Structuring Collective Action with LLM-Guided Evolution: From Ill-Structured Problems to Executable Heuristics

2025-09-24

AI Summary

This paper addresses the unstructured problem (ISP) of misaligned individual incentives and collective objectives in collective action. We propose ECHO-MIMIC: in the ECHO phase, an LLM-guided evolutionary algorithm optimizes executable Python behavioral strategies; in the MIMIC phase, interpretable and customizable persuasive textual messages co-evolve synchronously with the strategies. ECHO-MIMIC introduces the first code–natural-language co-evolution mechanism, integrating simulation-based environmental evaluation to translate macro-level collective challenges into micro-level, executable heuristics and high-impact persuasive communications. Evaluated in agricultural landscape management, the evolved strategies significantly outperform baselines, yielding substantial improvements in ecological connectivity. Results demonstrate the framework’s effectiveness—and novelty—in lowering cognitive barriers and fostering behavioral alignment toward collective goals.

Technology Category

• Multiagent Systems: Mechanism Design
• Cognitive Modeling & Cognitive Systems: Simulating Human Behavior
• Search and Optimization: Evolutionary Computation

Application Category

• Economics, Online Markets and Human Computation: Incentives in network design for Web infrastructures and ecosystems
• User Modeling, Personalization and Recommendation: User modeling and simulation for interactive and conversational systems
• Search and Retrieval-Augmented AI: Search Tool Learning with LLM: Teaching LLMs to invoke search and make use of retrieved information

Abstract

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 computational framework that converts this global complexity into a tractable, Well-Structured Problem (WSP) for each agent by discovering compact, 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 a canonical ISP in agricultural landscape management, where local farming decisions impact global ecological connectivity. Results show that ECHO-MIMIC discovers high-performing heuristics compared to baselines and crafts tailored messages that successfully align simulated farmer behavior with landscape-level ecological goals. By coupling algorithmic rule discovery with tailored communication, ECHO-MIMIC transforms the cognitive burden of collective action into a simple set of agent-level instructions, making previously ill-structured problems solvable in practice and opening a new path toward scalable, adaptive policy design.

Problem

• Transforming ill-structured collective action problems into well-structured ones
• Discovering executable heuristics that align individual actions with collective goals
• Developing persuasive rationales to motivate agents to adopt beneficial policies

Innovation

• Evolutionary search guided by LLM for code generation
• Two-stage framework combining heuristic discovery with messaging
• Transforms ill-structured problems into executable agent instructions