← Back to all news
arXiv AI By Jiakai Xu, Tiancheng Ge, Tujie Guan, Yusheng Li, Rohan Timmaraju, Eugene Wu, Kostis Kaffes

Probe-and-Resume: When and How to Evaluate Agent Execution

Read the original on arXiv AI →

The paper investigates the use of test‑time search, specifically Monte Carlo tree search (MCTS), to improve agent performance in terminal‑based computer‑use environments. It finds that conventional MCTS does not significantly boost task success due to limited critic information and poor intermediate state evaluation. The authors propose a new strategy called Probe‑and‑Resume, where a critic is invoked only when the agent believes it has finished, and it is given read, write, and execute access to a forked copy of the environment to probe hidden state. This approach raises success rates by 8.4 percentage points over standard MCTS and nearly matches a more expensive Codex CLI agent.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

Related stories

arXiv AI
5d ago

Long-Horizon-Terminal-Bench 2.0: Automating Diverse Task Construction and Measuring Sustained Agent Progress

arXiv:2610.14146v1 Announce Type: new Abstract: Long-horizon terminal benchmarks measure whether an agent can sustain progress through extended workflows with process rewards, not only whether its fi...

By Zongxia Li, Zhongzhi Li, Yucheng Shi, Ruhan Wang, Junyao Yang, Chengsong Huang, Zhichao Liu, Xiyang Wu, Anhao Li, Yue Yu, Ergan Shang, Fuxiao Liu, Tong Zheng, Ninghao Liu, Lichao Sun, Haitao Mi, Leowei Liang
llmsagentsbenchmarks
More like this →
arXiv AI
Sep 12

Grounding Agent Memory: Environment-Probing Curation for Enterprise Agents

The paper introduces environment‑probing curation, a deployment‑compatible method that equips asynchronous curator agents with read‑only world tools to verify, scope, and refresh candidate memories without retraining models. In a GitHub Copilot‑based harness, this approach improves pass rates on CLBench from 39% to 73%, boosts reward metrics, and reduces both query counts and task‑agent costs. Across six APEX management‑consulting tasks, the method consistently outperforms baselines, yielding higher rewards and fewer tool calls while maintaining a compact task‑time interface.

By Susheel Suresh, Hazel Mak, Sahil Bhatnagar, Chhaya Methani, Alejandro Gutierrez Munoz
llmsagents
More like this →
arXiv Computation and Language
Oct 9

Opera: A Verbal Critic Framework for Long-horizon Coding Agents

Opera is a verbal critic framework designed for long‑horizon coding agents, treating each correction as a persistent note that is followed until the problem is resolved. It uses periodic and event‑driven triggers to diagnose issues, audits feedback against visible evidence, and tracks subsequent actions to distinguish compliance from true resolution. In tests, Opera improves the resolve rate of non‑critic agents by up to 12.4, 15.0, and 8.9 percentage points on three benchmarks and provides on‑policy training data that boosts a model’s performance without requiring a critic at inference time.

By Kai Mei, Zhiyuan Hu, Yutong Dai, Juntao Tan, Yifan Zhang, Dingjie Song, Dimitris N. Metaxas, Silvio Savarese, Ran Xu, Zeyuan Chen
agentsfine-tuningbenchmarks
More like this →