The paper introduces the evidence-action gap, where coding agents persist in tasks even when completion is impossible, despite having sufficient evidence that outside help is needed. To quantify this, the authors present ImpasseBench, a benchmark that injects realistic blockers into repair tasks and marks the step at which evidence becomes sufficient. Across eight models and 19,371 trajectories, they find that many agents still exhaust their budget or make unsafe requests after the evidence threshold, but an escalation tool and external monitor can significantly reduce these failures.
By Tianyu Chen, Xinran Zhao, Vijay Viswanathan, Shoubin Yu, Mingyuan Zhou, Tongshuang Wu
arXiv:2607. 27283v1 Announce Type: new Abstract: Long-horizon benchmarks often show that agents fail more as tasks become longer.
By Chao Peng, Zhiheng Lyu, Peijie Dong, Hande Dong, Qiang Lin
arXiv:2610.27777v1 Announce Type: new
Abstract: Tool-using LLM agents increasingly answer e-commerce queries through multi-step tool interactions. The expected output of a tool call can shift between...
By Wenshuo Zhang, Yuquan Lin, Yushi Sun, Yishi Lin, Rui Sheng, Peng He, Han Gao, Wang Jikai, Yifeng Rong
arXiv:2607. 12385v1 Announce Type: new Abstract: A significant challenge in agentic AI is prospective memory: the ability to execute an intention at a specific future cue or state while other activities are ongoing.
By Genglin Liu, Saadia Gabriel
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
arXiv:2610.16117v2 Announce Type: new
Abstract: LLM-based multi-agent collaboration is increasingly used to solve complex tasks by dividing work among specialized agents and integrating complementary...
By Chen Huang, Yiyang Zhang, Yuhao Wu, Yang Deng, Wenxuan Zhang
Agent-Controlled Forgetting for Tool-Using Agents: Reversible Context Curation in Practice explores a method where an agent selectively replaces detailed tool results with concise notes while archiving the originals for recovery. Using a Python harness, the approach reduces prompt tokens from 912,492 to 231,951 and cuts cumulative input tokens by 50%, yielding significant API cost savings. However, the method increases request count, slightly slows execution, and its effectiveness varies across different workloads.
By Jan-Peter Franke
arXiv:2610.18614v1 Announce Type: new
Abstract: Controlling an acting LLM agent means deciding, at each step of a long-horizon task, whether to trust its next action, abstain, or hand off to a human....
By Ashutosh Hathidara
The paper evaluates the planning abilities of large language model (LLM) agents by comparing their performance against formal semantics defined in hidden PDDL models. Across five domains, four LLMs, six prompting strategies, and three agent architectures, the best setup solved 78% of solvable tasks offline but only 40% online, with limited recognition of unsolvable tasks and no clear benefit from more elaborate prompting. The study concludes that claims of LLM planning competence require validated action traces rather than end‑to‑end success rates.
By Oriol Miro-Lopez-Feliu, Oscar Mir\'o L\'opez-Feliu, Victor Gimenez-Abalos, Javier Vazquez-Salceda, Victor Carballo Araruna, Sergio Alvarez-Napagao
arXiv:2606. 14574v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly deployed as planners for autonomous agents in household environments.
By Xiaoxin Lu, Ranran Haoran Zhang, Rui Zhang
arXiv:2606. 01365v1 Announce Type: new Abstract: Tool-using multi-agent large language model (LLM) systems spend computation through model tokens, tool calls, retries, and code execution before producing an answer.
By Xianyou Li, Weiran Yan, Yichao Wu, Penghao Liang, Mengwei Yuan, Jianan Liu, Jing Yang
Large language model (LLM) agents are increasingly deployed as personal assistants. Existing evaluations, however, mostly use short, self-contained requests in static environments.