mlsanityData to 7 Oct 2026

ToolGen: Unified Tool Retrieval and Calling via Generation

arXiv 2410.03439 ↗First posted 4 Oct 2024cs.CLcited by 72

Not on the map. Why?

Cited by 52 in LLM agents and tool use, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

As large language models (LLMs) advance, their inability to autonomously execute tasks by directly interacting with external tools remains a critical limitation. Traditional methods rely on inputting tool descriptions as context, which is constrained by context length and requires separate, often inefficient, retrieval mechanisms. We introduce ToolGen, a paradigm shift that integrates tool knowledge directly into the LLM's parameters by representing each tool as a unique token. This enables the LLM to generate tool calls and arguments as part of its next token prediction capabilities, seamlessly blending tool invocation with language generation. Our framework allows the LLM to access and utilize a vast amount of tools with no additional retrieval step, significantly enhancing both performance and scalability. Experimental results with over 47,000 tools show that ToolGen not only achieves superior results in both tool retrieval and autonomous task completion but also sets the stage for a new era of AI agents that can adapt to tools across diverse domains. By fundamentally transforming tool retrieval into a generative process, ToolGen paves the way for more versatile, efficient, and autonomous AI systems. ToolGen enables end-to-end tool learning and opens opportunities for integration with other advanced techniques such as chain-of-thought and reinforcement learning, thereby expanding the practical capabilities of LLMs.

Key facts. Cited by 72 papers in the map (data through 7 Oct 2026). Builds on 41 of its 49 references that are in the map. First posted on arXiv 4 Oct 2024.

Builds on

41 of 49 references.

References · 41

  1. 2020Language Models are Few-Shot Learnerscited by 32,199
  2. 2022Training language models to follow instructions with human feedbackcited by 15,712
  3. 2024The Llama 3 Herd of Modelscited by 14,192
  4. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
  5. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
  6. 2023Reflexion: Language Agents with Verbal Reinforcement Learningcited by 4,064
  7. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,779
  8. 2022FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awarenesscited by 3,611
  9. 2023RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Controlcited by 2,993
  10. 2023FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioningcited by 2,551
  11. 2024Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameterscited by 1,928
  12. 2023ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIscited by 1,880
29 more
  1. 2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflectioncited by 1,800
  2. 2023Gorilla: Large Language Model Connected with Massive APIscited by 1,302
  3. 2019ZeRO: Memory Optimizations Toward Training Trillion Parameter Modelscited by 1,278
  4. 2023AgentBench: Evaluating LLMs as Agentscited by 1,211
  5. 2024Large Language Monkeys: Scaling Inference Compute with Repeated Samplingcited by 946
  6. 2020Approximate Nearest Neighbor Negative Contrastive Learning for Dense Text Retrievalcited by 846
  7. 2023AgentTuning: Enabling Generalized Agent Abilities for LLMscited by 319
  8. 2024Inference Scaling Laws: An Empirical Analysis of Compute-Optimal Inference for Problem-Solving with Language Modelscited by 282
  9. 2023FireAct: Toward Language Agent Fine-tuningcited by 247
  10. 2023ToolkenGPT: Augmenting Frozen Language Models with Massive Tools via Tool Embeddingscited by 238
  11. 2024Tool Learning with Large Language Models: A Surveycited by 221
  12. 2024StableToolBench: Towards Stable Large-Scale Benchmarking on Tool Learning of Large Language Modelscited by 129
  13. 2022A Neural Corpus Indexer for Document Retrievalcited by 107
  14. 2024Agent-FLAN: Designing Data and Methods of Effective Agent Tuning for Large Language Modelscited by 97
  15. 2024Small LLMs Are Weak Tool Learners: A Multi-LLM Agentcited by 92
  16. 2023BOLAA: Benchmarking and Orchestrating LLM-augmented Autonomous Agentscited by 83
  17. 2024AutoAct: Automatic Agent Learning from Scratch for QA via Self-Planningcited by 81
  18. 2023Agent Lumos: Unified and Modular Training for Open-Source Language Agentscited by 72
  19. 2023Learning to Tokenize for Generative Retrievalcited by 66
  20. 2024LLM3:Large Language Model-based Task and Motion Planning with Motion Failure Reasoningcited by 63
  21. 2024Re-Invoke: Tool Invocation Rewriting for Zero-Shot Tool Retrievalcited by 50
  22. 2024Learning From Failure: Integrating Negative Examples when Fine-tuning Large Language Models as Agentscited by 49
  23. 2023TPTU-v2: Boosting Task Planning and Tool Usage of Large Language Model-based Agents in Real-world Systemscited by 39
  24. 2022DSI++: Updating Transformer Memory with New Documentscited by 35
  25. 2024ToolPlanner: A Tool Augmented LLM for Multi Granularity Instructions with Path Planning and Feedbackcited by 28
  26. 2023Continual Learning for Generative Retrieval over Dynamic Corporacited by 25
  27. 2024Enhancing Tool Retrieval with Iterative Feedback from Large Language Modelscited by 17
  28. 2023IncDSI: Incrementally Updatable Document Retrievalcited by 12
  29. 2024Smurfs: Multi-Agent System using Context-Efficient DFSDT for Tool Planningcited by 12

