D-CORE: Incentivizing Task Decomposition in Large Reasoning Models for Complex Tool Use
Effective tool use and reasoning are essential capabilities for large reasoning models~(LRMs) to address complex real-world problems. Through empirical analysis, we identify that current LRMs lack the capability of sub-task decomposition in complex tool use scenarios, leading to Lazy Reasoning. To address this, we propose a two-stage training framework D-CORE~(\underline{\textbf{D}}ecomposing tasks and \underline{\textbf{Co}}mposing \underline{\textbf{Re}}asoning processes) that first incentivize the LRMs' task decomposition reasoning capability via self-distillation, followed by diversity-aware reinforcement learning~(RL) to restore LRMs' reflective reasoning capability. D-CORE achieves robust tool-use improvements across diverse benchmarks and model scales. Experiments on BFCLv3 demonstrate superiority of our method: D-CORE-8B reaches 77.7\% accuracy, surpassing the best-performing 8B model by 5.7\%. Meanwhile, D-CORE-14B establishes a new state-of-the-art at 79.3\%, outperforming 70B models despite being 5$\times$ smaller. The source code is available at https://github.com/alibaba/EfficientAI.
Code (0)
등록된 구현이 없습니다.
Tasks
Reinforcement LearningSimilar Papers 제목 키워드 기반
Incentivizing Reasoning for Advanced Instruction-Following of Large Language Models
Existing large language models (LLMs) face challenges of following complex instructions, especially when multiple constraints are present and organized in paralleling, chaining, and branching structures. One intuitive so…
Instruction FollowingReinforcement Learning (RL)Incentivizing Reasoning from Weak Supervision
Large language models (LLMs) have demonstrated impressive performance on reasoning-intensive tasks, but enhancing their reasoning abilities typically relies on either reinforcement learning (RL) with verifiable signals o…
reinforcement-learningReinforcement LearningReinforcement Learning (RL)ReVSeg: Incentivizing the Reasoning Chain for Video Segmentation with Reinforcement Learning
Reasoning-centric video object segmentation is an inherently complex task: the query often refers to dynamics, causality, and temporal interactions, rather than static appearances. Yet existing solutions generally collap…
Video Object SegmentationReinforcement LearningVideo SegmentationGraph-R1: Incentivizing the Zero-Shot Graph Learning Capability in LLMs via Explicit Reasoning
Generalizing to unseen graph tasks without task-pecific supervision remains challenging. Graph Neural Networks (GNNs) are limited by fixed label spaces, while Large Language Models (LLMs) lack structural inductive biases…
Reinforcement LearningGraph ClassificationNode ClassificationLink PredictionDistillation and Refinement of Reasoning in Small Language Models for Document Re-ranking
We present a novel approach for training small language models for reasoning-intensive document ranking that combines knowledge distillation with reinforcement learning optimization. While existing methods often rely on …
Document RankingInformation RetrievalKnowledge DistillationLanguage Modeling+4