Mimosa Framework: Toward Evolving Multi-Agent Systems for Scientific Research
arXiv:2603.28986v1 Announce Type: new 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 refineme
View PDF HTML (experimental)
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.
Comments: 48 pages, 4 figures, 1 table. Clean arXiv version prepared. Includes main manuscript plus appendix/supplementary-style implementation details and prompt listings. Dated 30 March 2026
Subjects:
Artificial Intelligence (cs.AI); Machine Learning (cs.LG); Multiagent Systems (cs.MA)
MSC classes: 68T01, 93A16
ACM classes: I.2.11; I.2.6; I.2.8
Cite as: arXiv:2603.28986 [cs.AI]
(or arXiv:2603.28986v1 [cs.AI] for this version)
https://doi.org/10.48550/arXiv.2603.28986
arXiv-issued DOI via DataCite (pending registration)
Submission history
From: Louis-Felix Nothias [view email] [v1] Mon, 30 Mar 2026 20:35:57 UTC (1,548 KB)
Sign in to highlight and annotate this article
Conversation starters
Daily AI Digest
Get the top 5 AI stories delivered to your inbox every morning.
More about
modellanguage modelbenchmark
State of Evaluation Study: Vector Institute Unlocks New Transparency in Benchmarking Global AI Models
Five takeaways for AI model developers, researchers and users Vector Institute’s first State of Evaluation study, developed by Vector’s AI Engineering team, shines new light on the evaluation and benchmarking [ ] The post State of Evaluation Study: Vector Institute Unlocks New Transparency in Benchmarking Global AI Models appeared first on Vector Institute for Artificial Intelligence .
Vector Institute Unveils Comprehensive Evaluation of Leading AI Models
At a glance: TORONTO, ON, April 10, 2025 — Canada’s Vector Institute has unveiled the results of its independent evaluation of leading large language models (LLMs), offering an objective look [ ] The post Vector Institute Unveils Comprehensive Evaluation of Leading AI Models appeared first on Vector Institute for Artificial Intelligence .
Vector Institute Announces the Appointment of Glenda Crisp as President and CEO
TORONTO, April 15, 2025 (GLOBE NEWSWIRE) The Board of Directors of the Vector Institute is pleased to announce the appointment of Glenda Crisp as President CEO effective April [ ] The post Vector Institute Announces the Appointment of Glenda Crisp as President and CEO appeared first on Vector Institute for Artificial Intelligence .
Knowledge Map
Connected Articles — Knowledge Graph
This article is connected to other articles through shared AI topics and tags.
More in Models
State of Evaluation Study: Vector Institute Unlocks New Transparency in Benchmarking Global AI Models
Five takeaways for AI model developers, researchers and users Vector Institute’s first State of Evaluation study, developed by Vector’s AI Engineering team, shines new light on the evaluation and benchmarking [ ] The post State of Evaluation Study: Vector Institute Unlocks New Transparency in Benchmarking Global AI Models appeared first on Vector Institute for Artificial Intelligence .
Vector Institute Unveils Comprehensive Evaluation of Leading AI Models
At a glance: TORONTO, ON, April 10, 2025 — Canada’s Vector Institute has unveiled the results of its independent evaluation of leading large language models (LLMs), offering an objective look [ ] The post Vector Institute Unveils Comprehensive Evaluation of Leading AI Models appeared first on Vector Institute for Artificial Intelligence .
Exploring Intelligence: Vector Faculty Member Kelsey Allen’s Path from Particle Physics to Cognitive Machine Learning
How do humans and machines build models to enable problem-solving and innovation? This is the question that has shaped Kelsey Allen’s career. It’s guided her from high-energy physics to machine [ ] The post Exploring Intelligence: Vector Faculty Member Kelsey Allen’s Path from Particle Physics to Cognitive Machine Learning appeared first on Vector Institute for Artificial Intelligence .
Discussion
Sign in to join the discussion
No comments yet — be the first to share your thoughts!