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 1; 2025: 28; 2026: 43.

72 papers.

Sort:

By area:

  1. 2025Prompt Injection Attack to Tool Selection in LLM Agentscited by 145
  2. 2025DeepAgent: A General Reasoning Agent with Scalable Toolsetscited by 69
  3. 2025Token Reduction Should Go Beyond Efficiency in Generative Models -- From Vision, Language to Multimodalitycited by 49
  4. 2025Retrieval Models Aren't Tool-Savvy: Benchmarking Tool Retrieval for Large Language Modelscited by 46
  5. 2025Agentic AI Security: Threats, Defenses, Evaluation, and Open Challengescited by 26
  6. 2025What to Retrieve for Effective Retrieval-Augmented Code Generation? An Empirical Study and Beyondcited by 22
  7. 2025ToolTweak: An Attack on Tool Selection in LLM-based Agentscited by 22
  8. 2026ReCreate: Reasoning and Creating Domain Agents Driven by Experiencecited by 22
  9. 2026From Failed Trajectories to Reliable LLM Agents: Diagnosing and Repairing Harness Flawscited by 21
  10. 2025Feedback-Driven Tool-Use Improvements in Large Language Models via Automated Build Environmentscited by 19
  11. 2024Explore the Reasoning Capability of LLMs in the Chess Testbedcited by 17
  12. 2026A Comprehensive Survey on Agent Skills: Taxonomy, Techniques, and Applicationscited by 17
38 more
  1. 2025Tool-R1: Sample-Efficient Reinforcement Learning for Agentic Tool Usecited by 16
  2. 2026SkillDAG: Self-Evolving Typed Skill Graphs for LLM Skill Selection at Scalecited by 15
  3. 2025DeepCode: Open Agentic Codingcited by 14
  4. 2025a1: Steep Test-time Scaling Law via Environment Augmented Generationcited by 13
  5. 2025MIP against Agent: Malicious Image Patches Hijacking Multimodal OS Agentscited by 12
  6. 2025Failure Makes the Agent Stronger: Enhancing Accuracy through Structured Reflection for Reliable Tool Interactionscited by 12
  7. 2025AutoTool: Dynamic Tool Selection and Integration for Agentic Reasoningcited by 11
  8. 2026Toward Efficient Agents: Memory, Tool learning, and Planningcited by 11
  9. 2026The Evolution of Tool Use in LLM Agents: From Single-Tool Call to Multi-Tool Orchestrationcited by 11
  10. 2026More Skills, Worse Agents? Skill Shadowing Degrades Performance When Expanding Skill Librariescited by 11
  11. 2026PlanBench-XL: Evaluating Long-Horizon Planning of LLM Tool-Use Agents in Large-Scale Tool Ecosystemscited by 10
  12. 2025AgentFly: Extensible and Scalable Reinforcement Learning for LM Agentscited by 8
  13. 2025LENS: Multi-level Evaluation of Multimodal Reasoning with Large Language Modelscited by 7
  14. 2025MIRROR: Multi-agent Intra- and Inter-Reflection for Optimized Reasoning in Tool Learningcited by 7
  15. 2026ToolOmni: Enabling Open-World Tool Use via Agentic learning with Proactive Retrieval and Grounded Executioncited by 7
  16. 2026SkCC: Portable and Secure Skill Compilation for Cross-Framework LLM Agentscited by 7
