TInR: Exploring Tool-Internalized Reasoning in Large Language Models

arXiv:2604.10788v1 Announce Type: cross Abstract: Tool-Integrated Reasoning (TIR) has emerged as a promising direction by extending Large Language Models' (LLMs) capabilities with external tools during reasoning. Existing TIR methods typically rely on external tool documentation during reasoning. However, this leads to tool mastery difficulty, tool size constraints, and inference inefficiency. To mitigate these issues, we explore Tool-Internalized Reasoning (TInR), aiming at facilitating reasoning with tool knowledge internalized into LLMs. Achieving this goal presents notable requirements, including tool internalization and tool-reasoning coordination. To address them, we propose TInR-U, a tool-internalized reasoning framework for unified reasoning and tool usage. TInR-U is trained through a three-phase pipeline: 1) tool internalization with a bidirectional knowledge alignment strategy; 2) supervised fine-tuning warm-up using high-quality reasoning annotations, and 3) reinforcement learning with TInR-specific rewards. We comprehensively evaluate our method across in-domain and out-of-domain settings. Experiment results show that TInR-U achieves superior performance in both settings, highlighting its effectiveness and efficiency.

Related

• E3-TIR: Enhanced Experience Exploitation for Tool-Integrated Reasoning
• Do LLMs Know Tool Irrelevance? Demystifying Structural Alignment Bias in Tool Invocations
• Rethinking Token-Level Credit Assignment in RLVR: A Polarity-Entropy Analysis
• A Comparative Theoretical Analysis of Entropy Control Methods in Reinforcement Learning
• SPPO: Sequence-Level PPO for Long-Horizon Reasoning Tasks

Source: arXiv cs.AI | 2026-04-14