Accelerating Scientific Discovery with Autonomous Goal-evolving Agents

• URL: http://arxiv.org/abs/2512.21782v1
• Date: Thu, 25 Dec 2025 20:54:41 GMT
• Title: Accelerating Scientific Discovery with Autonomous Goal-evolving Agents
• Abstract summary: We introduce the Scientific Autonomous Goal-evolving Agent (SAGA) to amend this challenge.<n>SAGA employs a bi-level architecture in which an outer loop of LLM agents analyzes optimization outcomes, proposes new objectives, and converts them into computable scoring functions.<n>We demonstrate the framework through a broad spectrum of applications, including antibiotic design, inorganic materials design, functional DNA sequence design, and chemical process design.
• Score: 51.6546298853762
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: There has been unprecedented interest in developing agents that expand the boundary of scientific discovery, primarily by optimizing quantitative objective functions specified by scientists. However, for grand challenges in science , these objectives are only imperfect proxies. We argue that automating objective function design is a central, yet unmet requirement for scientific discovery agents. In this work, we introduce the Scientific Autonomous Goal-evolving Agent (SAGA) to amend this challenge. SAGA employs a bi-level architecture in which an outer loop of LLM agents analyzes optimization outcomes, proposes new objectives, and converts them into computable scoring functions, while an inner loop performs solution optimization under the current objectives. This bi-level design enables systematic exploration of the space of objectives and their trade-offs, rather than treating them as fixed inputs. We demonstrate the framework through a broad spectrum of applications, including antibiotic design, inorganic materials design, functional DNA sequence design, and chemical process design, showing that automating objective formulation can substantially improve the effectiveness of scientific discovery agents.

Related papers

• Rethinking Scientific Discovery in the Agentic Era [69.85050591628048]
  SCION is an agentic scientific operating system that acts as an textbf organizational nexus.<n>At its core is the textbfResearch Execution Plan (REP), which compiles high-level scientific intent into staged objectives, dependencies, verification checkpoints, tool requirements, expected artifacts, and fallback conditions.<n>We formulate discovery under SCION as textbfTarget-conditioned Inverse Search and extend it to hidden-target settings through batch active search under finite experimental budgets.
  arXiv  Detail & Related papers  (2026-07-04T13:09:33Z)
• AI Scientists as Engines of Discovery: A Case for Development within Reformed Institutions [0.10102237605686408]
  Agentic artificial intelligence (AI) systems are beginning to assist, accelerate, and partially automate scientific discovery.<n>We argue that suitably designed multi-agent systems may evolve from passive computational tools into AI scientists''<n>Such systems must be developed and deployed within a scientific ecosystem fit for purpose.
  arXiv  Detail & Related papers  (2026-06-22T05:06:29Z)
• Beyond AI as Assistants: Toward Autonomous Discovery in Cosmology [0.02455468619225742]
  Recent advances in artificial intelligence (AI) agents are pushing AI beyond tools toward autonomous scientific discovery.<n>We discuss two complementary agentic systems for cosmology: textttCMBEvolve and textttCosmoEvolve<n>We show how cosmology can provide both controlled benchmark tasks and realistic open-ended research problems for the development of AI scientist systems.
  arXiv  Detail & Related papers  (2026-05-14T12:58:12Z)
• SciResearcher: Scaling Deep Research Agents for Frontier Scientific Reasoning [54.194672921128785]
  We introduce SciResearcher, a fully automated agentic framework for frontier-science data construction.<n>SciResearcher synthesizes diverse conceptual and computational tasks grounded in academic evidence.<n>We develop SciResearcher-8B, an agent foundation model that achieves 19.46% on the HLE-Bio/Chem-Gold benchmark.
  arXiv  Detail & Related papers  (2026-05-02T15:26:45Z)
• S1-NexusAgent: a Self-Evolving Agent Framework for Multidisciplinary Scientific Research [0.0]
  We propose S1-NexusAgent, a self-evolving agent framework for scientific research.<n>S1-NexusAgent adopts a hierarchical Plan-and-CodeAct execution paradigm, decoupling global scientific planning from subtask-level tool execution.<n>S1-NexusAgent achieves state-of-the-art generalization performance, validating its effectiveness and capability in complex scientific tasks.
  arXiv  Detail & Related papers  (2026-02-02T02:33:25Z)
• Towards Agentic Intelligence for Materials Science [73.4576385477731]
  This survey advances a unique pipeline-centric view that spans from corpus curation and pretraining to goal-conditioned agents interfacing with simulation and experimental platforms.<n>To bridge communities and establish a shared frame of reference, we first present an integrated lens that aligns terminology, evaluation, and workflow stages across AI and materials science.
  arXiv  Detail & Related papers  (2026-01-29T23:48:43Z)
• 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)
• AutoLabs: Cognitive Multi-Agent Systems with Self-Correction for Autonomous Chemical Experimentation [0.10999592665107412]
  AutoLabs is a self-correcting, multi-agent architecture designed to autonomously translate natural-language instructions into executable protocols.<n>We present a comprehensive evaluation framework featuring five benchmark experiments of increasing complexity.<n>Our results demonstrate that agent reasoning capacity is the most critical factor for success.
  arXiv  Detail & Related papers  (2025-09-30T01:51:46Z)
• DrugPilot: LLM-based Parameterized Reasoning Agent for Drug Discovery [54.79763887844838]
  Large language models (LLMs) integrated with autonomous agents hold significant potential for advancing scientific discovery through automated reasoning and task execution.<n>We introduce DrugPilot, a LLM-based agent system with a parameterized reasoning architecture designed for end-to-end scientific in drug discovery.<n>DrugPilot significantly outperforms state-of-the-art agents such as ReAct and LoT, achieving task completion rates of 98.0%, 93.5%, and 64.0% for simple, multi-tool, and multi-turn scenarios, respectively.
  arXiv  Detail & Related papers  (2025-05-20T05:18:15Z)
• Offline Model-Based Optimization: Comprehensive Review [61.91350077539443]
  offline optimization is a fundamental challenge in science and engineering, where the goal is to optimize black-box functions using only offline datasets.<n>Recent advances in model-based optimization have harnessed the generalization capabilities of deep neural networks to develop offline-specific surrogate and generative models.<n>Despite its growing impact in accelerating scientific discovery, the field lacks a comprehensive review.
  arXiv  Detail & Related papers  (2025-03-21T16:35:02Z)
• 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)
• Gödel Agent: A Self-Referential Agent Framework for Recursive Self-Improvement [112.04307762405669]
  G"odel Agent is a self-evolving framework inspired by the G"odel machine.<n>G"odel Agent can achieve continuous self-improvement, surpassing manually crafted agents in performance, efficiency, and generalizability.
  arXiv  Detail & Related papers  (2024-10-06T10:49:40Z)
• Efficient Evolutionary Search Over Chemical Space with Large Language Models [31.31899988523534]
  optimization objectives can be non-differentiable.<n>We introduce chemistry-aware Large Language Models (LLMs) into evolutionary algorithms.<n>Our algorithm improves both the quality of the final solution and convergence speed.
  arXiv  Detail & Related papers  (2024-06-23T06:22:49Z)

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.