LLM Tool Use

LLM: Large Language Model

Follow this topic Ask about this topic

Momentum

30 papers in the last four weeks, up 233% on the four weeks before. 0.3% of all new papers.

Jul 13Week of Sep 28

Latest papers 185

All topics

When Tools Hurt LLM Reasoning: State-Dependent Belief Revision under External Evidence
Aug 21, 2025Yufeng Zhao, Junnan Liu, Hongwei Liu +4Belief Revision Knowledge Conflicts in Language Models
Shanghai Artificial Intelligence Laboratory · Department of Electronic Engineering, Tsinghua University · Beijing National Research Center for Information Science and Technology +2
Beyond Semantic Similarity: Reducing Unnecessary API Calls via Behavior-Aligned Retriever
Aug 20, 2025Yixin Chen, Ying Xiong, Shangyu Wu +4In-Context Example Selection In-Context Retrieval
City University of Hong Kong · Mohamed Bin Zayed University of Artificial Intelligence · McGill University
Fast, Slow, and Tool-augmented Thinking for LLMs: A Review
Aug 17, 2025Xinda Jia, Jinpeng Li, Zezhong Wang +6LLM Tool Use LLM Reasoning
School of Mechanical Engineering, Shanghai Jiao Tong University, Shanghai 200240, China · Huawei Technologies Co., Ltd., Beijing 100084, China · Department of Systems Engineering and Engineering Management, The Chinese University of Hong Kong, Hong Kong 999077, China +3
CoHyDE: Iterative Co-Training of LLM Rewriter & Dense Encoder for Tool Retrieval
Date pendingVaishali Senthil, Ashutosh Hathidara, Sebastian SchreiberTool-Augmented Language Model Agents LLM Tool Use
SAP Labs
Palmyra x6 Technical Report: An Agentic, Tool-Use Model Post-Trained via Anchored Supervised Fine-Tuning
Date pendingPeng Du, Kiran Kamble, Rakshith Vasudev +5Supervised Fine-Tuning Tool-Augmented Language Model Agents
Writer AI Research, Writer, Inc.

Aug 21, 2025, cs.CLJ/K move · Enter open · S save

When Tools Hurt LLM Reasoning: State-Dependent Belief Revision under External Evidence

Yufeng Zhao, Junnan Liu, Hongwei Liu, Dongsheng Zhu+3

Shanghai Artificial Intelligence Laboratory · Department of Electronic Engineering, Tsinghua University · Beijing National Research Center for Information Science and Technology+2

Belief Revision Knowledge Conflicts in Language Models LLM Decision-Making LLM Tool Use Tool Use

Open paper AskPDF arXiv

Tool use is often assumed to monotonically improve reasoning, where external evidence is expected to help when relevant and be ignored when irrelevant. We show that this assumption fails in a state-dependent way. Across benchmarks with Python and Wikipedia tools, external evidence reliably helps when initial beliefs are weak, but can flip already-correct answers when those beliefs are strong. We frame this as a misallocation of revision authority, arguing that deferring to external evidence is suboptimal when internal support for the correct answer surpasses the tool's expected output quality. This predicts that harm should concentrate on high-confidence no-tool cases. We test this prediction with threshold localization, wrong-trace audits, and a same-clue intervention showing that revision framing changes the damage caused by misleading evidence. These findings suggest that mixed no-tool/tool-assisted inference should arbitrate authority rather than privilege tool evidence by default. As a minimal demonstration, we introduce CASE, a label-free controller that selects between no-tool and tool-assisted trajectories using answer-state certainty and improves over existing confidence-based arbitration baselines.The code for our experiments is available at https://github.com/epsilondylan/State-Dependent-Belief-Revision.

Momentum

Related topics

Latest papers 185

When Tools Hurt LLM Reasoning: State-Dependent Belief Revision under External Evidence

Beyond Semantic Similarity: Reducing Unnecessary API Calls via Behavior-Aligned Retriever

Fast, Slow, and Tool-augmented Thinking for LLMs: A Review

CoHyDE: Iterative Co-Training of LLM Rewriter & Dense Encoder for Tool Retrieval

Palmyra x6 Technical Report: An Agentic, Tool-Use Model Post-Trained via Anchored Supervised Fine-Tuning