Structuring Collective Action with LLM-Guided Evolution: From Ill-Structured Problems to Executable Heuristics
Not on the map. Why?
Abstract (arXiv)
Collective action problems, which require aligning individual incentives with collective goals, are classic examples of Ill-Structured Problems (ISPs). For an individual agent, the causal links between local actions and global outcomes are unclear, stakeholder objectives often conflict, and no single, clear algorithm can bridge micro-level choices with macro-level welfare. We present ECHO-MIMIC, a general computational framework that converts this global complexity into a tractable, Well-Structured Problem (WSP) for each agent by discovering executable heuristics and persuasive rationales. The framework operates in two stages: ECHO (Evolutionary Crafting of Heuristics from Outcomes) evolves snippets of Python code that encode candidate behavioral policies, while MIMIC (Mechanism Inference & Messaging for Individual-to-Collective Alignment) evolves companion natural language messages that motivate agents to adopt those policies. Both phases employ a large-language-model-driven evolutionary search: the LLM proposes diverse and context-aware code or text variants, while population-level selection retains those that maximize collective performance in a simulated environment. We demonstrate this framework on two distinct ISPs: a canonical agricultural landscape management problem and a carbon-aware EV charging time slot usage problem. Results show that ECHO-MIMIC discovers high-performing heuristics compared to baselines and crafts tailored messages that successfully align simulated agent behavior with system-level goals. By coupling algorithmic rule discovery with tailored communication, ECHO-MIMIC transforms the cognitive burden of collective action into a implementable set of agent-level instructions, making previously ill-structured problems solvable in practice and opening a new path toward scalable, adaptive policy design.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 19 of its 46 references that are in the map. First posted on arXiv 24 Sep 2025.
Builds on
19 of 46 references.
References · 19
- 2023AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversationcited by 1,988
- 2025AlphaEvolve: A coding agent for scientific and algorithmic discoverycited by 867
- 2023Large Language Models as Optimizerscited by 864
- 2023DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelinescited by 832
- 2024Optimizing Instructions and Demonstrations for Multi-Stage Language Model Programscited by 291
- 2024ReEvo: Large Language Models as Hyper-Heuristics with Reflective Evolutioncited by 276
- 2024Evolution of Heuristics: Towards Efficient Automatic Algorithm Design Using Large Language Modelcited by 268
- 2017Multi-agent Reinforcement Learning in Sequential Social Dilemmascited by 209
- 2023EvoPrompting: Language Models for Code-Level Neural Architecture Searchcited by 131
- 2023Large Language Models as Evolutionary Optimizerscited by 124
- 2024G-Designer: Architecting Multi-agent Communication Topologies via Graph Neural Networkscited by 119
- 2018Inequity aversion improves cooperation in intertemporal social dilemmascited by 106
7 more
- 2024HSEvo: Elevating Automatic Heuristic Design with Diversity-Driven Harmony Search and Genetic Algorithm Using LLMscited by 73
- 2024Large Language Models As Evolution Strategiescited by 58
- 2020Learning to Incentivize Other Learning Agentscited by 57
- 2017Prosocial learning agents solve generalized Stag Hunts better than selfish onescited by 47
- 2024Persuasion with Large Language Models: A Survey of Empirical Evidence, Study Methodologies, and Ethical Implicationscited by 32
- 2022Carbon-Aware EV Chargingcited by 5
- 2025Bridging Farm Economics and Landscape Ecology for Global Sustainability through Hierarchical and Bayesian Optimizationcited by 1
Built on by
Not cited yet.