# Tool learning and function calling Area: [LLM agents and tool use](https://mlsanity.com/agents/index.md). HTML: https://mlsanity.com/agents/tool-learning-and-function-calling/ ## Key facts - Tool learning and function calling: 456 papers on arXiv since 2022 (data through 7 Oct 2026). - 252 of its 456 mapped papers (55%) cite “ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs” (2023, arXiv 2307.16789). - 217 of its 456 mapped papers (48%) cite “Toolformer: Language Models Can Teach Themselves to Use Tools” (2023, arXiv 2302.04761). - 34 new papers 17 Sep–7 Oct. ## Most cited here - [ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs](https://mlsanity.com/paper/2307.16789/) (2023), cited by 252 papers here - [Toolformer: Language Models Can Teach Themselves to Use Tools](https://mlsanity.com/paper/2302.04761/) (2023), cited by 217 papers here - [Gorilla: Large Language Model Connected with Massive APIs](https://mlsanity.com/paper/2305.15334/) (2023), cited by 213 papers here - [API-Bank: A Comprehensive Benchmark for Tool-Augmented LLMs](https://mlsanity.com/paper/2304.08244/) (2023), cited by 111 papers here - [ToolAlpaca: Generalized Tool Learning for Language Models with 3000 Simulated Cases](https://mlsanity.com/paper/2306.05301/) (2023), cited by 105 papers here - [MetaTool Benchmark for Large Language Models: Deciding Whether to Use Tools and Which to Use](https://mlsanity.com/paper/2310.03128/) (2023), cited by 65 papers here - [ToolkenGPT: Augmenting Frozen Language Models with Massive Tools via Tool Embeddings](https://mlsanity.com/paper/2305.11554/) (2023), cited by 58 papers here - [APIGen: Automated Pipeline for Generating Verifiable and Diverse Function-Calling Datasets](https://mlsanity.com/paper/2406.18518/) (2024), cited by 52 papers here - [ToolACE: Winning the Points of LLM Function Calling](https://mlsanity.com/paper/2409.00920/) (2024), cited by 46 papers here - [ToolQA: A Dataset for LLM Question Answering with External Tools](https://mlsanity.com/paper/2306.13304/) (2023), cited by 45 papers here ## New (17 Sep–7 Oct) - [Loud Failures, Quiet Failures: Fault Detection and Recovery in Tool-Using Language Model Agents](https://mlsanity.com/paper/2610.10062/) (2026-10-07) - [How Do Agentic LLMs Decide to Call Tools? A Tool-Call Vector Shaped by Suppression](https://mlsanity.com/paper/2610.09624/) (2026-10-07) - [Tool-calling retrieval versus vector RAG for a small Greek--English knowledge base: accuracy and robustness to how users type Greek](https://mlsanity.com/paper/2610.08205/) (2026-10-06) - [Quantization Effects on Tool-Failure Recovery Vary Across Prompts and Evaluation Designs](https://mlsanity.com/paper/2610.07781/) (2026-10-06) - [Dynamic Budget Allocation for LLM Evaluation under Hard Resource Constraints](https://mlsanity.com/paper/2610.07362/) (2026-10-05) - [SchemaFill: Efficient LLM Tool Calling via Slot-Parallel Speculative Decoding](https://mlsanity.com/paper/2610.07086/) (2026-10-05) - [Turnslide: Scalable Multi-Turn Data Synthesis by Walking a Finite-State Machine](https://mlsanity.com/paper/2610.07070/) (2026-10-05) - [Topology-Consistent Task Planning over Cellular Workflow Complexes for LLM-based Agents](https://mlsanity.com/paper/2610.07004/) (2026-10-04) - [Understanding and Mitigating Hallucination Escape in Tool-Using LLM Agents](https://mlsanity.com/paper/2610.04409/) (2026-10-03) - [SHarP: Saliency-based Pruning of Agent Harnesses](https://mlsanity.com/paper/2610.04178/) (2026-10-03) - [MLLMs Fail to Refuse when Using Tools Agentically](https://mlsanity.com/paper/2610.03938/) (2026-10-02) - [Proxy Confidence: Auditing Black-Box LLM Agents with a Surrogate's Log-Probabilities](https://mlsanity.com/paper/2610.03894/) (2026-10-02) - [Toward SLM-based agentic task-tool intent matching](https://mlsanity.com/paper/2610.03213/) (2026-10-02) - [What Does a Token Cost? A Mixture-of-Agents Measurement of Sufficient Per-Token Compute](https://mlsanity.com/paper/2610.02491/) (2026-10-01) - [Choosing Before Acting: Comparative Value Estimation for Long-Horizon Tool-Use Agents](https://mlsanity.com/paper/2610.02330/) (2026-10-01) - [Fast Models, Slow Evidence: A Paired and Self-Audited Evaluation of System-1 Decision Models for LLM Agent Harnesses](https://mlsanity.com/paper/2610.02267/) (2026-10-01) - [Keyword Harnesses Fail Open: A Cheap Diagnostic Ladder for Tool-Use Claims in Small Language Models](https://mlsanity.com/paper/2610.02142/) (2026-10-01) - [What Can Component-Replacement Evidence Establish? A Critical Scoping Review of Local Decisions in LLM Agents](https://mlsanity.com/paper/2609.39989/) (2026-09-30) - [ContextRender: From Execution Dependencies to Agent Context](https://mlsanity.com/paper/2609.37743/) (2026-09-29) - [TokenCast: Forecasting Token Consumption During LLM Agent Execution](https://mlsanity.com/paper/2609.35760/) (2026-09-29) - [One Readout, Many Repairs: Diffusion-Guided Hierarchical Search for Tool-Agent Repair](https://mlsanity.com/paper/2609.34879/) (2026-09-29) - [When Does Correction Become Repair? Mechanistic Auditing of Internal Interventions in Tool-Using LLMs](https://mlsanity.com/paper/2609.36138/) (2026-09-28) - [Action-Space Shaping for LLM Agents: Measuring and Mitigating Tool-Schema Bias](https://mlsanity.com/paper/2609.34971/) (2026-09-28) - [PDEU-Bench: Benchmarking the Personalized Planning Lifecycle of Tool-Calling LLM Agents](https://mlsanity.com/paper/2609.34930/) (2026-09-28) - [Quantization Thresholds Replicate, Failure Modes Do Not: A Three-Model Study of Agentic Tool Use in Polish from 8-bit to 2-bit](https://mlsanity.com/paper/2609.32042/) (2026-09-25) - [ToolSearcher: Optimizing Tool Selection at Scale via Reinforcement Learning](https://mlsanity.com/paper/2609.30906/) (2026-09-25) - [Learning from Failures: Heterogeneous Graph Memory for Small Language Model Tool-Using Agents](https://mlsanity.com/paper/2609.28003/) (2026-09-23) - [TwinCheck: Evidence-Grounded Negative-Twin Verification for Stateful Tool Agents](https://mlsanity.com/paper/2609.26911/) (2026-09-22) - [Measuring the Serving Stack Instead of the Model: Hidden Confounds in Local Tool-Use Evaluation](https://mlsanity.com/paper/2609.26693/) (2026-09-22) - [MCP-GRANITE Benchmark: GRANularity Interface TEsting for MCP-Based LLM Agents](https://mlsanity.com/paper/2609.24161/) (2026-09-21)