Adaptive Robust Estimator for Multi-Agent Reinforcement Learning

• URL: http://arxiv.org/abs/2603.21574v1
• Date: Mon, 23 Mar 2026 04:51:15 GMT
• Title: Adaptive Robust Estimator for Multi-Agent Reinforcement Learning
• Abstract summary: We propose a robust multi-agent reinforcement learning framework for collaborative reasoning.<n>It consists of two components: Dual-Agent Answer-Critique-Rewrite (DACR) and an Adaptive Robust Estimator (ARE)
• Score: 27.595086716369483
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Multi-agent collaboration has emerged as a powerful paradigm for enhancing the reasoning capabilities of large language models, yet it suffers from interaction-level ambiguity that blurs generation, critique, and revision, making credit assignment across agents difficult. Moreover, policy optimization in this setting is vulnerable to heavy-tailed and noisy rewards, which can bias advantage estimation and trigger unstable or even divergent training. To address both issues, we propose a robust multi-agent reinforcement learning framework for collaborative reasoning, consisting of two components: Dual-Agent Answer-Critique-Rewrite (DACR) and an Adaptive Robust Estimator (ARE). DACR decomposes reasoning into a structured three-stage pipeline: answer, critique, and rewrite, while enabling explicit attribution of each agent's marginal contribution to its partner's performance. ARE provides robust estimation of batch experience means during multi-agent policy optimization. Across mathematical reasoning and embodied intelligence benchmarks, even under noisy rewards, our method consistently outperforms the baseline in both homogeneous and heterogeneous settings. These results indicate stronger robustness to reward noise and more stable training dynamics, effectively preventing optimization failures caused by noisy reward signals.

Related papers

• Plug-and-Play Reweighting for Resilient Collaborative Decision-Making in Connected Autonomous Driving [35.0382657479364]
  perceptual noise and adversarial attacks in collaborators can severely affect decision reliability.<n>We propose a novel Resilient Collaborative Decision-Making framework that consists of an attention-based encoder and an attention-based decoder.<n>Our approach consistently outperforms existing methods by up to 26% and achieves state-of-the-art resilient performance.
  arXiv  Detail & Related papers  (2026-07-10T23:36:31Z)
• 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)
• Taming Actor-Observer Asymmetry in Agents via Dialectical Alignment [59.536125286960186]
  Multi-agent frameworks assigning specialized roles are increasingly adopted to enable self-reflection and mutual auditing.<n>We find it simultaneously induces a human-like cognitive bias known as Actor-Observer Asymmetry.<n>ReTAS guides agents to synthesize conflicting viewpoints into an objective consensus.
  arXiv  Detail & Related papers  (2026-04-21T15:05:58Z)
• DR-MMSearchAgent: Deepening Reasoning in Multimodal Search Agents [24.61813749877376]
  Deepening Reasoning MMSearchAgent derives advantage signals from whole rollout trajectories in an entire batch.<n> differentiated gaussian rewards are employed to dynamically calibrate interaction tolerance.<n>Our method achieves state-of-the-art performance, outperforming the MMSearch-R1 by 8.4$%$ on FVQA-test.
  arXiv  Detail & Related papers  (2026-04-21T09:28:34Z)
• Weak-Link Optimization for Multi-Agent Reasoning and Collaboration [24.206703927810825]
  LLM-driven multi-agent frameworks address complex reasoning tasks through multi-role collaboration.<n>Existing approaches often suffer from reasoning instability, where individual agent errors are amplified through collaboration.<n>We propose WORC, a framework for identification and reinforcement of performance-limiting agents.
  arXiv  Detail & Related papers  (2026-04-17T11:36:20Z)
• CDRRM: Contrast-Driven Rubric Generation for Reliable and Interpretable Reward Modeling [61.75914342638658]
  CDRRM (Contrast-Driven Reward Model) is a framework for high-quality rubric generation and guided preference judgment.<n>This work offers a scalable, interpretable, and data-efficient path for reward modeling.
  arXiv  Detail & Related papers  (2026-03-09T07:15:23Z)
• Search-R2: Enhancing Search-Integrated Reasoning via Actor-Refiner Collaboration [49.9937230730202]
  We propose Search-R2, a novel Actor-Refiner collaboration framework that enhances reasoning through targeted intervention.<n>Our approach decomposes the generation process into an Actor, which produces initial reasoning trajectories.<n>We show that Search-R2 consistently outperforms strong RAG and RL-based baselines across model scales.
  arXiv  Detail & Related papers  (2026-02-03T15:32:09Z)
• ICPO: Intrinsic Confidence-Driven Group Relative Preference Optimization for Efficient Reinforcement Learning [17.98065634130798]
  We propose the Intrinsic Confidence-Driven Group Relative Preference Optimization method (ICPO)<n>ICPO calculates a preference advantage score for each response by comparing the relative generation probabilities of multiple responses under the same input prompt.<n>We have discovered that the preference advantage score not only alleviates the issues of coarse-grained rewards and reward noise but also effectively curbs overconfident errors.
  arXiv  Detail & Related papers  (2025-11-26T03:10:15Z)
• Sycophancy Mitigation Through Reinforcement Learning with Uncertainty-Aware Adaptive Reasoning Trajectories [58.988535279557546]
  We introduce textbf sycophancy Mitigation through Adaptive Reasoning Trajectories.<n>We show that SMART significantly reduces sycophantic behavior while preserving strong performance on out-of-distribution inputs.
  arXiv  Detail & Related papers  (2025-09-20T17:09:14Z)
• STARec: An Efficient Agent Framework for Recommender Systems via Autonomous Deliberate Reasoning [54.28691219536054]
  We introduce STARec, a slow-thinking augmented agent framework that endows recommender systems with autonomous deliberative reasoning capabilities.<n>We develop anchored reinforcement training - a two-stage paradigm combining structured knowledge distillation from advanced reasoning models with preference-aligned reward shaping.<n>Experiments on MovieLens 1M and Amazon CDs benchmarks demonstrate that STARec achieves substantial performance gains compared with state-of-the-art baselines.
  arXiv  Detail & Related papers  (2025-08-26T08:47:58Z)
• On the Role of Feedback in Test-Time Scaling of Agentic AI Workflows [71.92083784393418]
  Agentic AI (systems that autonomously plan and act) are becoming widespread, yet their task success rate on complex tasks remains low.<n>Inference-time alignment relies on three components: sampling, evaluation, and feedback.<n>We introduce Iterative Agent Decoding (IAD), a procedure that repeatedly inserts feedback extracted from different forms of critiques.
  arXiv  Detail & Related papers  (2025-04-02T17:40:47Z)
• Adversarial Robustness in Two-Stage Learning-to-Defer: Algorithms and Guarantees [6.792743621449621]
  Two-stage Learning-to-Defer (L2D) enables optimal task delegation by assigning each input to either a fixed main model or one of several offline experts.<n>Existing L2D frameworks assume clean inputs and are vulnerable to adversarial perturbations that can manipulate query allocation.<n>We present the first comprehensive study of adversarial robustness in two-stage L2D systems.
  arXiv  Detail & Related papers  (2025-02-03T03:44:35Z)

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.