash Karn, Mouli V, Prakhar Mehrotra
arXiv:2605. 27898v2 Announce Type: replace Abstract: As LLMs are increasingly deployed as agents, reliable assessment of their agentic capabilities has become essential.
By Pengyu Zhu, Lijun Li, Yaxing Lyu, Qianxin Luo, Jingyi Yang, Yi Liu, Tingfeng Hui, Xinyu Yuan, Li Sun, Sen Su, Jing Shao