Learning How to Use Tools, Not Just When: Pattern-Aware Tool-Integrated Reasoning
Tool-integrated reasoning (TIR) has become a key approach for improving large reasoning models (LRMs) on complex problems. Prior work has mainly studied when to invoke tools, while overlooking how tools are applied. We identify two common patterns: a calculator pattern that uses code for direct computation, and an algorithmic pattern that encodes problems as programs. Misaligned choices often cause failures even when reasoning is sound. We propose a two-stage framework that first builds code competence from both patterns and then aligns pattern selection with teacher preferences. Across challenging math datasets, our pattern-aware method substantially improves both code usage and accuracy, for instance raising Code@1 on MATH500 from 64.0% to 70.5% and on AIME24 from 26.7% to 50.0%. These gains highlight the effectiveness of a pattern-aware approach for tool-integrated reasoning.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
AdaTIR: Adaptive Tool-Integrated Reasoning via Difficulty-Aware Policy Optimization
Tool-Integrated Reasoning (TIR) has significantly enhanced the capabilities of Large Language Models (LLMs), yet current agents tend to exhibit cognitive offloading, redundantly invoking external tools even for simple ta…
SMART: Self-Aware Agent for Tool Overuse Mitigation
Current Large Language Model (LLM) agents demonstrate strong reasoning and tool use capabilities, but often lack self-awareness, failing to balance these approaches effectively. This imbalance leads to Tool Overuse, wher…
GSM8KLarge Language ModelAdaTooler-V: Adaptive Tool-Use for Images and Videos
Recent advances have shown that multimodal large language models (MLLMs) benefit from multimodal interleaved chain-of-thought (CoT) with vision tool interactions. However, existing open-source models often exhibit blind …
Reinforcement LearningVisual ReasoningWhen Lower Privileges Suffice: Investigating Over-Privileged Tool Selection in LLM Agents
As LLM agents increasingly select tools autonomously, their choices among tools with different privileges become safety-relevant. However, prior tool-selection studies focus on safety-agnostic metadata preferences, leavi…
How do "technical" design-choices made when building algorithmic decision-making tools for criminal justice authorities create constitutional dangers?
This two part paper argues that seemingly "technical" choices made by developers of machine-learning based algorithmic tools used to inform decisions by criminal justice authorities can create serious constitutional dang…
Decision Making