RLAC: Reinforcement Learning with Adversarial Critic for Free-Form Generation Tasks

• URL: http://arxiv.org/abs/2511.01758v1
• Date: Mon, 03 Nov 2025 17:15:05 GMT
• Title: RLAC: Reinforcement Learning with Adversarial Critic for Free-Form Generation Tasks
• Authors: Mian Wu, Gavin Zhang, Sewon Min, Sergey Levine, Aviral Kumar,
• Abstract summary: Open-ended generation tasks require outputs to satisfy diverse and often implicit task-specific evaluation rubrics.<n>The sheer number of relevant rubrics leads to prohibitively high verification costs and incomplete assessments of a response.<n>We propose Reinforcement Learning with Adrial Critic (RLAC), a post-training approach that addresses these challenges via dynamic rubric verification.
• Score: 75.52891348667491
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Open-ended generation tasks require outputs to satisfy diverse and often implicit task-specific evaluation rubrics. The sheer number of relevant rubrics leads to prohibitively high verification costs and incomplete assessments of a response, making reinforcement learning (RL) post-training with rubric-based rewards difficult to scale. This problem is exacerbated by the fact that often the best way to combine these rubrics into one single reward is also highly prompt-specific. We propose Reinforcement Learning with Adversarial Critic (RLAC), a post-training approach that addresses these challenges via dynamic rubric verification. Our approach employs a large language model (LLM) as a critic that dynamically identifies only the most likely failure modes (e.g., a factual error or unhandled edge case), which are then verified by an external validator to optimize both generator and critic jointly. By training both the generator and the critic, this game enhances the critic's error detection and the generator's output quality while reducing required verifications. Our experiments demonstrate that RLAC improves factual accuracy in text generation and correctness in code generation, while also outperforming exhaustive verification and reward model methods. We show that dynamic critics are more effective than fixed critics, showcasing the potential of RLAC for scaling RL post-training to free-form generation tasks.

Related papers

• From Verifiable Dot to Reward Chain: Harnessing Verifiable Reference-based Rewards for Reinforcement Learning of Open-ended Generation [52.62655622099456]
  We propose reinforcement learning with verifiable reference-based rewards (RLVRR)<n>Instead of checking the final answer, RLVRR extracts an ordered linguistic signal from high-quality references (i.e., reward chain)<n>In this way, RLVRR decomposes rewards into two dimensions: content, which preserves deterministic core concepts, and style, which evaluates adherence to stylistic properties.
  arXiv  Detail & Related papers  (2026-01-26T14:39:58Z)
• 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)
• Beyond Binary Rewards: Training LMs to Reason About Their Uncertainty [59.97939500426759]
  This paper describes RLCR, an approach to training reasoning models that jointly improves accuracy and confidence estimation.<n>We show that across diverse datasets, RLCR substantially improves calibration with no loss in accuracy.<n>We also demonstrate that verbalized confidence can be leveraged at test time to improve accuracy and calibration.
  arXiv  Detail & Related papers  (2025-07-22T17:56:01Z)
• 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)
• Writing-Zero: Bridge the Gap Between Non-verifiable Tasks and Verifiable Rewards [11.149294285483782]
  We propose a unified RLVR-based training paradigm that bridges the gap between non-verifiable tasks and verifiable rewards.<n>We introduce a writing-principle-based pairwise Generative Reward Model (GenRM) and a novel Bootstrapped Relative Policy Optimization (BRPO) algorithm.<n>Our approach empowers LLMs to develop robust writing capabilities without supervised fine-tuning.
  arXiv  Detail & Related papers  (2025-05-30T14:34:57Z)
• Teaching Language Models to Critique via Reinforcement Learning [59.36253627145115]
  We show that critics trained with $textttCTRL$ significantly enhance pass rates and mitigate errors across both base and stronger generator models.<n>We also show that these critic models act as accurate generative reward models and enable test-time scaling through iterative critique-revision.
  arXiv  Detail & Related papers  (2025-02-05T02:18:46Z)
• Agent-R: Training Language Model Agents to Reflect via Iterative Self-Training [18.896813839389893]
  We propose an iterative self-training framework, Agent-R, that enables language Agent to Reflect on the fly.<n>Unlike traditional methods that reward or penalize actions based on correctness, Agent-R leverages MCTS to construct training data that recover correct trajectories from erroneous ones.<n>Our findings demonstrate that Agent-R continuously improves the model's ability to recover from errors and enables timely error correction.
  arXiv  Detail & Related papers  (2025-01-20T11:46:04Z)
• Can We Further Elicit Reasoning in LLMs? Critic-Guided Planning with Retrieval-Augmentation for Solving Challenging Tasks [68.49251303172674]
  State-of-the-art large language models (LLMs) exhibit impressive problem-solving capabilities but may struggle with complex reasoning and factual correctness. Existing methods harness the strengths of chain-of-thought and retrieval-augmented generation (RAG) to decompose a complex problem into simpler steps and apply retrieval to improve factual correctness. We introduce Critic-guided planning with Retrieval-augmentation, CR-Planner, a novel framework that leverages fine-tuned critic models to guide both reasoning and retrieval processes through planning.
  arXiv  Detail & Related papers  (2024-10-02T11:26:02Z)

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.