Bridging Online and Offline RL: Contextual Bandit Learning for Multi-Turn Code Generation

• URL: http://arxiv.org/abs/2602.03806v1
• Date: Tue, 03 Feb 2026 18:08:41 GMT
• Title: Bridging Online and Offline RL: Contextual Bandit Learning for Multi-Turn Code Generation
• Authors: Ziru Chen, Dongdong Chen, Ruinan Jin, Yingbin Liang, Yujia Xie, Huan Sun,
• Abstract summary: Multi-turn code generation can be formulated as a one-step recoverable Markov decision process.<n>Cobalt is a new method that combines the benefits of online and offline RL.<n>Our results demonstrate Cobalt as a promising solution for iterative decision-making tasks like code generation.
• Score: 60.14439536069839
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Recently, there have been significant research interests in training large language models (LLMs) with reinforcement learning (RL) on real-world tasks, such as multi-turn code generation. While online RL tends to perform better than offline RL, its higher training cost and instability hinders wide adoption. In this paper, we build on the observation that multi-turn code generation can be formulated as a one-step recoverable Markov decision process and propose contextual bandit learning with offline trajectories (Cobalt), a new method that combines the benefits of online and offline RL. Cobalt first collects code generation trajectories using a reference LLM and divides them into partial trajectories as contextual prompts. Then, during online bandit learning, the LLM is trained to complete each partial trajectory prompt through single-step code generation. Cobalt outperforms two multi-turn online RL baselines based on GRPO and VeRPO, and substantially improves R1-Distill 8B and Qwen3 8B by up to 9.0 and 6.2 absolute Pass@1 scores on LiveCodeBench. Also, we analyze LLMs' in-context reward hacking behaviors and augment Cobalt training with perturbed trajectories to mitigate this issue. Overall, our results demonstrate Cobalt as a promising solution for iterative decision-making tasks like multi-turn code generation. Our code and data are available at https://github.com/OSU-NLP-Group/cobalt.

Related papers

• Transitive RL: Value Learning via Divide and Conquer [54.190627631246166]
  Transitive Reinforcement Learning (TRL) is a new value learning algorithm based on a divide-and-conquer paradigm.<n>Unlike Monte Carlo methods, TRL suffers less from high variance as it performs dynamic programming.
  arXiv  Detail & Related papers  (2025-10-26T03:32:31Z)
• Scaling Offline RL via Efficient and Expressive Shortcut Models [13.050231036248338]
  offline reinforcement learning (RL) remains challenging due to the iterative nature of their noise sampling processes.<n>We introduce Scalable Offline Reinforcement Learning (SORL), a new offline RL algorithm that leverages shortcut models to scale both training and inference.<n>We demonstrate that SORL achieves strong performance across a range of offline RL tasks and exhibits positive scaling behavior with increased test-time compute.
  arXiv  Detail & Related papers  (2025-05-28T20:59:22Z)
• Unsupervised-to-Online Reinforcement Learning [59.910638327123394]
  Unsupervised-to-online RL (U2O RL) replaces domain-specific supervised offline RL with unsupervised offline RL. U2O RL not only enables reusing a single pre-trained model for multiple downstream tasks, but also learns better representations. We empirically demonstrate that U2O RL achieves strong performance that matches or even outperforms previous offline-to-online RL approaches.
  arXiv  Detail & Related papers  (2024-08-27T05:23:45Z)
• 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)
• 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)
• Dual RL: Unification and New Methods for Reinforcement and Imitation Learning [26.59374102005998]
  We first cast several state-of-the-art offline RL and offline imitation learning (IL) algorithms as instances of dual RL approaches with shared structures. We propose a new discriminator-free method ReCOIL that learns to imitate from arbitrary off-policy data to obtain near-expert performance. For offline RL, our analysis frames a recent offline RL method XQL in the dual framework, and we further propose a new method f-DVL that provides alternative choices to the Gumbel regression loss.
  arXiv  Detail & Related papers  (2023-02-16T20:10:06Z)
• Bootstrapped Transformer for Offline Reinforcement Learning [31.43012728924881]
  offline reinforcement learning (RL) aims at learning policies from previously collected static trajectory data without interacting with the real environment. Recent works provide a novel perspective by viewing offline RL as a generic sequence generation problem. We propose a novel algorithm named Bootstrapped Transformer, which incorporates the idea of bootstrapping and leverages the learned model to self-generate more offline data.
  arXiv  Detail & Related papers  (2022-06-17T05:57:47Z)
• RvS: What is Essential for Offline RL via Supervised Learning? [77.91045677562802]
  Recent work has shown that supervised learning alone, without temporal difference (TD) learning, can be remarkably effective for offline RL. In every environment suite we consider simply maximizing likelihood with two-layer feedforward is competitive. They also probe the limits of existing RvS methods, which are comparatively weak on random data.
  arXiv  Detail & Related papers  (2021-12-20T18:55:16Z)
• 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.