No More Stale Feedback: Co-Evolving Critics for Open-World Agent Learning

• URL: http://arxiv.org/abs/2601.06794v1
• Date: Sun, 11 Jan 2026 07:29:08 GMT
• Title: No More Stale Feedback: Co-Evolving Critics for Open-World Agent Learning
• Abstract summary: ECHO is a framework that jointly optimize the policy and critic through a synchronized co-evolutionary loop.<n>ECHO yields more stable training and higher long-horizon task success across open-world environments.
• Score: 21.237273221334963
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Critique-guided reinforcement learning (RL) has emerged as a powerful paradigm for training LLM agents by augmenting sparse outcome rewards with natural-language feedback. However, current methods often rely on static or offline critic models, which fail to adapt as the policy evolves. In on-policy RL, the agent's error patterns shift over time, causing stationary critics to become stale and providing feedback of diminishing utility. To address this, we introduce ECHO (Evolving Critic for Hindsight-Guided Optimization)}, a framework that jointly optimizes the policy and critic through a synchronized co-evolutionary loop. ECHO utilizes a cascaded rollout mechanism where the critic generates multiple diagnoses for an initial trajectory, followed by policy refinement to enable group-structured advantage estimation. We address the challenge of learning plateaus via a saturation-aware gain shaping objective, which rewards the critic for inducing incremental improvements in high-performing trajectories. By employing dual-track GRPO updates, ECHO ensures the critic's feedback stays synchronized with the evolving policy. Experimental results show that ECHO yields more stable training and higher long-horizon task success across open-world environments.

