Adnan KhanAdnanProduct & AI
San Francisco Bay Area
Get in touch

Source note3 min read

Digital Pantheon: Simulating and Auditing Coalition Formation with LLM Agents

Source

arXiv

arxiv.org/abs/2607.15095v1

Read the source

Source

Plain-Language Brief

Researchers present a multi-agent framework that simulates political coalition formation using Large Language Models (LLMs). The framework combines Supervised Fine-Tuning (SFT), Direct Preference Optimization (DPO), and Retrieval-Augmented Generation (RAG) to create party-specific personas while keeping each agent bounded to its official manifesto. The research operationalizes the framework on the 2019 Flemish election and introduces a Multi-Layered Information Lineage Topology (MILT) for traceability and interpretation of negotiations. Simulations resulted in a stable winner and ranking, with the method predicting real-world materialization.

What the Document Says

  • A multi-agent framework was presented for simulating political coalition formation using LLMs.
  • The framework combines Supervised Fine-Tuning (SFT), Direct Preference Optimization (DPO), and Retrieval-Augmented Generation (RAG).
  • Each agent is bound to its official manifesto to create party-specific personas.
  • The framework was operationalized on the 2019 Flemish election, with agents negotiating in a hub-and-spoke setup mediated by a formateur.
  • A Multi-Layered Information Lineage Topology (MILT) was introduced for traceability and interpretation of negotiations.
  • Three independent simulations resulted in a stable winner and ranking: N-VA ahead of CD&V and Open Vld.
  • The method predicts real-world materialization, while hallucinated content does not.

Key Concepts Mentioned

  • Political coalition formation
  • Large Language Models (LLMs)
  • Supervised Fine-Tuning (SFT)
  • Direct Preference Optimization (DPO)
  • Retrieval-Augmented Generation (RAG)
  • 2019 Flemish election
  • Hub-and-spoke negotiation
  • Multi-Layered Information Lineage Topology (MILT)
  • Coalition Influence Score (CIS)
  • Real-world grounding pass

Claims Made by the Document

  • The presented framework can simulate political coalition formation.
  • Simulations yield a stable winner and ranking.
  • The method predicts real-world materialization.

Evidence Used

  • The text describes a multi-agent framework for simulating political coalitions, the operationalization of this framework on the 2019 Flemish election, and results from three independent simulations.

Methods / Approach

  • Multi-agent framework combining SFT, DPO, and RAG
  • Hub-and-spoke negotiation mediated by a formateur
  • Multi-Layered Information Lineage Topology (MILT)
  • Coalition Influence Score (CIS)
  • Real-world grounding pass

Limitations Stated by the Authors

UNKNOWN

Limitations Noted by the Agent

Agent interpretation — not from the source.

The text does not mention any specific limitations of the LLMs used in the research.

Open Questions

  • What other elections or political scenarios have been tested with this framework?

Notes for Future Q&A

May include interpretation. Labeled where it does.

The research focuses on the Flemish election of 2019. It's unclear if the method has been applied to other elections or political contexts.

Raw Abstract / Excerpt

The formation of political coalitions is a complex negotiation driven by both concrete policy objectives and deep-seated ideological convictions. While Large Language Models (LLMs) open new avenues for computational political science, the neutrality and helpfulness biases instilled by Reinforcement Learning from Human Feedback (RLHF) prevent them from sustaining steadfast partisan behaviour. We present a multi-agent framework that reconciles factual grounding with ideological alignment by combining Supervised Fine-Tuning (SFT), Direct Preference Optimization (DPO), and Retrieval-Augmented Generation (RAG): DPO instils aggressive party-specific personas, while a per-party RAG pipeline keeps each agent bounded to its official manifesto. We operationalize the framework on the 2019 Flemish election, deploying the partisan agents in a hub-and-spoke negotiation arbitrated by a formateur. To make the emergent negotiation interpretable, we introduce a Multi-Layered Information Lineage Topology (MILT) that traces every clause in the final agreement back to its manifesto origin and classifies it into five provenance states, a Coalition Influence Score (CIS) that aggregates these traceable contributions to identify which party shaped the agreement, and a real-world grounding pass that benchmarks each simulated provision against the historically adopted coalition agreement. Across three independent simulations the framework yields a stable winner and ranking (N-VA ahead of CD&V and Open Vld), and manifesto-anchored lineage reliably predicts real-world materialization whereas hallucinated content does not. The result is a transparent, scalable testbed for the ex-ante exploration of party compatibility and formateur-mediated compromise.