跳到正文
HuggingFace Daily Papers(社區熱門論文)·· 2026-10-19AI 評分47

AdaExploreBench:評測 LLM 智能體在演變環境中的主動探索與測試時適應能力

AdaExploreBench: Benchmarking LLM Agents for Proactive Exploration and Test-time Adaptation in Evolving Environments

AI 導讀

AdaExploreBench 評測 LLM 智能體在演變環境中主動探索隱藏規則及適應未預告變化的能力,發現現有智能體難以搜尋相關證據和識別過時知識。測試八款領先 LLM 時,GPT-6 Sol 的校準準確率為 61.9%;提供足夠證據或移除規則漂移,均可令平均表現顯著提升近 10%。

正文

Published on Oct 19

·

Submitted by

Jeff

on Oct 20

Authors:

,

,

,

,

,

,

,

,

,

,

,

,

,

,

,

,

Abstract

AdaExploreBench evaluates whether LLM agents can actively discover hidden environmental rules and adapt to unannounced changes, revealing that current models struggle to seek relevant evidence and detect stale knowledge.

Large Language Model (LLM) agents are increasingly deployed in unfamiliar and evolving environments, requiring them to proactively explore, understand, and adapt to environmental dynamics. However, existing benchmarks rarely test whether agents can proactively discover how an environment works and adapt as it evolves. To address this gap, we introduce AdaExploreBench, a benchmark for proactive exploration and test-time adaptation in evolving environments. By instantiating environmental dynamics as hidden rules, AdaExploreBench requires agents to actively acquire evidence and infer the rules. Under implicit rule drift, the latent rule changes without announcement, requiring agents to detect from degraded performance that prior knowledge is stale and re-explore. Experiments on eight leading LLMs show that proactive and adaptive exploration remain challenging: GPT-6 Sol achieves only 61.9% calibrated accuracy, while providing sufficient evidence or removing rule drift improves average performance significantly by close to 10%. These results reveal a critical bottleneck in current LLM agents: they can often reason effectively from informative evidence once it is available, but struggle to actively acquire the right evidence and recognize when previously acquired evidence is no longer valid.

View arXiv page View PDF Project page GitHub Add to collection

Get this paper in your agent:

hf papers read 2610.25950

Don't have the latest CLI?

curl -LsSf https://hf.co/cli/install.sh | bash

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2610.25950 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2610.25950 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2610.25950 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.

來源:HuggingFace Daily Papers(社區熱門論文) · huggingface.co