DHRCL:Training Code LLMs with Dense Hierarchical Rewards and Curriculum Learning

• URL: http://arxiv.org/abs/2607.26457v2
• Date: Tue, 04 Aug 2026 08:18:00 GMT
• Title: DHRCL:Training Code LLMs with Dense Hierarchical Rewards and Curriculum Learning
• Abstract summary: We propose DHRCL, a reinforcement learning framework with Dense Hierarchical Rewards and Curriculum Learning.<n>DHRCL decomposes feedback into syntax validation, execution success, unit-test pass rate, and AST-based structural similarity.<n>We evaluate DHRCL across Qwen3-4B, Qwen3-8B, and Qwen3-14B backbones, showing that its advantage remains consistent as model capacity increases.
• Score: 15.421698703970167
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Reinforcement learning is a natural post-training paradigm for code-oriented large language models because generated programs can be evaluated through parsing, execution, unit tests, and structural analysis. However, existing methods often rely on sparse outcome rewards or statically combine heterogeneous dense signals, even though syntax validity, executability, functional correctness, and structural organization describe different and progressively dependent programming capabilities. We propose DHRCL, a reinforcement learning framework with Dense Hierarchical Rewards and Curriculum Learning. DHRCL decomposes feedback into syntax validation, execution success, unit-test pass rate, and AST-based structural similarity, and organizes these signals through a three-stage Syntax, Execution, Pass & Structural curriculum. Stage duration is determined automatically from recent validation trends rather than manually specified capability thresholds. We further introduce stage-aware probability-based token credit redistribution. The mechanism follows a consolidation-to-refinement principle: it emphasizes established token patterns during syntax-oriented optimization, applies uniform propagation for non-local execution feedback, and allocates more credit or blame to less-established token decisions during final functional optimization. Under a unified Qwen3-8B and KodCode protocol, the experiments compare DHRCL with binary, pass-rate, reward-model-based, and verifiable dense-reward baselines. We further evaluate DHRCL across Qwen3-4B, Qwen3-8B, and Qwen3-14B backbones, showing that its advantage remains consistent as model capacity increases.

Related papers

• Weave of Formal Thought [51.56484100374058]
  We introduce Weave of Formal Thought (WoFT), a paradigm uniting rigorous syntactic validation with learned structural representations.<n>We present a latent-variable fine-tuning method training the language model to interleave non-terminal grammar symbols directly into generation.<n>For Python, fine-tuning StarCoder2-3B with our RWS objective reduces per-token cross-entropy by 14.3% relative to a text-only SFT baseline.
  arXiv  Detail & Related papers  (2026-06-24T15:58:11Z)
• From Holistic Evaluation to Structured Criteria: Rubrics Across the Evolving LLM Landscape [79.30826980815927]
  rubrics are explicit criteria sets that transform complex quality judgments into structured and actionable standards.<n>We systematically organize existing rubric designs, examine their construction and optimization, and analyze their role across evaluation and training.
  arXiv  Detail & Related papers  (2026-06-07T13:34:55Z)
• Prism: Efficient Test-Time Scaling via Hierarchical Search and Self-Verification for Discrete Diffusion Language Models [96.0074341403456]
  Inference-time compute has re-emerged as a practical way to improve LLM reasoning.<n>Most test-time scaling (TTS) algorithms rely on autoregressive decoding.<n>We propose Prism, an efficient TTS framework for dLLMs.
  arXiv  Detail & Related papers  (2026-02-02T09:14:51Z)
• Graph Reasoning Paradigm: Structured and Symbolic Reasoning with Topology-Aware Reinforcement Learning for Large Language Models [45.28250076657801]
  Long Chain-of-Thought (LCoT) has proven effective in enhancing the reasoning capabilities of Large Language Models (LLMs)<n>Despite RLVR-based optimization, existing methods still suffer from coarse-grained supervision, reward hacking, high training costs, and poor generalization.<n>We propose the Graph Reasoning Paradigm (GRP), which realizes structured and symbolic reasoning, implemented via graph-structured representations with step-level cognitive labels.
  arXiv  Detail & Related papers  (2026-01-19T12:23:00Z)
• SCRIBE: Structured Mid-Level Supervision for Tool-Using Language Models [10.04930078540686]
  SCRIBE is a reinforcement learning framework that intervenes at a novel mid-level abstraction.<n>It achieves state-of-the-art performance across a range of reasoning and tool-use benchmarks.
  arXiv  Detail & Related papers  (2026-01-07T03:49:48Z)
• BRIDGE: Building Representations In Domain Guided Program Verification [67.36686119518441]
  BRIDGE decomposes verification into three interconnected domains: Code, Specifications, and Proofs.<n>We show that this approach substantially improves both accuracy and efficiency beyond standard error feedback methods.
  arXiv  Detail & Related papers  (2025-11-26T06:39:19Z)
• CoT Referring: Improving Referring Expression Tasks with Grounded Reasoning [67.18702329644526]
  CoT Referring enhances model reasoning across modalities through a structured, chain-of-thought training data structure.<n>We restructure the training data to enforce a new output form, providing new annotations for existing datasets.<n>We also integrate detection and segmentation capabilities into a unified MLLM framework, training it with a novel adaptive weighted loss to optimize performance.
  arXiv  Detail & Related papers  (2025-10-03T08:50:21Z)
• Post-Completion Learning for Language Models [20.589364712188015]
  Current language model training paradigms terminate learning upon reaching the end-of-sequence (eos>) token.<n>We propose Post-Completion Learning (PCL), a novel training framework that systematically utilizes the sequence space after model output completion.<n>PCL enables models to continue generating self-assessments and reward predictions during training, while maintaining efficient inference by stopping at the completion point.
  arXiv  Detail & Related papers  (2025-07-27T12:47:26Z)
• Enhancing Spatial Reasoning in Vision-Language Models via Chain-of-Thought Prompting and Reinforcement Learning [0.42855555838080844]
  This study investigates the spatial reasoning capabilities of vision-language models (VLMs) through Chain-of-Thought prompting and reinforcement learning.<n>We find that simple CoT formats, where the model generates a reasoning step before the answer, can harm the model's original performance.<n>In contrast, structured multi-stage prompting based on scene graphs (SceneGraph CoT) significantly improves spatial reasoning accuracy.
  arXiv  Detail & Related papers  (2025-07-06T10:51:12Z)
• SCOUT: Teaching Pre-trained Language Models to Enhance Reasoning via Flow Chain-of-Thought [37.53215651690168]
  Chain of Thought (CoT) prompting improves the reasoning performance of large language models (LLMs) by encouraging step by step thinking.<n>While promising, CoT-based approaches often require costly pretraining and lack a principled framework for how reasoning should evolve.<n>We propose SCOUT, a lightweight fine tuning framework that enables Flow CoT style reasoning without the need for pretraining.
  arXiv  Detail & Related papers  (2025-05-30T03:43:24Z)
• Scalable Learning of Latent Language Structure With Logical Offline Cycle Consistency [71.42261918225773]
  Conceptually, LOCCO can be viewed as a form of self-learning where the semantic being trained is used to generate annotations for unlabeled text. As an added bonus, the annotations produced by LOCCO can be trivially repurposed to train a neural text generation model.
  arXiv  Detail & Related papers  (2023-05-31T16:47:20Z)

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.