Search papers, labs, and topics across Lattice.
This paper introduces ExRole, a framework that transforms multi-agent language models by learning executable roles from team trajectories, rather than relying on static, hand-written prompts. By summarizing behavior that predicts future utility, ExRole enhances interaction and identifies trainable capacities, leading to significant performance improvements in two benchmarks: MuSiQue and 2WikiMultiHopQA. The results demonstrate that trajectory-induced role conditioning consistently outperforms traditional methods, achieving up to 16.1 F1 points higher than the best non-ExRole controls.
Executable roles derived from team trajectories can boost multi-agent language model performance by over 16 points, reshaping agent interactions.
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.
