{"ID":2843641,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2511.10687","arxiv_id":"2511.10687","title":"Who Gets the Reward, Who Gets the Blame? Evaluation-Aligned Training Signals for Multi-LLM Agents","abstract":"Large Language Models (LLMs) in multi-agent systems (MAS) have shown promise for complex tasks, yet current training methods lack principled ways to connect system-level evaluation with agent-level and message-level learning. We propose a theoretical framework that unifies cooperative game-theoretic attribution with process reward modeling to transform system evaluation into agent credit and then into response-level signals. Unlike prior approaches that rely only on attribution (e.g., Shapley) or step-level labels (e.g., PRM), our method produces local, signed, and credit-conserving signals. In success cases, Shapley-based credit assignment fairly allocates outcomes across agents and is refined into per-message rewards that promote cooperation while discouraging redundancy or sabotage. In failure cases, first-error localization yields repair-aware preferences that penalize harmful steps while rewarding corrective attempts. The resulting signals are bounded, cooperative, and directly compatible with reinforcement-based or preference-based post-training, providing a unified and auditable pathway from global evaluation to local supervision in LLM multi-agent training. Our contribution is conceptual: we present a theoretical foundation and training signals, leaving empirical validation for future work.","short_abstract":"Large Language Models (LLMs) in multi-agent systems (MAS) have shown promise for complex tasks, yet current training methods lack principled ways to connect system-level evaluation with agent-level and message-level learning. We propose a theoretical framework that unifies cooperative game-theoretic attribution with pr...","url_abs":"https://arxiv.org/abs/2511.10687","url_pdf":"https://arxiv.org/pdf/2511.10687v2","authors":"[\"Chih-Hsuan Yang\",\"Tanwi Mallick\",\"Le Chen\",\"Krishnan Raghavan\",\"Azton Wells\",\"Amal Gueroudji\",\"Ian T. Foster\",\"Rajeev Thakur\"]","published":"2025-11-11T22:21:08Z","proceeding":"cs.MA","tasks":"[\"cs.MA\",\"cs.AI\",\"cs.CL\",\"cs.GT\"]","methods":"[\"Large Language Model\",\"Language Model\"]","has_code":false}