Counterfactual Credit Policy Optimization for Multi-Agent Collaboration

• URL: http://arxiv.org/abs/2603.21563v1
• Date: Mon, 23 Mar 2026 04:35:02 GMT
• Title: Counterfactual Credit Policy Optimization for Multi-Agent Collaboration
• Abstract summary: Collaborative multi-agent large language models (LLMs) can solve complex reasoning tasks by decomposing roles and aggregating diverse hypotheses.<n>We introduce Counterfactual Credit Policy Optimization (CCPO), a framework that assigns agent-specific learning signals.<n> CCPO builds dynamic counterfactual baselines that simulate outcomes with an agent's contribution removed.
• Score: 27.260904103460664
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Collaborative multi-agent large language models (LLMs) can solve complex reasoning tasks by decomposing roles and aggregating diverse hypotheses. Yet, reinforcement learning (RL) for such systems is often undermined by credit assignment: a shared global reward obscures individual contributions, inflating update variance and encouraging free-riding. We introduce Counterfactual Credit Policy Optimization (CCPO), a framework that assigns agent-specific learning signals by estimating each agent's marginal contribution through counterfactual trajectories. CCPO builds dynamic counterfactual baselines that simulate outcomes with an agent's contribution removed, yielding role-sensitive advantages for policy optimization. To further improve stability under heterogeneous tasks and data distributions, we propose a global-history-aware normalization scheme that calibrates advantages using global rollout statistics. We evaluate CCPO on two collaboration topologies: a sequential Think--Reason dyad and multi-agent voting. Across mathematical and logical reasoning benchmarks, CCPO mitigates free-riding and outperforms strong multi-agent RL baselines, yielding finer-grained and more effective credit assignment for collaborative LLM training. Our code is available at https://github.com/bhai114/ccpo.