  17. 2026Gated Differentiable Working Memory for Long-Context Language Modelingcited by 6
  18. 2026PhGPO: Pheromone-Guided Policy Optimization for Long-Horizon Tool Planningcited by 6
  19. 2026SEARL: Joint Optimization of Policy and Tool Graph Memory for Self-Evolving Agentscited by 6
  20. 2025TokMem: One-Token Procedural Memory for Large Language Modelscited by 5
  21. 2025GraphChain: Large Language Models for Large-scale Graph Analysis via Tool Chainingcited by 5
  22. 2026SkillsInjector: Dynamic Skill Context Construction for LLM Agentscited by 5
  23. 2025GATE: Graph-based Adaptive Tool Evolution Across Diverse Taskscited by 3
  24. 2025PEToolLLM: Towards Personalized Tool Learning in Large Language Modelscited by 3
  25. 2025LoSemB: Logic-Guided Semantic Bridging for Inductive Tool Retrievalcited by 3
  26. 2026AgentSelect: Benchmark for Narrative Query-to-Agent Recommendationcited by 3
  27. 2026Training LLM Agents for Spontaneous, Reward-Free Self-Evolution via World Knowledge Explorationcited by 3
  28. 2026Tools Are Not Islands: Set-Level Tool Retrieval for LLM Agents via Query-Conditioned Hyperedge Predictioncited by 3
  29. 2026ReCache: Efficient KV Cache Reuse and Compression for Tool-Augmented LLM Agentscited by 3
  30. 2025Schema as Parameterized Tools for Universal Information Extractioncited by 2
  31. 2025Online-Optimized RAG for Tool Use and Function Callingcited by 2
  32. 2025RIMRULE: Improving Tool-Using Language Agents via MDL-Guided Rule Learningcited by 2
  33. 2026Beyond Single-Shot: Multi-step Tool Retrieval via Query Planningcited by 2
  34. 2026FinTrace: Holistic Trajectory-Level Evaluation of LLM Tool Calling for Long-Horizon Financial Taskscited by 2
  35. 2026RS-Claw: Progressive Active Tool Exploration via Hierarchical Skill Trees for Remote Sensing Agentscited by 2
  36. 2026SKILL-DISCO: Distilling and Compiling Agent Traces into Reusable Procedural Skillscited by 2
  37. 2026The Menu Is an Execution Prior: State-Path Tool Menus for Online Agentscited by 2
  38. 2025Planning Agents on an Ego-Trip: Leveraging Hybrid Ego-Graph Ensembles for Improved Tool Retrieval in Enterprise Task Planningcited by 1

50 most cited of 72 All 72 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2026ToolWeaver: Weaving Collaborative Semantics for Scalable Tool Use in Large Language Models
  2. 2024Tool Learning in the Wild: Empowering Language Models as Automatic Tool Agents
  3. 2025GRETEL: A Goal-driven Retrieval and Execution-based Trial Framework for LLM Tool Selection Enhancing
  4. 2026SING: Synthetic Intention Graph for Scalable Active Tool Discovery in LLM Agents
  5. 2026NTILC: Neural Tool Invocation via Learned Compression
  6. 2026OpaqueToolsBench: Learning Nuances of Tool Behavior Through Interaction
  7. 2026RaTA-Tool: Retrieval-based Tool Selection with Multimodal Large Language Models
  8. 2025ToolLibGen: Scalable Automatic Tool Creation and Aggregation for LLM Reasoning