# Roles with Rails: Contract-Preserving Role Evolution in Multi-Agent Structured Reasoning

arXiv: https://arxiv.org/abs/2605.28433 · HTML: https://mlsanity.com/paper/2605.28433/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Reasoning for agents, planning and code, one of 17 directions in LLM reasoning.
- Builds on 14 of its 38 references that are in the map.
- First posted on arXiv 27 May 2026.

## Placed in

- LLM reasoning / [Reasoning for agents, planning and code](https://mlsanity.com/lr/reasoning-for-agents-planning-and-code/)
- LLM agents and tool use / [General LLM agent frameworks and benchmarks](https://mlsanity.com/agents/general-llm-agent-frameworks-and-benchmarks/)

## Builds on (most cited first, 14 of 14)

- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://mlsanity.com/paper/2203.11171/) (2022)
- [AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation](https://mlsanity.com/paper/2308.08155/) (2023)
- [A Dynamic LLM-Powered Agent Network for Task-Oriented Agent Collaboration](https://mlsanity.com/paper/2310.02170/) (2023)
- [NATURAL PLAN: Benchmarking LLMs on Natural Language Planning](https://mlsanity.com/paper/2406.04520/) (2024)
- [Exponential Moving Average of Weights in Deep Learning: Dynamics and Benefits](https://mlsanity.com/paper/2411.18704/) (2024)
- [Multi-Agent Evolve: LLM Self-Improve through Co-evolution](https://mlsanity.com/paper/2510.23595/) (2025)
- [Adaptive Graph Pruning for Multi-Agent Communication](https://mlsanity.com/paper/2506.02951/) (2025)
- [Leveraging Large Language Models for Effective and Explainable Multi-Agent Credit Assignment](https://mlsanity.com/paper/2502.16863/) (2025)
- [MetaGen: Self-Evolving Roles and Topologies for Multi-Agent LLM Reasoning](https://mlsanity.com/paper/2601.19290/) (2026)
- [Dynamic Role Assignment for Multi-Agent Debate](https://mlsanity.com/paper/2601.17152/) (2026)
- [TodyComm: Task-Oriented Dynamic Communication for Multi-Round LLM-based Multi-Agent System](https://mlsanity.com/paper/2602.03688/) (2026)
- [GoAgent: Group-of-Agents Communication Topology Generation for LLM-based Multi-Agent Systems](https://mlsanity.com/paper/2603.19677/) (2026)
- [SC-MAS: Constructing Cost-Efficient Multi-Agent Systems with Edge-Level Heterogeneous Collaboration](https://mlsanity.com/paper/2601.09434/) (2026)

## Abstract (arXiv)

Role-based LLM multi-agent systems need adaptive role pools, yet adapting such systems is not merely a matter of prompt optimization: roles often carry structural obligations, including capability coverage, message compatibility, validation, final-answer aggregation, and parser-compatible output protocols. Existing systems either fix the role inventory and lose adaptivity, or allow unconstrained generation to induce role drift, removing structurally necessary roles and breaking answer contracts. We formulate this as contract-preserving role evolution, requiring every committed edit to preserve five structural contracts (capability, communication, validation, aggregation, output protocol). We instantiate this formulation in SERO, a Self-Evolving Role Orchestration framework that evolves a typed role-card pool through credit-guided retrieval, a credit-ranked communication DAG with a protected terminal aggregator and conditional validator repair, and a contextual-bandit controller whose LLM-proposed edits are committed only when they preserve the contracts and improve task score. Experiments on real-world reasoning benchmarks across three LLM backbones confirm the value of contract-preserving role evolution.