TInR: Exploring Tool-Internalized Reasoning in Large Language Models
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866916070251560960 |
|---|---|
| author | Xu, Qiancheng Li, Yongqi Liu, Fan Wang, Hongru Yang, Min Li, Wenjie |
| author_facet | Xu, Qiancheng Li, Yongqi Liu, Fan Wang, Hongru Yang, Min Li, Wenjie |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_10788 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | TInR: Exploring Tool-Internalized Reasoning in Large Language Models Xu, Qiancheng Li, Yongqi Liu, Fan Wang, Hongru Yang, Min Li, Wenjie Computation and Language Artificial Intelligence 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. |
| title | TInR: Exploring Tool-Internalized Reasoning in Large Language Models |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2604.10788 |