arXiv：cs.AI· Abhranil Chandra, Utsav Dhanuka, Varun Gandhi, Sankaran Vaidyanathan, Scott Niekum·· 13 小时前
HExA：面向 LLM 的层级式实验型智能体框架
Hierarchical Experimentalist Agents
AI 导读
研究者提出 Hierarchical Experimentalist Agents（HExA），一个以实验为中心的上下文自改进框架，可迭代设计实验、将经验蒸馏为可复用技能并整合证据作答，适配包括前沿黑盒模型在内的任意 LLM，无需外部监督、oracle 解或离线数据。
正文
Abstract:Large language models (LLMs) are increasingly used to act in the real world and augment human decision-making, yet most systems rely on parametric knowledge acquired through imitation, optionally improved by post-training, retrieval, or search over fixed data. This paradigm struggles in novel domains or on complex queries that require information unavailable from prior knowledge alone; knowing the laws of physics, for example, does not by itself enable reliable reasoning or long-horizon actions in a complex physical system. We argue that agents need active experimentation: the ability to gather targeted query-specific evidence, discover general principles of unseen environments, and convert interaction experience into reusable skills. We introduce Hierarchical Experimentalist Agents (HExA), an in-context, experiment-centric self-improvement framework that (1) iteratively designs and refines query-relevant experiments, (2) incrementally distills experience into reusable and composable skills that accelerate experimentation within and across tasks, and (3) integrates experimental evidence to act or answer queries. HExA can work with any LLM including frontier black-box models, and requires no external supervision, oracle solutions, or offline data. We evaluate HExA on multi-step reasoning, interactive partially observable games, and physics law discovery tasks. To further evaluate when active experimentation is necessary, we introduce Interphyre, a set of hard procedural physics tasks where we enable tool-calling and intervention APIs. Current frontier LLMs including GPT-6 Astra fail in these settings: on the most challenging Interphyre tasks, we show that HExA can enable such models to near 100% success. Moreover, HExA improves token efficiency compared to naive agentic and memory baselines and enables generalization via hierarchical skill transfer from easier to harder tasks.
| Subjects: | Artificial Intelligence (cs.AI); Machine Learning (cs.LG) |
| Cite as: | arXiv:2606.29315 [cs.AI] |
| (or arXiv:2606.29315v2 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2606.29315 arXiv-issued DOI via DataCite |
Submission history
From: Abhranil Chandra [view email]
[v1]
Sun, 28 Jun 2026 10:21:55 UTC (6,992 KB)
[v2]
Fri, 9 Oct 2026 05:17:07 UTC (7,508 KB)
来源：arXiv：cs.AI · arxiv.org