Hierarchical Experimentalist Agents

• URL: http://arxiv.org/abs/2606.29315v1
• Date: Sun, 28 Jun 2026 10:21:55 GMT
• Title: Hierarchical Experimentalist Agents
• Abstract summary: Large language models (LLMs) are increasingly used to take actions in the real world.<n>Most agents rely on parametric knowledge, fixed post-training data, retrieval, or search.<n>We introduce Hierarchical Experimentalist Agents (HExA) to learn from active experimentation.
• Score: 9.21307651025192
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large language models (LLMs) are increasingly used to take actions in the real world and support human decision-making, yet most agents rely on parametric knowledge, fixed post-training data, retrieval, or search. This paradigm breaks down in novel domains and for sophisticated queries that cannot be answered from prior knowledge alone. Knowing the laws of physics, for instance, does not by itself enable LLMs to answer queries or complete long-horizon tasks in a complex physical system. To address this, we introduce Hierarchical Experimentalist Agents (HExA), an in-context self-improvement framework to learn from active experimentation. HExA iteratively designs and refines query-relevant experiments, learns a reusable library of composable skills from experience, and integrates experimental evidence to answer queries or take actions. HExA is training-free, compatible with any black-box model, and does not require external supervision, oracles, or offline data. To evaluate active experimentation, we introduce Interphyre, a tool-calling benchmark built on the PHYRE 2D procedural physics environment, where agents propose interventions and test hypotheses through simulation APIs. Experiments show that current LLM agents struggle in these settings, especially on the hardest levels of Interphyre. Claude Sonnet 4.6 achieves only 2% success, while HExA improves the same model to up to 77% success. HExA also improves open-weight models and outperforms agentic baselines such as ReAct and Reflexion. Moreover, using only skills learned from easier levels and transferred without active experimentation, HExA achieves 44% success, demonstrating the reusability and generalization of its learned skills. Overall, HExA shows that learning through active experimentation can help agents discover useful knowledge, acquire reusable skills, and make efficient progress on novel long-horizon tasks.

Related papers

• Evo-Harness: Context-to-Harness Skill Compilation for Self-Evolving Agents [67.97365535829098]
  Learning from experience is critical for developing capable, self-improving large language model (LLM) agents.<n>We propose Evo-Harness, which distills noisy, single-shot executions into reusable skill harnesses for cross-domain and topic-level adaptation.<n>Our analysis demonstrates the effectiveness of Evo-Harness and provides a principled understanding of how LLM agents can effectively learn on the fly.
  arXiv  Detail & Related papers  (2026-08-15T06:43:56Z)
• TREX: Automating LLM Fine-tuning via Agent-Driven Tree-based Exploration [31.598039827972727]
  Large Language Models (LLMs) have empowered AI research agents to perform isolated scientific tasks.<n>In this paper, we introduce TREX, a multi-agent system that automates the entire LLM training life-cycle.
  arXiv  Detail & Related papers  (2026-04-15T17:38:06Z)
• Experiential Reflective Learning for Self-Improving LLM Agents [1.1074589887824053]
  We introduce Experiential Reflective Learning (ERL), a simple self-improvement framework that enables rapid environment adaptation.<n>ERL reflects on task trajectories and outcomes to generate actionable lessons that transfer across tasks.<n>ERL improves success rate by 7.8% over a ReAct baseline, with large gains in task completion reliability.
  arXiv  Detail & Related papers  (2026-03-25T11:43:22Z)
• ExpVid: A Benchmark for Experiment Video Understanding & Reasoning [65.17173232816818]
  We introduce ExpVid, the first benchmark designed to systematically evaluate MLLMs on scientific experiment videos.<n>We evaluate 19 leading MLLMs on ExpVid and find that while they excel at coarse-grained recognition, they struggle with disambiguating fine details, tracking state changes over time, and linking experimental procedures to scientific outcomes.<n>Our results reveal a notable performance gap between proprietary and open-source models, particularly in high-order reasoning.
  arXiv  Detail & Related papers  (2025-10-13T16:45:28Z)
• Improving LLM Agent Planning with In-Context Learning via Atomic Fact Augmentation and Lookahead Search [48.348209577994865]
  Large Language Models (LLMs) are increasingly capable but often require significant guidance or extensive interaction history to perform effectively in complex, interactive environments.<n>We introduce a novel LLM agent framework that enhances planning capabilities through in-context learning.<n>Our agent learns to extract task-critical atomic facts'' from its interaction trajectories.
  arXiv  Detail & Related papers  (2025-06-10T18:36:31Z)
• Autonomous Microscopy Experiments through Large Language Model Agents [4.241267255764773]
  Large language models (LLMs) are revolutionizing self driving laboratories (SDLs) for materials research.<n>We introduce Artificially Intelligent Lab Assistant (AILA), a framework automating atomic force microscopy through LLM driven agents.<n>We find that state of the art models struggle with basic tasks and coordination scenarios.
  arXiv  Detail & Related papers  (2024-12-18T09:35:28Z)
• ExACT: Teaching AI Agents to Explore with Reflective-MCTS and Exploratory Learning [78.42927884000673]
  ExACT is an approach to combine test-time search and self-learning to build o1-like models for agentic applications.<n>We first introduce Reflective Monte Carlo Tree Search (R-MCTS), a novel test time algorithm designed to enhance AI agents' ability to explore decision space on the fly.<n>Next, we introduce Exploratory Learning, a novel learning strategy to teach agents to search at inference time without relying on any external search algorithms.
  arXiv  Detail & Related papers  (2024-10-02T21:42:35Z)
• ExpeL: LLM Agents Are Experiential Learners [57.13685954854463]
  We introduce the Experiential Learning (ExpeL) agent to allow learning from agent experiences without requiring parametric updates.<n>Our agent autonomously gathers experiences and extracts knowledge using natural language from a collection of training tasks.<n>At inference, the agent recalls its extracted insights and past experiences to make informed decisions.
  arXiv  Detail & Related papers  (2023-08-20T03:03:34Z)
• LIBERO: Benchmarking Knowledge Transfer for Lifelong Robot Learning [64.55001982176226]
  LIBERO is a novel benchmark of lifelong learning for robot manipulation. We focus on how to efficiently transfer declarative knowledge, procedural knowledge, or the mixture of both. We develop an extendible procedural generation pipeline that can in principle generate infinitely many tasks.
  arXiv  Detail & Related papers  (2023-06-05T23:32:26Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.