Who Deserves the Reward? SHARP: Shapley Credit-based Optimization for Multi-Agent System
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911433931882496 |
|---|---|
| author | Li, Yanming Zhang, Xuelin Lu, WenJie Tang, Ziye Wu, Maodong Luo, Haotian Wu, Tongtong Peng, Zijie Mi, Hongze Feng, Yibo Tan, Naiqiang Huang, Chao Chen, Hong Shen, Li |
| author_facet | Li, Yanming Zhang, Xuelin Lu, WenJie Tang, Ziye Wu, Maodong Luo, Haotian Wu, Tongtong Peng, Zijie Mi, Hongze Feng, Yibo Tan, Naiqiang Huang, Chao Chen, Hong Shen, Li |
| contents | Integrating Large Language Models (LLMs) with external tools via multi-agent systems offers a promising new paradigm for decomposing and solving complex problems. However, training these systems remains notoriously difficult due to the credit assignment challenge, as it is often unclear which specific functional agent is responsible for the success or failure of decision trajectories. Existing methods typically rely on sparse or globally broadcast rewards, failing to capture individual contributions and leading to inefficient reinforcement learning. To address these limitations, we introduce the Shapley-based Hierarchical Attribution for Reinforcement Policy (SHARP), a novel framework for optimizing multi-agent reinforcement learning via precise credit attribution. SHARP effectively stabilizes training by normalizing agent-specific advantages across trajectory groups, primarily through a decomposed reward mechanism comprising a global broadcast-accuracy reward, a Shapley-based marginal-credit reward for each agent, and a tool-process reward to improve execution efficiency. Extensive experiments across various real-world benchmarks demonstrate that SHARP significantly outperforms recent state-of-the-art baselines, achieving average match improvements of 23.66% and 14.05% over single-agent and multi-agent approaches, respectively. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_08335 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Who Deserves the Reward? SHARP: Shapley Credit-based Optimization for Multi-Agent System Li, Yanming Zhang, Xuelin Lu, WenJie Tang, Ziye Wu, Maodong Luo, Haotian Wu, Tongtong Peng, Zijie Mi, Hongze Feng, Yibo Tan, Naiqiang Huang, Chao Chen, Hong Shen, Li Artificial Intelligence Integrating Large Language Models (LLMs) with external tools via multi-agent systems offers a promising new paradigm for decomposing and solving complex problems. However, training these systems remains notoriously difficult due to the credit assignment challenge, as it is often unclear which specific functional agent is responsible for the success or failure of decision trajectories. Existing methods typically rely on sparse or globally broadcast rewards, failing to capture individual contributions and leading to inefficient reinforcement learning. To address these limitations, we introduce the Shapley-based Hierarchical Attribution for Reinforcement Policy (SHARP), a novel framework for optimizing multi-agent reinforcement learning via precise credit attribution. SHARP effectively stabilizes training by normalizing agent-specific advantages across trajectory groups, primarily through a decomposed reward mechanism comprising a global broadcast-accuracy reward, a Shapley-based marginal-credit reward for each agent, and a tool-process reward to improve execution efficiency. Extensive experiments across various real-world benchmarks demonstrate that SHARP significantly outperforms recent state-of-the-art baselines, achieving average match improvements of 23.66% and 14.05% over single-agent and multi-agent approaches, respectively. |
| title | Who Deserves the Reward? SHARP: Shapley Credit-based Optimization for Multi-Agent System |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2602.08335 |