Reinforcement Learning-Guided Chain-of-Draft for Token-Efficient Code Generation

• URL: http://arxiv.org/abs/2509.25243v1
• Date: Fri, 26 Sep 2025 08:40:17 GMT
• Title: Reinforcement Learning-Guided Chain-of-Draft for Token-Efficient Code Generation
• Authors: Xunzhu Tang, Iyiola Emmanuel Olatunji, Tiezhu Sun, Jacques Klein, Tegawende F. Bissyande,
• Abstract summary: LLMs demonstrate surface-level fluency in code generation but struggle with structured reasoning tasks.<n>We propose multicod, a reinforcement learning framework that learns to select the most promising candidate from CoD-generated solutions.
• Score: 7.69951622965475
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: LLMs demonstrate surface-level fluency in code generation but struggle with structured reasoning tasks requiring correctness and semantic alignment. While Chain-of-Thought (CoT) prompting enhances reasoning through intermediate steps, it suffers from verbosity and inefficiency. Chain-of-Draft (CoD) prompting offers more concise reasoning, but the stochastic nature of LLMs produces varying solution quality, making optimal selection challenging. We propose \multicod, a reinforcement learning framework that learns to select the most promising candidate from CoD-generated solutions. Our approach uses strategy-guided prompting to encourage diverse reasoning styles and models solution selection as a contextual bandit problem. The framework optimizes interpretable features including code complexity, reasoning structure, and strategic metadata through a reward function balancing correctness, efficiency, and clarity. Experiments on MBPP, BigCodeBench, SWE-bench Verified, and Defects4J show \multicod~outperforms and in some cases, on par with standard prompting, CoT, and CoD baselines while achieving cost and token efficiency from the user's perspective through a multi-candidate design that charges only for the selected output, reducing user billing by over 50\% and improving LLM response quality, making \multicod~more sustainable and scalable for real-world deployment. Our code is available: https://anonymous.4open.science/r/MultiCoD.

Related papers

• $\ abla$-Reasoner: LLM Reasoning via Test-Time Gradient Descent in Latent Space [71.23672814629448]
  $nabla$-Reasoner is an iterative generation framework that integrates differentiable optimization over token logits into the decoding loop.<n>$nabla$-Reasoner achieves over 20% accuracy improvement on a challenging mathematical reasoning benchmark.
  arXiv  Detail & Related papers  (2026-03-05T08:42:54Z)
• Reasoning in a Combinatorial and Constrained World: Benchmarking LLMs on Natural-Language Combinatorial Optimization [28.52469449694436]
  Large language models (LLMs) have shown strong performance in math and logic reasoning.<n>But their ability to handle systematic optimization (CO) remains underexplored.<n>We introduce NLCO, a benchmark that evaluates LLMs on end-to-end CO reasoning.
  arXiv  Detail & Related papers  (2026-02-02T14:55:48Z)
• Latent Chain-of-Thought for Visual Reasoning [53.541579327424046]
  Chain-of-thought (CoT) reasoning is critical for improving the interpretability and reliability of Large Vision-Language Models (LVLMs)<n>We reformulate reasoning in LVLMs as posterior inference and propose a scalable training algorithm based on amortized variational inference.<n>We empirically demonstrate that the proposed method enhances the state-of-the-art LVLMs on seven reasoning benchmarks.
  arXiv  Detail & Related papers  (2025-10-27T23:10:06Z)
• Optimizing Prompt Sequences using Monte Carlo Tree Search for LLM-Based Optimization [20.44067161623662]
  Large language models (LLMs) have demonstrated remarkable capabilities in code generation and structured reasoning.<n>We propose a novel neural-symbolic framework that formulates prompt selection as a sequential decision process guided by Monte Carlo Tree Search.<n>Our method explores and refines multi-step prompt sequences for the goal of improving code generation quality.
  arXiv  Detail & Related papers  (2025-08-08T04:01:24Z)
• 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)
• AdaCoT: Pareto-Optimal Adaptive Chain-of-Thought Triggering via Reinforcement Learning [30.265984245328124]
  Chain-of-Thought prompting indiscriminately generates lengthy reasoning steps for all queries.<n>AdaCoT (Adaptive Chain-of-Thought) is a novel framework enabling LLMs to adaptively decide when to invoke CoT.<n>A key technical contribution is Selective Loss Masking (SLM), designed to counteract decision boundary collapse.
  arXiv  Detail & Related papers  (2025-05-17T08:27:00Z)
• Uncertainty-Guided Chain-of-Thought for Code Generation with LLMs [45.33160999781074]
  Chain-of-Thought (CoT) reasoning has been demonstrated as an effective technique for improving the problem-solving capabilities of large language models (LLMs)<n>We introduce UnCert-CoT, an approach designed to enhance code generation by incorporating an uncertainty-aware CoT reasoning mechanism.
  arXiv  Detail & Related papers  (2025-03-19T15:40:45Z)
• Robust Multi-Objective Controlled Decoding of Large Language Models [14.58153072993207]
  We introduce Robust Multi-Objective Decoding (RMOD), a novel inference-time algorithm that optimize for improving worst-case rewards.<n>RMOD formalizes the robust decoding problem as a maximin two-player game between reward weights and the sampling policy.<n>We show that the game reduces to a convex optimization problem to find the worst-case weights, while the best response policy can be computed analytically.
  arXiv  Detail & Related papers  (2025-03-11T18:15:26Z)
• SoftCoT: Soft Chain-of-Thought for Efficient Reasoning with LLMs [48.28847964704554]
  Chain-of-Thought (CoT) reasoning enables Large Language Models (LLMs) to solve complex reasoning tasks.<n>We propose a novel approach for continuous-space reasoning that does not require modifying the LLM.
  arXiv  Detail & Related papers  (2025-02-17T18:52:29Z)
• 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)
• In-context Demonstration Matters: On Prompt Optimization for Pseudo-Supervision Refinement [71.60563181678323]
  Large language models (LLMs) have achieved great success across diverse tasks, and fine-tuning is sometimes needed to further enhance generation quality.<n>To handle these challenges, a direct solution is to generate high-confidence'' data from unsupervised downstream tasks.<n>We propose a novel approach, pseudo-supervised demonstrations aligned prompt optimization (PAPO) algorithm, which jointly refines both the prompt and the overall pseudo-supervision.
  arXiv  Detail & Related papers  (2024-10-04T03:39:28Z)
• Enhancing Chain-of-Thoughts Prompting with Iterative Bootstrapping in Large Language Models [81.01397924280612]
  Large language models (LLMs) can achieve highly effective performance on various reasoning tasks by incorporating step-by-step chain-of-thought (CoT) prompting as demonstrations. We introduce Iter-CoT (Iterative bootstrapping in Chain-of-Thoughts Prompting), an iterative bootstrapping approach for selecting exemplars and generating reasoning chains.
  arXiv  Detail & Related papers  (2023-04-23T13:54:39Z)

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.