Saved in:
Bibliographic Details
Main Authors: Dsouza, Kevin Bradley, Watt, Graham Alexander, Leonenko, Yuri, Moreno-Cruz, Juan
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2509.20412
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914178115043328
author Dsouza, Kevin Bradley
Watt, Graham Alexander
Leonenko, Yuri
Moreno-Cruz, Juan
author_facet Dsouza, Kevin Bradley
Watt, Graham Alexander
Leonenko, Yuri
Moreno-Cruz, Juan
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2509_20412
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Structuring Collective Action with LLM-Guided Evolution: From Ill-Structured Problems to Executable Heuristics
Dsouza, Kevin Bradley
Watt, Graham Alexander
Leonenko, Yuri
Moreno-Cruz, Juan
Multiagent Systems
Machine Learning
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.
title Structuring Collective Action with LLM-Guided Evolution: From Ill-Structured Problems to Executable Heuristics
topic Multiagent Systems
Machine Learning
url https://arxiv.org/abs/2509.20412