Toward Effective Tool-Integrated Reasoning via Self-Evolved Preference Learning
Tool-Integrated Reasoning (TIR) enables large language models (LLMs) to improve their internal reasoning ability by integrating external tools. However, models employing TIR often display suboptimal behaviors, such as insufficient or excessive tool usage and overthinking after tool calls. The challenge of incentivizing LLMs to perform TIR efficiently and accurately, while stabilizing the reasoning process, remains an open question. In this paper, we start by exploring the impact of tool calls on model reasoning from the perspective of information entropy. Our findings indicate that tool call results lead to a distinct change in the information entropy of subsequent reasoning, with the overall entropy of the reasoning chain varying based on the number of tool calls. Building on these insights, we propose Tool-Light, a framework designed to encourage LLMs to perform TIR efficiently and accurately. Our framework includes dataset construction and multi-stage fine-tuning. For dataset construction, we employ continuous self-evolved sampling using the fine-tuned model, integrating both vanilla sampling and entropy-guided sampling. Besides, we establish strict criteria for selecting positive-negative pairs during sampling. The training process involves a two-stage approach, comprising Supervised Fine-Tuning (SFT) and Self-Evolved Direct Preference Optimization (DPO). Experimental results on 10 datasets demonstrate the effectiveness of Tool-Light, significantly improving the model's efficiency in executing TIR tasks.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Agent0-VL: Exploring Self-Evolving Agent for Tool-Integrated Vision-Language Reasoning
Vision-language agents have achieved remarkable progress in a variety of multimodal reasoning tasks; however, their learning remains constrained by the limitations of human-annotated supervision. Recent self-rewarding ap…
Reinforcement LearningMultimodal ReasoningVisual ReasoningToRL: Scaling Tool-Integrated RL
We introduce ToRL (Tool-Integrated Reinforcement Learning), a framework for training large language models (LLMs) to autonomously use computational tools via reinforcement learning. Unlike supervised fine-tuning, ToRL al…
Mathreinforcement-learningReinforcement LearningHybrid Retriever Evolution for Multimodal Document Reasoning Agents
Different retrievers, including lexical, semantic, and multimodal approaches, provide highly complementary strengths for multimodal document understanding, yet most systems combine them through fixed pipelines that canno…
Question AnsweringDeepTool: Scaling Interleaved Deliberation in Tool-Integrated Reasoning via Process-Supervised Reinforcement Learning
Tool-Integrated Reasoning (TIR) extends LLM capabilities by leveraging external environments. However, existing methods lack the deliberation during sequential tool invocation required for strategic planning and self-cor…
Reinforcement LearningTool-Star: Empowering LLM-Brained Multi-Tool Reasoner via Reinforcement Learning
Recently, large language models (LLMs) have shown remarkable reasoning capabilities via large-scale reinforcement learning (RL). However, leveraging the RL algorithm to empower effective multi-tool collaborative reasonin…
Reinforcement Learning (RL)