Related papers

• Multi-Agent Reinforcement Learning via Agent-Specific Preference [13.390117775984798]
  Multi-agent reinforcement learning relies heavily on well-defined global reward functions.<n>We introduce Multi-AGent Preference-Integrated lEarning (MAGPIE), which addresses these challenges through agent-specific preference modeling.<n>We show that MAGPIE achieves performance comparable to reward-engineered baselines.
  arXiv  Detail & Related papers  (2026-08-09T09:38:41Z)
• GD$^2$PO: Mitigating Multi-Reward Conflicts via Group-Dynamic reward-Decoupled Policy Optimization [54.596224644751565]
  Post-training reinforcement learning (RL) increasingly relies on multi-dimensional rewards to cultivate comprehensive capabilities.<n>To address this, existing methods such as Group reward-Decoupled Policy Optimization (GDPO) decompose the overall score into independent reward groups, then compute the RL loss separately within each group.<n>We propose Group-Dynamic reward-Decoupled Policy Optimization (GD$2$PO), which employs a conflict-aware filtering mechanism to mask out rollouts suffering from severe reward-wise disagreement.
  arXiv  Detail & Related papers  (2026-06-15T14:19:28Z)
• TRACE: A Unified Rollout Budget Allocation Framework for Efficient Agentic Reinforcement Learning [52.67756371231985]
  Reinforcement learning with verifiable rewards (RLVR) is a promising approach for enhancing reasoning and agentic behavior in large language models.<n>We introduce Tree Rollout Allocation for Contrastive Exploration (TRACE), a unified rollout allocation framework.<n>Technically, TRACE allocates rollout budget to both prompt roots and intermediate prefixes that are most likely to yield mixed terminal rewards.
  arXiv  Detail & Related papers  (2026-06-09T17:16:03Z)
• Breaking $\ extit{Winner-Takes-All}$: Cooperative Policy Optimization Improves Diverse LLM Reasoning [53.42577591449649]
  Group Cooperative Policy Optimization shifts the training paradigm from rollout competition to team cooperation.<n>GCPO replaces independent rollout scoring with team-level credit assignment.<n>It redistributes the collective team reward to each single rollout according to its average marginal contribution to the team.
  arXiv  Detail & Related papers  (2026-05-12T03:20:24Z)
• CoFi-PGMA: Counterfactual Policy Gradients under Filtered Feedback for Multi-Agent LLMs [0.0]
  We introduce CoFi-PGMA, a unified framework for learning under filtered feedback in multi-agent LLM systems.<n>Our approach derives a counterfactual per-agent training objective based on marginal contribution, which corrects the learning signal under both routing and collaborative mechanisms.
  arXiv  Detail & Related papers  (2026-04-03T22:55:23Z)
• GDPO: Group reward-Decoupled Normalization Policy Optimization for Multi-reward RL Optimization [133.27496265096445]
  We show how to apply Group Relative Policy Optimization under multi-reward setting without examining its suitability.<n>We then introduce Group reward-Decoupled Normalization Policy Optimization (GDPO), a new policy optimization method to resolve these issues.<n>GDPO consistently outperforms GRPO, demonstrating its effectiveness and generalizability for multi-reward reinforcement learning optimization.
  arXiv  Detail & Related papers  (2026-01-08T18:59:24Z)
• Information Gain-based Policy Optimization: A Simple and Effective Approach for Multi-Turn LLM Agents [28.145430029174577]
  Large language model (LLM)-based agents are increasingly trained with reinforcement learning (RL) to enhance their ability to interact with external environments.<n>Existing approaches typically rely on outcome-based rewards that are only provided at the final answer.<n>In this paper, we propose Information Gain-based Policy Optimization (IGPO), a simple yet effective RL framework that provides dense and intrinsic supervision for multi-turn agent training.
  arXiv  Detail & Related papers  (2025-10-16T17:59:32Z)
• Agentic Reinforcement Learning with Implicit Step Rewards [92.26560379363492]
  Large language models (LLMs) are increasingly developed as autonomous agents using reinforcement learning (agentic RL)<n>We introduce implicit step rewards for agentic RL (iStar), a general credit-assignment strategy that integrates seamlessly with standard RL algorithms.<n>We evaluate our method on three challenging agent benchmarks, including WebShop and VisualSokoban, as well as open-ended social interactions with unverifiable rewards in SOTOPIA.
  arXiv  Detail & Related papers  (2025-09-23T16:15:42Z)
• Enhancing Diversity in Parallel Agents: A Maximum State Entropy Exploration Story [40.82741665804367]
  We introduce a novel learning framework that maximizes the entropy of collected data in a parallel setting.<n>Our approach carefully balances the entropy of individual agents with inter-agent diversity, effectively minimizing redundancies.
  arXiv  Detail & Related papers  (2025-05-02T15:08:17Z)
• Collab: Controlled Decoding using Mixture of Agents for LLM Alignment [90.6117569025754]
  Reinforcement learning from human feedback has emerged as an effective technique to align Large Language models.<n>Controlled Decoding provides a mechanism for aligning a model at inference time without retraining.<n>We propose a mixture of agent-based decoding strategies leveraging the existing off-the-shelf aligned LLM policies.
  arXiv  Detail & Related papers  (2025-03-27T17:34:25Z)
• Redistributing Rewards Across Time and Agents for Multi-Agent Reinforcement Learning [14.852334980733369]
  Credit assignmen, disentangling each agent's contribution to a shared reward, is a critical challenge in cooperative multi-agent reinforcement learning.<n>We introduce Temporal-Agent Reward Redistribution (TAR$2$), an approach that decouples credit modeling from this constraint.<n>We demonstrate that this method is equivalent to a valid Potential-Based Reward Shaping (PBRS), which guarantees the optimal policy is preserved regardless of model accuracy.
  arXiv  Detail & Related papers  (2025-02-07T12:07:57Z)
• VinePPO: Refining Credit Assignment in RL Training of LLMs [66.80143024475635]
  We propose VinePPO, a straightforward approach that leverages the flexibility of language environments to compute unbiased Monte Carlo-based estimates.<n>Our method consistently outperforms PPO and other baselines across MATH and GSM8K datasets in less wall-clock time.
  arXiv  Detail & Related papers  (2024-10-02T15:49:30Z)
• Learning Cooperative Multi-Agent Policies with Partial Reward Decoupling [13.915157044948364]
  One of the preeminent obstacles to scaling multi-agent reinforcement learning is assigning credit to individual agents' actions. In this paper, we address this credit assignment problem with an approach that we call textitpartial reward decoupling (PRD) PRD decomposes large cooperative multi-agent RL problems into decoupled subproblems involving subsets of agents, thereby simplifying credit assignment.
  arXiv  Detail & Related papers  (2021-12-23T17:48:04Z)

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.