ReflexiCoder: Teaching Large Language Models to Self-Reflect on Generated Code and Self-Correct It via Reinforcement Learning

• URL: http://arxiv.org/abs/2603.05863v1
• Date: Fri, 06 Mar 2026 03:38:17 GMT
• Title: ReflexiCoder: Teaching Large Language Models to Self-Reflect on Generated Code and Self-Correct It via Reinforcement Learning
• Abstract summary: Existing iterative refinement strategies rely on external oracles, execution feedback, or computationally expensive prompt-response cycles.<n>We propose ReflexiCoder, a novel reinforcement learning (RL) framework that internalizes the structured reasoning trajectory.<n>Our framework is significantly more token-efficient than base models, reducing inference-time compute overhead by approximately 40%.
• Score: 17.115542346570972
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: While Large Language Models (LLMs) have revolutionized code generation, standard "System 1" approaches, generating solutions in a single forward pass, often hit a performance ceiling when faced with complex algorithmic tasks. Existing iterative refinement strategies attempt to bridge this gap at inference time, yet they predominantly rely on external oracles, execution feedback, or computationally expensive prompt-response cycles. In this work, we propose ReflexiCoder, a novel reinforcement learning (RL) framework that internalizes the structured reasoning trajectory, encompassing initial generation, bug and optimization aware reflection, and self-correction, directly into the model's weights. Unlike prior methods, ReflexiCoder shifts the paradigm from external-dependent refinement to an intrinsic, fully autonomous self-reflection and self-correction capabilities at inference time. We utilize an RL-zero training paradigm with granular reward functions to optimize the entire reflection-correction trajectory, teaching the model how to debug without reliance on ground-truth feedback or execution engines at inference time. Extensive experiments across seven benchmarks demonstrate that our ReflexiCoder-8B establishes a new state-of-the-art (SOTA) among leading open-source models in the 1.5B-14B range, achieving 94.51% (87.20%) on HumanEval (Plus), 81.80% (78.57%) on MBPP (Plus), 35.00% on BigCodeBench, 52.21% on LiveCodeBench, and 37.34% on CodeForces in a single-attempt setting, rivaling or surpassing proprietary models like GPT-5.1. Notably, our framework is significantly more token-efficient than base models, reducing inference-time compute overhead by approximately 40% through disciplined, high-speed reasoning and reflection patterns. Source code is available at https://github.com/juyongjiang/ReflexiCoder.

Related papers

• Teaching Large Reasoning Models Effective Reflection [62.73646680747003]
  Large Reasoning Models (LRMs) have recently shown impressive performance on complex reasoning tasks.<n>However, not all reflections are beneficial-many are superficial, offering little to no improvement over the original answer.<n>We first propose Self-Critique Fine-Tuning (SCFT), a training framework that enhances the model's reflective reasoning ability using only self-generated critiques.
  arXiv  Detail & Related papers  (2026-01-19T04:51:53Z)
• Revolutionizing Reinforcement Learning Framework for Diffusion Large Language Models [49.911784762244814]
  TraceRL is a trajectory-aware reinforcement learning framework for diffusion language models (DLMs)<n>We derive a series of state-of-the-art diffusion language models, namely TraDo.<n>TraDo-8B-Instruct achieves relative accuracy improvements of 6.1% over Qwen2.5-7B-Instruct and 51.3% over Llama3.1-8B-Instruct on mathematical reasoning benchmarks.
  arXiv  Detail & Related papers  (2025-09-08T17:58:06Z)
• Temporal Self-Rewarding Language Models: Decoupling Chosen-Rejected via Past-Future [38.1810626252963]
  Self-Rewarding Language Models propose an architecture in which the Large Language Models(LLMs) both generates responses and evaluates its own outputs via LLM-as-a-Judge prompting.<n>We propose textbf Self-Rewarding Language Models that strategically coordinate past, present, and future model generations to sustain learning signals.
  arXiv  Detail & Related papers  (2025-08-08T05:25:54Z)
• Efficient Reasoning for Large Reasoning Language Models via Certainty-Guided Reflection Suppression [30.653381666162275]
  Certainty-Guided Reflection Suppression (CGRS) is a novel method that mitigates overthinking in Large Reasoning Language Models (LRLMs)<n>CGRS operates by dynamically suppressing the model's generation of reflection triggers when it exhibits high confidence in its current response.<n>Our approach is model-agnostic, requires no retraining or architectural modifications, and can be integrated seamlessly with existing autoregressive generation pipelines.
  arXiv  Detail & Related papers  (2025-08-07T12:38:22Z)
• Teaching LLM to Reason: Reinforcement Learning from Algorithmic Problems without Code [76.80306464249217]
  We propose TeaR, which aims at teaching LLMs to reason better.<n>TeaR leverages careful data curation and reinforcement learning to guide models in discovering optimal reasoning paths through code-related tasks.<n>We conduct extensive experiments using two base models and three long-CoT distillation models, with model sizes ranging from 1.5 billion to 32 billion parameters, and across 17 benchmarks spanning Math, Knowledge, Code, and Logical Reasoning.
  arXiv  Detail & Related papers  (2025-07-10T07:34:05Z)
• 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)
• Aligning Frozen LLMs by Reinforcement Learning: An Iterative Reweight-then-Optimize Approach [65.6966065843227]
  Iterative Reweight-then-IRO is a framework that performs RL-style alignment of a frozen base model without touching its parameters.<n>At test time, the value functions are used to guide the base model generation via a search-based optimization process.<n> Notably, users can apply IRO to align a model on their own dataset, similar to OpenAI's reinforcement fine-tuning (RFT)
  arXiv  Detail & Related papers  (2025-06-21T21:49:02Z)
• Co-Evolving LLM Coder and Unit Tester via Reinforcement Learning [48.66688117533318]
  We propose CURE, a novel reinforcement learning framework with a dedicated reward design.<n>CURE co-evolves coding and unit test generation capabilities based on their interaction outcomes.<n>We find that our model can serve as an effective reward model for reinforcement learning on base models.
  arXiv  Detail & Related papers  (2025-06-03T17:58:42Z)
• ReTool: Reinforcement Learning for Strategic Tool Use in LLMs [27.07998056454784]
  ReTool enhances long-form reasoning with tool-integrated learning.<n>Model achieves 67% accuracy with 400 training steps.<n>Remarkably, ReTool-32B attains 72.5% accuracy in extended settings.
  arXiv  Detail & Related papers  (2025-04-15T18:10:22Z)
• SPaR: Self-Play with Tree-Search Refinement to Improve Instruction-Following in Large Language Models [88.29990536278167]
  We introduce SPaR, a self-play framework integrating tree-search self-refinement to yield valid and comparable preference pairs.<n>Our experiments show that a LLaMA3-8B model, trained over three iterations guided by SPaR, surpasses GPT-4-Turbo on the IFEval benchmark without losing general capabilities.
  arXiv  Detail & Related papers  (2024-12-16T09:47:43Z)

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.