Mimosa Framework: Toward Evolving Multi-Agent Systems for Scientific Research

• URL: http://arxiv.org/abs/2603.28986v1
• Date: Mon, 30 Mar 2026 20:35:57 GMT
• Title: Mimosa Framework: Toward Evolving Multi-Agent Systems for Scientific Research
• Abstract summary: Mimosa is an evolving multi-agent framework that automatically synthesizes task-specific multi-agents and iteratively refines them.<n>Released as a fully open-source platform, Mimosa aims to provide an open foundation for community-driven ASR.
• Score: 2.4251063179584436
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Current Autonomous Scientific Research (ASR) systems, despite leveraging large language models (LLMs) and agentic architectures, remain constrained by fixed workflows and toolsets that prevent adaptation to evolving tasks and environments. We introduce Mimosa, an evolving multi-agent framework that automatically synthesizes task-specific multi-agent workflows and iteratively refines them through experimental feedback. Mimosa leverages the Model Context Protocol (MCP) for dynamic tool discovery, generates workflow topologies via a meta-orchestrator, executes subtasks through code-generating agents that invoke available tools and scientific software libraries, and scores executions with an LLM-based judge whose feedback drives workflow refinement. On ScienceAgentBench, Mimosa achieves a success rate of 43.1% with DeepSeek-V3.2, surpassing both single-agent baselines and static multi-agent configurations. Our results further reveal that models respond heterogeneously to multi-agent decomposition and iterative learning, indicating that the benefits of workflow evolution depend on the capabilities of the underlying execution model. Beyond these benchmarks, Mimosa modular architecture and tool-agnostic design make it readily extensible, and its fully logged execution traces and archived workflows support auditability by preserving every analytical step for inspection and potential replication. Combined with domain-expert guidance, the framework has the potential to automate a broad range of computationally accessible scientific tasks across disciplines. Released as a fully open-source platform, Mimosa aims to provide an open foundation for community-driven ASR.

Related papers

• From Atomic Actions to Standard Operating Procedures: Iterative Tool Optimization for Self-Evolving LLM Agents [90.3279207163486]
  EvoSOP is a framework that empowers agents to extract SOPs from execution trajectories and iteratively optimize the toolset.<n>We show that EvoSOP significantly boosts task success rates while substantially reducing the number of interaction rounds.
  arXiv  Detail & Related papers  (2026-07-08T12:09:49Z)
• AgentCo-op: Retrieval-Based Synthesis of Interoperable Multi-Agent Workflows [5.357463600626556]
  AgentCo-op is a retrieval framework that composes reusable skills, tools, and external agents into executable artifacts.<n>It applies self-guided local repair to implicated components when execution indicates failure.<n>It coordinates specialized agents for spatialomics and gene-set interpretation, and builds a parallel workflow for cross-modality marker analysis on single-cell multiome data.
  arXiv  Detail & Related papers  (2026-05-19T19:22:21Z)
• 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)
• Multi-Agent Orchestration for High-Throughput Materials Screening on a Leadership-Class System [1.4669344809969722]
  Large language models (LLMs) play a critical role in autonomous decision-making.<n>We present a scalable, hierarchical multi-agent framework for orchestrating high- throughput screening campaigns.<n>Results demonstrate that the proposed agentic framework enables efficient and scalable execution on the Aurora supercomputer.
  arXiv  Detail & Related papers  (2026-04-09T01:01:11Z)
• MiroFlow: Towards High-Performance and Robust Open-Source Agent Framework for General Deep Research Tasks [95.86122998005612]
  MiroFlow is an open-source agent framework for large language models (LLMs)<n>It incorporates an agent graph for flexible orchestration, an optional deep reasoning mode to enhance performance, and a robust execution to ensure stable and reproducible performance.<n>It consistently achieves state-of-the-art performance across multiple agent benchmarks, including GAIA, BrowseComp-EN/ZH, HLE, xBench-DeepSearch, and FutureX.
  arXiv  Detail & Related papers  (2026-02-26T09:45:04Z)
• EmboCoach-Bench: Benchmarking AI Agents on Developing Embodied Robots [68.29056647487519]
  Embodied AI is fueled by high-fidelity simulation and large-scale data collection.<n>However, this scaling capability remains bottlenecked by a reliance on labor-intensive manual oversight.<n>We introduce textscEmboCoach-Bench, a benchmark evaluating the capacity of LLM agents to autonomously engineer embodied policies.
  arXiv  Detail & Related papers  (2026-01-29T11:33:49Z)
• FROAV: A Framework for RAG Observation and Agent Verification - Lowering the Barrier to LLM Agent Research [0.5729426778193398]
  We present FROAV, an open-source research platform that democratizes Large Language Models (LLMs) agent research.<n>FROAV implements a multi-stage Retrieval-Augmented Generation (RAG) pipeline and a rigorous "LLM-as-a-Judge" evaluation system.<n>Our framework integrates n8n for no-code workflow design, FastAPI for flexible backend logic, and Streamlit for human-in-the-loop interaction.
  arXiv  Detail & Related papers  (2026-01-12T13:02:32Z)
• An Agentic Framework for Autonomous Materials Computation [70.24472585135929]
  Large Language Models (LLMs) have emerged as powerful tools for accelerating scientific discovery.<n>Recent advances integrate LLMs into agentic frameworks, enabling retrieval, reasoning, and tool use for complex scientific experiments.<n>Here, we present a domain-specialized agent designed for reliable automation of first-principles materials computations.
  arXiv  Detail & Related papers  (2025-12-22T15:03:57Z)
• Code-in-the-Loop Forensics: Agentic Tool Use for Image Forgery Detection [59.04089915447622]
  ForenAgent is an interactive IFD framework that enables MLLMs to autonomously generate, execute, and refine Python-based low-level tools around the detection objective.<n>Inspired by human reasoning, we design a dynamic reasoning loop comprising global perception, local focusing, iterative probing, and holistic adjudication.<n>Experiments show that ForenAgent exhibits emergent tool-use competence and reflective reasoning on challenging IFD tasks.
  arXiv  Detail & Related papers  (2025-12-18T08:38:44Z)
• MLE-Dojo: Interactive Environments for Empowering LLM Agents in Machine Learning Engineering [57.156093929365255]
  Gym-style framework for systematically reinforcement learning, evaluating, and improving autonomous large language model (LLM) agents.<n>MLE-Dojo covers diverse, open-ended MLE tasks carefully curated to reflect realistic engineering scenarios.<n>Its fully executable environment supports comprehensive agent training via both supervised fine-tuning and reinforcement learning.
  arXiv  Detail & Related papers  (2025-05-12T17:35:43Z)
• AgentSquare: Automatic LLM Agent Search in Modular Design Space [16.659969168343082]
  Large Language Models (LLMs) have led to a rapid growth of agentic systems capable of handling a wide range of complex tasks.<n>We introduce a new research problem: Modularized LLM Agent Search (MoLAS)
  arXiv  Detail & Related papers  (2024-10-08T15:52:42Z)
• ComfyBench: Benchmarking LLM-based Agents in ComfyUI for Autonomously Designing Collaborative AI Systems [80.69865295743149]
  This work attempts to study using LLM-based agents to design collaborative AI systems autonomously.<n>Based on ComfyBench, we develop ComfyAgent, a framework that empowers agents to autonomously design collaborative AI systems by generating.<n>While ComfyAgent achieves a comparable resolve rate to o1-preview and significantly surpasses other agents on ComfyBench, ComfyAgent has resolved only 15% of creative tasks.
  arXiv  Detail & Related papers  (2024-09-02T17:44:10Z)

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.