mlsanityData to 7 Oct 2026

Investigating Tool-Memory Conflicts in Tool-Augmented LLMs

arXiv 2601.09760 ↗First posted 14 Jan 2026cs.SE cs.AIcited by 5

On the map: LLM agents and tool use → Tool learning and function calling

Abstract (arXiv)

Tool-augmented large language models (LLMs) have powered many applications. However, they are likely to suffer from knowledge conflict. In this paper, we propose a new type of knowledge conflict -- Tool-Memory Conflict (TMC), where the internal parametric knowledge contradicts with the external tool knowledge for tool-augmented LLMs. We find that existing LLMs, though powerful, suffer from TMC, especially on STEM-related tasks. We also uncover that under different conditions, tool knowledge and parametric knowledge may be prioritized differently. We then evaluate existing conflict resolving techniques, including prompting-based and RAG-based methods. Results show that none of these approaches can effectively resolve tool-memory conflicts.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Placed in Tool learning and function calling, one of 16 directions in LLM agents and tool use. Builds on 38 of its 45 references that are in the map. First posted on arXiv 14 Jan 2026.

Builds on

38 of 45 references.

Closest ancestors · 9

Same direction, newest first

  1. 2025Tool Unlearning for Tool-Augmented LLMs3 Feb
  2. 2024API-BLEND: A Comprehensive Corpora for Training and Benchmarking API LLMs23 Feb
  3. 2023ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs31 Jul
  4. 2023ToolAlpaca: Generalized Tool Learning for Language Models with 3000 Simulated Cases8 Jun
  5. 2023Gorilla: Large Language Model Connected with Massive APIs24 May
  6. 2023Tool Learning with Foundation Models17 Apr
  7. 2023API-Bank: A Comprehensive Benchmark for Tool-Augmented LLMs14 Apr
  8. 2023Toolformer: Language Models Can Teach Themselves to Use Tools9 Feb
  9. 2022TALM: Tool Augmented Language Models24 May

Other references · 29

  1. 2024The Llama 3 Herd of Modelscited by 14,192
  2. 2021Training Verifiers to Solve Math Word Problemscited by 9,743
  3. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  4. 2020Measuring Massive Multitask Language Understandingcited by 7,768
  5. 2024Qwen2.5 Technical Reportcited by 4,713
  6. 2024GPT-4o System Cardcited by 4,467
  7. 2023Let's Verify Step by Stepcited by 3,598
  8. 2023GPQA: A Graduate-Level Google-Proof Q&A Benchmarkcited by 2,748
  9. 2021Entity-Based Knowledge Conflicts in Question Answeringcited by 349
  10. 2023Adaptive Chameleon or Stubborn Sloth: Revealing the Behavior of Large Language Models in Knowledge Conflictscited by 333
  11. 2024Knowledge Conflicts for LLMs: A Surveycited by 274
  12. 2022RealTime QA: What's the Answer Right Now?cited by 239
17 more
  1. 2022Factuality Enhanced Language Models for Open-Ended Text Generationcited by 200
  2. 2021SituatedQA: Incorporating Extra-Linguistic Contexts into QAcited by 145
  3. 2022Rich Knowledge Sources Bring Complex Knowledge Conflicts: Recalibrating Models to Reflect Conflicting Evidencecited by 142
  4. 2023On the Risk of Misinformation Pollution with Large Language Modelscited by 124
  5. 2022TemporalWiki: A Lifelong Benchmark for Training and Evaluating Ever-Evolving Language Modelscited by 117
  6. 2023Cross-Lingual Consistency of Factual Knowledge in Multilingual Language Modelscited by 117
  7. 2024ClashEval: Quantifying the tug-of-war between an LLM's internal prior and external evidencecited by 109
  8. 2024Tug-of-War Between Knowledge: Exploring and Resolving Knowledge Conflicts in Retrieval-Augmented Language Modelscited by 93
  9. 2023Context-faithful Prompting for Large Language Modelscited by 76
  10. 2024What Evidence Do Language Models Find Convincing?cited by 74
  11. 2024SciAgent: Tool-augmented Language Models for Scientific Reasoningcited by 69
  12. 2023Resolving Knowledge Conflicts in Large Language Modelscited by 49
  13. 2024Blinded by Generated Contexts: How Language Models Merge Generated and Retrieved Contexts When Knowledge Conflicts?cited by 47
  14. 2022Plug-and-Play Adaptation for Continuously-updated QAcited by 21
  15. 2023A Causal View of Entity Bias in (Large) Language Modelscited by 21
  16. 2023Mitigating Temporal Misalignment by Discarding Outdated Factscited by 21
  17. 2024TART: An Open-Source Tool-Augmented Framework for Explainable Table-based Reasoningcited by 10

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 5.

5 papers.

  1. 2026Are Tools All We Need? Unveiling the Tool-Use Tax in LLM Agentscited by 11
  2. 2026When the Tool Decides: LLM Agents Defer Blindly to Graph Neural Network Tools, and Stronger Backbones Defer Morecited by 5
  3. 2026TRACER: Token ReAssignment for Concept ERasure in Generative Recommendationcited by 2
  4. 2026MissingBench-Verified: Probing Vision-Language Models' Inability to Detect Missing Object Partscited by 0
  5. 2026Agents Trust Tools Too Much: Measuring Reliance on Unreliable Toolscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024LLM With Tools: A Survey
  2. 2025DRAGged into Conflicts: Detecting and Addressing Conflicting Sources in Search-Augmented LLMs
  3. 2026Exploring Knowledge Conflicts for Faithful LLM Reasoning: Benchmark and Method
  4. 2025Alignment for Efficient Tool Calling of Large Language Models
  5. 2024Studying Large Language Model Behaviors Under Context-Memory Conflicts With Real Documents
  6. 2025Accommodate Knowledge Conflicts in Retrieval-augmented LLMs: Towards Robust Response Generation in the Wild
  7. 2026MemToC: Benchmarking Memory-Tool Conflict Resolution in Large Language Models
  8. 2024Tool Learning with Large Language Models: A Survey