ExRole: From Team Trajectories to Executable Roles in Multi-Agent Language Models

• URL: http://arxiv.org/abs/2608.11949v1
• Date: Wed, 12 Aug 2026 11:35:31 GMT
• Title: ExRole: From Team Trajectories to Executable Roles in Multi-Agent Language Models
• Abstract summary: We argue that a useful role should instead be an executable control variable.<n>We introduce ExRole, a trajectory-to-role framework that learns future-aware role prototypes.<n>Across benchmarks, the results consistently favor trajectory-induced role conditioning over role-free, manual, random, and shuffled alternatives.
• Score: 8.17263506524276
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Roles provide an interpretable interface for organizing language-model agents, yet most multi-agent systems treat them as hand-written prompt labels disconnected from learned behavior and parameter updates. We argue that a useful role should instead be an executable control variable: it should summarize behavior predictive of future utility, guide subsequent interaction, and identify the trainable capacity responsible for that behavior. We introduce ExRole, a trajectory-to-role framework that learns future-aware role prototypes from prefix-local team traces, resolves them into readable instructions and token-aligned role markers, and optionally routes shared LoRA rank slots with turn-aligned credit. Across MuSiQue and 2WikiMultiHopQA, ExRole improves over single-agent search by 15.0/14.4 and 13.5/16.1 EM/F1 points, respectively. Against the strongest non-ExRole controls, the corresponding gains remain 11.5/11.6 and 7.7/9.7 points. Across both benchmarks, the controlled results consistently favor trajectory-induced role conditioning over role-free, manual, random, and shuffled alternatives. Role-Agent-Turn interventions further show that the induced roles capture transferable behavioral specialization beyond fixed agent identities or turn positions.

Related papers

• Role Steering of Language Models for Social Simulations [1.593682229070013]
  Social simulations built from language-model agents need role-conditioned behavior that can be checked before agents are placed into a simulated population.<n>We introduce an activation-steering screening workflow for role-conditioned agents.<n>We apply the workflow to a mixed 275-role inventory with 228 role-agnostic questions, GPT-4.1-mini prompted role references, and GPT-4.1-mini judges.
  arXiv  Detail & Related papers  (2026-07-09T22:07:27Z)
• The Why Behind the Action: Unveiling Internal Drivers via Agentic Attribution [63.61358761489141]
  Large Language Model (LLM)-based agents are widely used in real-world applications such as customer service, web navigation, and software engineering.<n>We propose a novel framework for textbfgeneral agentic attribution, designed to identify the internal factors driving agent actions regardless of the task outcome.<n>We validate our framework across a diverse suite of agentic scenarios, including standard tool use and subtle reliability risks like memory-induced bias.
  arXiv  Detail & Related papers  (2026-01-21T15:22:21Z)
• AdaMARP: An Adaptive Multi-Agent Interaction Framework for General Immersive Role-Playing [71.66362858228418]
  LLM role-playing aims to portray arbitrary characters in interactive narratives, yet existing systems often suffer from limited immersion and adaptability.<n>We propose an adaptive multi-agent role-playing framework, AdaMARP, featuring an immersive message format that interleaves [Thought], (Action), Environment>, and Speech.
  arXiv  Detail & Related papers  (2026-01-16T05:41:45Z)
• MoRAgent: Parameter Efficient Agent Tuning with Mixture-of-Roles [25.198556596878362]
  We introduce three key strategies for parameter-efficient fine-tuning (PEFT) in agent tasks.<n>Inspired by the increasingly dominant Reason+Action paradigm, we first decompose the capabilities necessary for the agent tasks into three distinct roles.<n>We propose the Mixture-of-Roles (MoR) framework, which comprises three specialized Low-Rank Adaptation (LoRA) groups, each designated to fulfill a distinct role.
  arXiv  Detail & Related papers  (2025-12-25T15:02:07Z)
• AgentRouter: A Knowledge-Graph-Guided LLM Router for Collaborative Multi-Agent Question Answering [51.07491603393163]
  tAgent is a framework that formulates multi-agent QA as a knowledge-graph-guided routing problem supervised by empirical performance signals.<n>By leveraging soft supervision and weighted aggregation of agent outputs, Agent learns principled collaboration schemes that capture the complementary strengths of diverse agents.
  arXiv  Detail & Related papers  (2025-10-06T23:20:49Z)
• The Illusion of Role Separation: Hidden Shortcuts in LLM Role Learning (and How to Fix Them) [15.48684126686974]
  We show that fine-tuned large language models often rely on two proxies for role identification.<n>We propose reinforcing emphinvariant signals that mark role boundaries by adjusting token-wise cues in the model's input encoding.
  arXiv  Detail & Related papers  (2025-05-01T16:06:16Z)
• RoleMRC: A Fine-Grained Composite Benchmark for Role-Playing and Instruction-Following [31.80357046048002]
  Role-playing is important for Large Language Models to follow diverse instructions.<n>Existing role-playing datasets mostly contribute to controlling role style and knowledge boundaries.<n>We introduce a fine-grained role-playing and instruction-following benchmark, named RoleMRC.
  arXiv  Detail & Related papers  (2025-02-17T03:08:37Z)
• RNR: Teaching Large Language Models to Follow Roles and Rules [153.6596303205894]
  We propose model, an automated data generation pipeline that generates diverse roles and rules from existing IFT instructions. This data can then be used to train models that follow complex system prompts. Our framework significantly improves role and rule following capability in large language models.
  arXiv  Detail & Related papers  (2024-09-10T06:07:32Z)
• RoleLLM: Benchmarking, Eliciting, and Enhancing Role-Playing Abilities of Large Language Models [107.00832724504752]
  We introduce RoleLLM, a framework to benchmark, elicit, and enhance role-playing abilities in Large Language Models (LLMs) By Context-Instruct and RoleGPT, we create RoleBench, the first systematic and fine-grained character-level benchmark dataset for role-playing with 168,093 samples.
  arXiv  Detail & Related papers  (2023-10-01T17:52:59Z)
• About latent roles in forecasting players in team sports [47.066729480128856]
  Team sports contain a significant social component that influences interactions between teammates and opponents. We create RolFor, a novel end-to-end model for Role-based Forecasting.
  arXiv  Detail & Related papers  (2023-04-17T13:33:23Z)
• RODE: Learning Roles to Decompose Multi-Agent Tasks [69.56458960841165]
  Role-based learning holds the promise of achieving scalable multi-agent learning by decomposing complex tasks using roles. We propose to first decompose joint action spaces into restricted role action spaces by clustering actions according to their effects on the environment and other agents. By virtue of these advances, our method outperforms the current state-of-the-art MARL algorithms on 10 of the 14 scenarios that comprise the challenging StarCraft II micromanagement benchmark.
  arXiv  Detail & Related papers  (2020-10-04T09:20:59Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.