AI Paper Atlas

Research map / Multi-agent systems and games / LLM agents

EvoMAS: Heuristics in the Loop—Evolving Smarter Agentic Workflows

Yangbo Wei, Zhen Huang, Ronghao Xu, Hong Wang, WEI W. XING

ICML 2026 · Multi-agent systems and games › LLM agents · approach: Robust and efficient agent execution

Read the paperCheck your idea against 137,217 papers

AI-extracted summary. Written by AI from the paper's full text. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Proposes EvoMAS, an evolutionary framework that automatically constructs and optimizes multi-agent system workflows using a diverse repertoire of heuristics, aiming for efficiency across task complexity levels.

Problem

Constructing efficient multi-agent systems requires labor-intensive manual design, and existing automated methods generate templated agents, use monolithic optimization, and ignore task complexity gradients.

Approach

A biologically-inspired evolutionary framework maintaining a dynamic, diverse repertoire of seven (heuristic-based) components evolved within the loop to produce agentic workflows adapted to task complexity, rather than templated agents or monolithic optimization.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add exploration strategies (ablation)EvoMAS · MATHaccuracy (%): 48.10 -> 60.33Improved
add exploitation strategies (ablation)EvoMAS · MBPPPass@1 (%): 72.14 -> 86.21Improved
add the Cyber Creator meta-controller (ablation)EvoMAS · MATHaccuracy (%): 56.00 -> 60.33Improved
add the Cyber Creator meta-controller (ablation)EvoMAS · MATHcost ($): 3.12 -> 2.54Improved
add curriculum-guided evolution (ablation)EvoMAS · MBPPPass@1 (%): 83.57 -> 86.21Improved
add curriculum-guided evolution (ablation)EvoMAS · MATHaccuracy (%): 57.80 -> 60.33Improved
add evolution resource library (ablation)EvoMAS · MBPPPass@1 (%): 76.90 -> 86.21Improved
replace optimizer LLM with Qwen-4B (ablation)EvoMAS · MBPPPass@1 (%): 86.2 -> 74.7Hurt
replace Judge LLM with Qwen-4B (ablation)EvoMAS · MBPPPass@1 (%): 86.2 -> 84.8No clear effect
replace Cyber Creator LLM with Qwen-4B (ablation)EvoMAS · MBPPPass@1 (%): 86.2 -> 81.4Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy