RL Tango: Reinforcing Generator and Verifier Together for Language Reasoning

• URL: http://arxiv.org/abs/2505.15034v1
• Date: Wed, 21 May 2025 02:43:15 GMT
• Title: RL Tango: Reinforcing Generator and Verifier Together for Language Reasoning
• Authors: Kaiwen Zha, Zhengqi Gao, Maohao Shen, Zhang-Wei Hong, Duane S. Boning, Dina Katabi,
• Abstract summary: Tango is a novel framework that usesReinforcement learning to concurrently train both an LLM generator and a verifier.<n>A central innovation of Tango is its generative, process-level LLM verifier, which is trained via RL and co-evolves with the generator.<n>Experiments demonstrate that both components of Tango achieve state-of-the-art results among 7B/8B-scale models.
• Score: 26.95555634754465
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Reinforcement learning (RL) has recently emerged as a compelling approach for enhancing the reasoning capabilities of large language models (LLMs), where an LLM generator serves as a policy guided by a verifier (reward model). However, current RL post-training methods for LLMs typically use verifiers that are fixed (rule-based or frozen pretrained) or trained discriminatively via supervised fine-tuning (SFT). Such designs are susceptible to reward hacking and generalize poorly beyond their training distributions. To overcome these limitations, we propose Tango, a novel framework that uses RL to concurrently train both an LLM generator and a verifier in an interleaved manner. A central innovation of Tango is its generative, process-level LLM verifier, which is trained via RL and co-evolves with the generator. Importantly, the verifier is trained solely based on outcome-level verification correctness rewards without requiring explicit process-level annotations. This generative RL-trained verifier exhibits improved robustness and superior generalization compared to deterministic or SFT-trained verifiers, fostering effective mutual reinforcement with the generator. Extensive experiments demonstrate that both components of Tango achieve state-of-the-art results among 7B/8B-scale models: the generator attains best-in-class performance across five competition-level math benchmarks and four challenging out-of-domain reasoning tasks, while the verifier leads on the ProcessBench dataset. Remarkably, both components exhibit particularly substantial improvements on the most difficult mathematical reasoning problems. Code is at: https://github.com/kaiwenzha/rl-tango.

Related papers

• DiffuCoder: Understanding and Improving Masked Diffusion Models for Code Generation [68.19756761027351]
  Diffusion large language models (dLLMs) are compelling alternatives to autoregressive (AR) models.<n>We investigate their denoising processes and reinforcement learning methods.<n>Our work provides deeper insight into the machinery of dLLM generation and offers an effective, diffusion-native RL training framework.
  arXiv  Detail & Related papers  (2025-06-25T17:35:47Z)
• ReVeal: Self-Evolving Code Agents via Iterative Generation-Verification [6.983144806500892]
  ReVeal is a multi-turn reinforcement learning framework that interleaves code generation with explicit self-verification and tool-based evaluation.<n>It fosters the co-evolution of a model's generation and verification capabilities through RL training, expanding the reasoning boundaries of the base model.<n>It also enables test-time scaling into deeper inference regimes, with code consistently evolving as the number of turns increases during inference.
  arXiv  Detail & Related papers  (2025-06-13T03:41:04Z)
• VerIF: Verification Engineering for Reinforcement Learning in Instruction Following [55.60192044049083]
  Reinforcement learning with verifiable rewards (RLVR) has become a key technique for enhancing large language models (LLMs)<n>We propose VerIF, a verification method that combines rule-based code verification with LLM-based verification from a large reasoning model.<n>We apply RL training with VerIF to two models, achieving significant improvements across several representative instruction-following benchmarks.
  arXiv  Detail & Related papers  (2025-06-11T17:10:36Z)
• SeRL: Self-Play Reinforcement Learning for Large Language Models with Limited Data [65.56911325914582]
  We propose Self-play Reinforcement Learning (SeRL) to bootstrap Large Language Models (LLMs) training with limited initial data.<n>The proposed SeRL yields results superior to its counterparts and achieves performance on par with those obtained by high-quality data with verifiable rewards.
  arXiv  Detail & Related papers  (2025-05-25T13:28:04Z)
• Reinforced Latent Reasoning for LLM-based Recommendation [83.18146814163308]
  Large Language Models (LLMs) have demonstrated impressive reasoning capabilities in complex problem-solving tasks.<n>Existing methods typically rely on fine-tuning with explicit chain-of-thought (CoT) data.<n>In this work, we explore an alternative approach that shifts from explicit CoT reasoning to compact, information-dense latent reasoning.
  arXiv  Detail & Related papers  (2025-05-25T11:03:45Z)
• Agent RL Scaling Law: Agent RL with Spontaneous Code Execution for Mathematical Problem Solving [27.133677615587555]
  Large Language Models (LLMs) often struggle with mathematical reasoning tasks requiring precise, verifiable computation.<n>While Reinforcement Learning (RL) from outcome-based rewards enhances text-based reasoning, understanding how agents autonomously learn to leverage external tools like code execution remains crucial.
  arXiv  Detail & Related papers  (2025-05-12T17:23:34Z)
• OpenVLThinker: An Early Exploration to Complex Vision-Language Reasoning via Iterative Self-Improvement [91.88062410741833]
  This study investigates whether similar reasoning capabilities can be successfully integrated into large vision-language models (LVLMs)<n>We consider an approach that iteratively leverages supervised fine-tuning (SFT) on lightweight training data and Reinforcement Learning (RL) to further improve model generalization.<n>OpenVLThinker, a LVLM exhibiting consistently improved reasoning performance on challenging benchmarks such as MathVista, MathVerse, and MathVision, demonstrates the potential of our strategy for robust vision-language reasoning.
  arXiv  Detail & Related papers  (2025-03-21T17:52:43Z)
• Process Supervision-Guided Policy Optimization for Code Generation [15.943210767010045]
  Reinforcement learning (RL) with unit test feedback has enhanced large language models' (LLMs) code generation, but relies on sparse rewards provided only after complete code evaluation.<n>We propose a Process Reward Model (PRM) that delivers dense, line-level feedback on code correctness during generation, mimicking human code refinement.
  arXiv  Detail & Related papers  (2024-10-23T07:22:33Z)
• Improving LLM Reasoning through Scaling Inference Computation with Collaborative Verification [52.095460362197336]
  Large language models (LLMs) struggle with consistent and accurate reasoning. LLMs are trained primarily on correct solutions, reducing their ability to detect and learn from errors. We propose a novel collaborative method integrating Chain-of-Thought (CoT) and Program-of-Thought (PoT) solutions for verification.
  arXiv  Detail & Related papers  (2024-10-05T05:21:48Z)
• Generative Verifiers: Reward Modeling as Next-Token Prediction [29.543787728397643]
  We propose training verifiers using the ubiquitous next-token prediction objective, jointly on verification and solution generation.<n>Compared to standard verifiers, such generative verifiers (GenRM) can benefit from several advantages of LLMs.<n>We observe improvements of 28% $rightarrow$ 44.6% on MATH, and 37.9% $rightarrow$ 53.5% on MMLU abstract algebra.
  arXiv  Detail & Related papers  (2024-08-27T17:57:45Z)
• StepCoder: Improve Code Generation with Reinforcement Learning from Compiler Feedback [58.20547418182074]
  We introduce StepCoder, a novel framework for code generation, consisting of two main components. CCCS addresses the exploration challenge by breaking the long sequences code generation task into a Curriculum of Code Completion Subtasks. FGO only optimize the model by masking the unexecuted code segments to provide Fine-Grained Optimization. Our method improves the ability to explore the output space and outperforms state-of-the-art approaches in corresponding benchmarks.
  arXiv  Detail & Related papers  (2024-02-02T13:14:31Z)
• Prompt Optimization via Adversarial In-Context Learning [51.18075178593142]
  adv-ICL is implemented as a two-player game between a generator and a discriminator. The generator tries to generate realistic enough output to fool the discriminator. We show that adv-ICL results in significant improvements over state-of-the-art prompt optimization techniques.
  arXiv  Detail & Related papers  (2023-12-05T09:44:45Z)
• RLTF: Reinforcement Learning from Unit Test Feedback [17.35361167578498]
  Reinforcement Learning from Unit Test Feedback is a novel online RL framework with unit test feedback of multi-granularity for refining code LLMs. Our approach generates data in real-time during training and simultaneously utilizes fine-grained feedback signals to guide the model towards producing higher-quality code.
  arXiv  Detail & Related papers  (2023-07-10T05:18:18Z)
• Text Generation with Efficient (Soft) Q-Learning [91.47743595382758]
  Reinforcement learning (RL) offers a more flexible solution by allowing users to plug in arbitrary task metrics as reward. We introduce a new RL formulation for text generation from the soft Q-learning perspective. We apply the approach to a wide range of tasks, including learning from noisy/negative examples, adversarial attacks, and prompt generation.
  arXiv  Detail & Related papers  (2021-06-14T18:48:40Z)

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.