EurekAgent: Agent Environment Engineering is All You Need For Autonomous Scientific Discovery

• URL: http://arxiv.org/abs/2606.13662v2
• Date: Fri, 12 Jun 2026 02:37:51 GMT
• Title: EurekAgent: Agent Environment Engineering is All You Need For Autonomous Scientific Discovery
• Abstract summary: We present EurekAgent, an environment-engineered agent system for metric-driven autonomous scientific discovery.<n>We frame this as environment engineering: building environments that amplify productive behaviors, while suppressing harmful behaviors, such as reward hacking and high-friction human oversight.<n>We open-source our code and results, and call for environment engineering as a core research direction for developing reliable autonomous research agents.
• Score: 51.466674519159824
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: LLM-based agents have shown increasing potential in automating scientific discovery. Given an optimizable metric and an execution environment, they can propose, validate, and iterate scientific solutions, and have produced results that outperform human-designed approaches. As model capabilities continue to improve, we argue that the bottleneck for autonomous scientific discovery is shifting from prescribing agent workflows to designing agent environments: the resources, constraints, and interfaces that shape agent behavior. We frame this as environment engineering: building environments that amplify productive behaviors, such as open-ended exploration, systematic artifact management, and inter-agent collaboration, while suppressing harmful behaviors, such as reward hacking and high-friction human oversight. We present EurekAgent, an environment-engineered agent system for metric-driven autonomous scientific discovery. EurekAgent engineers the environment along four dimensions: permissions engineering for bounded agent execution and isolated evaluation; artifact engineering for filesystem and Git-based collaboration; budget engineering for budget-aware exploration; and human-in-the-loop engineering for easy human supervision and intervention. EurekAgent sets new state-of-the-art results on multiple mathematics, kernel engineering, and machine learning tasks, including new state-of-the-art 26-circle packing results discovered with less than $11 in total API cost. We open-source our code and results, and call for environment engineering as a core research direction for developing reliable autonomous research agents.

Related papers

• El Agente Forjador: Task-Driven Agent Generation for Quantum Simulation [7.535793342235731]
  El Agente Forjador is a multi-agent framework in which universal coding agents autonomously forge, validate, and reuse tools.<n>We show that our tool generation and reuse framework consistently improves accuracy over the baseline.
  arXiv  Detail & Related papers  (2026-04-16T04:28:56Z)
• Agent World Model: Infinity Synthetic Environments for Agentic Reinforcement Learning [62.499592503950026]
  Large language model (LLM) have empowered autonomous agents to perform complex tasks that require multi-turn interactions with tools and environments.<n>We propose Agent World Model (AWM), a fully synthetic environment generation pipeline.<n>We scale to 1,000 environments covering everyday scenarios, in which agents can interact with rich toolsets.
  arXiv  Detail & Related papers  (2026-02-10T18:55:41Z)
• Bohrium + SciMaster: Building the Infrastructure and Ecosystem for Agentic Science at Scale [82.20980951765891]
  We argue that scaling agentic science requires an infrastructure-and-ecosystem approach, instantiated Bohrium+SciMaster.<n>Bohrium acts as a managed, traceable hub for AI4S assets that turns diverse scientific data, software, compute, and laboratory systems into agent-ready capabilities.<n>SciMaster orchestrates these capabilities into long-horizon scientific, on which scientific agents can be composed and executed.
  arXiv  Detail & Related papers  (2025-12-23T16:04:41Z)
• Simple Agents Outperform Experts in Biomedical Imaging Workflow Optimization [69.36509281190662]
  Adapting production-level computer vision tools to bespoke scientific datasets is a critical "last mile" bottleneck.<n>We consider using AI agents to automate this manual coding, and focus on the open question of optimal agent design.<n>We demonstrate that a simple agent framework consistently generates adaptation code that outperforms human-expert solutions.
  arXiv  Detail & Related papers  (2025-12-02T18:42:26Z)
• ScienceBoard: Evaluating Multimodal Autonomous Agents in Realistic Scientific Workflows [82.07367406991678]
  Large Language Models (LLMs) have extended their impact beyond Natural Language Processing.<n>Among these, computer-using agents are capable of interacting with operating systems as humans do.<n>We introduce ScienceBoard, which encompasses a realistic, multi-domain environment featuring dynamic and visually rich scientific software.
  arXiv  Detail & Related papers  (2025-05-26T12:27:27Z)
• SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering [79.07755560048388]
  SWE-agent is a system that facilitates LM agents to autonomously use computers to solve software engineering tasks. SWE-agent's custom agent-computer interface (ACI) significantly enhances an agent's ability to create and edit code files, navigate entire repositories, and execute tests and other programs. We evaluate SWE-agent on SWE-bench and HumanEvalFix, achieving state-of-the-art performance on both with a pass@1 rate of 12.5% and 87.7%, respectively.
  arXiv  Detail & Related papers  (2024-05-06T17:41:33Z)
• Multi-Agent Simulation for AI Behaviour Discovery in Operations Research [0.9137554315375919]
  ACE0 is a platform for evaluating the suitability and viability of AI methods for behaviour discovery in multiagent simulations. We provide a technical overview of the system architecture, describe a case study of behaviour discovery in the aerospace domain, and provide a qualitative evaluation of the system.
  arXiv  Detail & Related papers  (2021-08-30T15:14:06Z)

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.