Related papers

• IADD-TR: Intervention-Aware Dynamics Decoupling with Targeted Regularization for Model-Based Reinforcement Learning [57.16513298507272]
  We propose IADD-TR, a unified framework combining Intervention-Aware Dynamics Decoupling (IADD) and Targeted Regularization (TR)<n>IADD factorizes transitions into an action-intervention stage and an action-free natural evolution stage, using a zero-action anchor to resolve the non-uniqueness of this two-stage factorization for robust generalization.<n>For policy learning, we derive TR from the efficient influence function of a replay-state policy-gradient functional.
  arXiv  Detail & Related papers  (2026-08-11T08:20:02Z)
• Contrastive Reinforced Policy Optimization via Privileged Self-Distillation [23.840537431318296]
  We introduce Contrastive Reinforced Policy Optimization (CRPO), which reformulates agentic On-Policy Self-Distillation (OPSD) from a contrastive learning perspective.<n>CRPO consistently outperforms existing reinforcement learning and self-distillation baselines.
  arXiv  Detail & Related papers  (2026-07-30T11:14:11Z)
• Collaborative Weighting with Pessimistic Critic for Mitigating Overestimation in Off-Policy Reinforcement Learning [7.604367783364084]
  Collaborative Weighting Actor-Critic (CWAC) is a unified framework that accounts for predictive uncertainty in value estimation.<n>CWAC can be seamlessly integrated into existing off-policy algorithm frameworks with minimal overhead.
  arXiv  Detail & Related papers  (2026-07-29T06:18:19Z)
• VIMPO: Value-Implicit Policy Optimization for LLMs [106.88933849641272]
  Group-relative methods such as GRPO avoid training a critic, but typically assign a trajectory-level advantage to every token.<n>Actor-critic methods provide denser learning signals, but require a learned value function with its own training instability.<n>We introduce VIMPO, a critic-free policy optimization method that derives a policy-implied value function from optimality conditions of KL-regularized reinforcement learning.
  arXiv  Detail & Related papers  (2026-06-18T09:44:12Z)
• Learning from Failures: Correction-Oriented Policy Optimization with Verifiable Rewards [73.44333771806282]
  Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as an effective paradigm for improving the reasoning capabilities of large language models.<n>We propose Correction-Oriented Policy Optimization (CIPO), a simple and effective extension to RLVR that converts on-policy failed trajectories into correction-oriented supervision.<n>CIPO improves learning effectiveness while explicitly enhancing the model's ability to correct its own errors.
  arXiv  Detail & Related papers  (2026-05-14T08:22:21Z)
• EVPO: Explained Variance Policy Optimization for Adaptive Critic Utilization in LLM Post-Training [69.32453275232662]
  We show that a learned critic can inject estimation noise that exceeds the state signal it captures, increasing rather than reducing advantage variance.<n>We propose Explained Variance Policy Optimization (EVPO), which monitors batch-level EV at each training step and adaptively switches between critic-based and batch-mean advantage estimation.
  arXiv  Detail & Related papers  (2026-04-21T14:07:39Z)
• Hindsight-Anchored Policy Optimization: Turning Failure into Feedback in Sparse Reward Settings [7.554296968064274]
  We present Hindsight-Anchored Policy optimization (HAPO) for Reinforcement Learning with Verifiable Rewards (RLVR)<n>HAPO employs a hindsight mechanism that selectively anchors optimization to teacher demonstrations during failure.<n>We show that HAPO achieves textitasymptotic consistency: by naturally annealing the teacher signal as the policy improves, HAPO recovers the unbiased on-policy gradient.
  arXiv  Detail & Related papers  (2026-03-11T21:33:41Z)
• Experiential Reinforcement Learning [22.545003569634982]
  Experiential Reinforcement Learning (ERL) is a training paradigm that embeds an explicit experience-reflection-consolidation loop into the reinforcement learning process.<n>ERL consistently improves learning efficiency and final performance over strong reinforcement learning baselines.<n>These results suggest that integrating explicit self-reflection into policy training provides a practical mechanism for transforming feedback into durable behavioral improvement.
  arXiv  Detail & Related papers  (2026-02-15T01:23:48Z)
• Q-learning with Adjoint Matching [58.78551025170267]
  We propose Q-learning with Adjoint Matching (QAM), a novel TD-based reinforcement learning (RL) algorithm.<n>QAM sidesteps two challenges by leveraging adjoint matching, a recently proposed technique in generative modeling.<n>It consistently outperforms prior approaches on hard, sparse reward tasks in both offline and offline-to-online RL.
  arXiv  Detail & Related papers  (2026-01-20T18:45:34Z)
• Generative Actor Critic [74.04971271003869]
  Generative Actor Critic (GAC) is a novel framework that decouples sequential decision-making by reframing textitpolicy evaluation as learning a generative model of the joint distribution over trajectories and returns.<n>Experiments on Gym-MuJoCo and Maze2D benchmarks demonstrate GAC's strong offline performance and significantly enhanced offline-to-online improvement compared to state-of-the-art methods.
  arXiv  Detail & Related papers  (2025-12-25T06:31:11Z)
• M-GRPO: Stabilizing Self-Supervised Reinforcement Learning for Large Language Models with Momentum-Anchored Policy Optimization [9.358876832727239]
  Self-supervised reinforcement learning (RL) presents a promising approach for enhancing the reasoning capabilities of Large Language Models (LLMs)<n>We find that existing methods suffer from a critical failure mode under long-horizon training: a "policy collapse" where performance precipitously degrades.<n>We introduce M-GRPO, a framework that leverages a slowly evolving momentum model to provide a stable training target.<n>We also propose an adaptive filtering method based on the interquartile range (IQR) that dynamically prunes low-entropy trajectories.
  arXiv  Detail & Related papers  (2025-12-15T08:07:23Z)
• CriticSearch: Fine-Grained Credit Assignment for Search Agents via a Retrospective Critic [24.371889836599138]
  CriticSearch is a fine-grained credit-assignment framework that supplies dense, turn-level feedback via a retrospective critic mechanism.<n> Experimental results across diverse multi-hop reasoning benchmarks demonstrate that CriticSearch consistently outperforms existing baselines.
  arXiv  Detail & Related papers  (2025-11-15T11:06:57Z)
• Critique-RL: Training Language Models for Critiquing through Two-Stage Reinforcement Learning [89.60378227969643]
  We propose Critique-RL, an online RL approach for developing critiquing language models without stronger supervision.<n>Our approach operates on a two-player paradigm: the actor generates a response, the critic provides feedback, and the actor refines the response accordingly.<n>Experiments across various tasks and models show that Critique-RL delivers substantial performance improvements.
  arXiv  Detail & Related papers  (2025-10-28T11:37:01Z)
• BAPO: Stabilizing Off-Policy Reinforcement Learning for LLMs via Balanced Policy Optimization with Adaptive Clipping [69.74252624161652]
  We propose BAlanced Policy Optimization with Adaptive Clipping (BAPO)<n>BAPO dynamically adjusts clipping bounds to adaptively re-balance positive and negative contributions, preserve entropy, and stabilize RL optimization.<n>On AIME 2024 and AIME 2025 benchmarks, our 7B BAPO model surpasses open-source counterparts such as SkyWork-OR1-7B.
  arXiv  Detail & Related papers  (2025-10-21T12:55:04Z)
• Training Language Model to Critique for Better Refinement [58.73039433159486]
  We introduce textbfRefinement-oriented textbfCritique textbfOptimization (RCO), a novel framework designed to train critic models using refinement signals.<n>RCO uses a feedback loop where critiques, generated by the critic model, guide the actor model in refining its responses.<n>By focusing on critiques that lead to better refinements, RCO eliminates the need for direct critique preference assessment.
  arXiv  Detail & Related papers  (2025-06-27T12:10:57Z)
• The Actor-Critic Update Order Matters for PPO in Federated Reinforcement Learning [10.727328530242461]
  We propose FedRAC, which reverses the update order (actor first, then critic) to eliminate the divergence of critics from different clients.<n> Empirical results indicate that the proposed algorithm obtains higher cumulative rewards and converges more rapidly in five experiments.
  arXiv  Detail & Related papers  (2025-06-02T02:20:22Z)
• DisCO: Reinforcing Large Reasoning Models with Discriminative Constrained Optimization [50.91849555841057]
  Group Relative Policy Optimization is a reinforcement learning method for large reasoning models (LRMs)<n>We introduce a new Discriminative Constrained Optimization framework for reinforcing LRMs, grounded in the principle of discriminative learning.<n>DisCO significantly outperforms GRPO and its improved variants such as DAPO, achieving average gains of 7% over GRPO and 6% over DAPO.
  arXiv  Detail & Related papers  (2025-05-18T11:08:32Z)
• Self-Evolving Critique Abilities in Large Language Models [59.861013614500024]
  This paper explores enhancing critique abilities of Large Language Models (LLMs)<n>We introduce SCRIT, a framework that trains LLMs with self-generated data to evolve their critique abilities.<n>Our analysis reveals that SCRIT's performance scales positively with data and model size.
  arXiv  Detail & Related papers  (2025-01-10T05:51:52Z)
• Dynamic Learning Rate for Deep Reinforcement Learning: A Bandit Approach [2.743898388459522]
  In deep Reinforcement Learning (RL), the learning rate critically influences both stability and performance, yet its optimal value shifts during training as the environment and policy evolve.<n>Standard decay schedulers assume monotonic convergence and often misalign with these dynamics, leading to premature or delayed adjustments.<n>We introduce LRRL, a meta-learning approach that dynamically selects the learning rate based on policy performance rather than training steps.
  arXiv  Detail & Related papers  (2024-10-16T14:15:28Z)

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.