mlsanityData to 7 Oct 2026

xLAM: A Family of Large Action Models to Empower AI Agent Systems

arXiv 2409.03215 ↗First posted 5 Sep 2024cs.CL cs.AI cs.LGcited by 108

On the map: LLM agents and tool use → General LLM agent frameworks and benchmarks

Abstract (arXiv)

Autonomous agents powered by large language models (LLMs) have attracted significant research interest. However, the open-source community faces many challenges in developing specialized models for agent tasks, driven by the scarcity of high-quality agent datasets and the absence of standard protocols in this area. We introduce and publicly release xLAM, a series of large action models designed for AI agent tasks. The xLAM series includes five models with both dense and mixture-of-expert architectures, ranging from 1B to 8x22B parameters, trained using a scalable, flexible pipeline that unifies, augments, and synthesizes diverse datasets to enhance AI agents' generalizability and performance across varied environments. Our experimental results demonstrate that xLAM consistently delivers exceptional performance across multiple agent ability benchmarks, notably securing the 1st position on the Berkeley Function-Calling Leaderboard, outperforming GPT-4, Claude-3, and many other models in terms of tool use. By releasing the xLAM series, we aim to advance the performance of open-source LLMs for autonomous AI agents, potentially accelerating progress and democratizing access to high-performance models for agent tasks. Models are available at https://huggingface.co/collections/Salesforce/xlam-models-65f00e2a0a63bbcd1c2dade4

Key facts. Cited by 108 papers in the map (data through 7 Oct 2026). Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use. Builds on 40 of its 48 references that are in the map. First posted on arXiv 5 Sep 2024.

Builds on

40 of 48 references.

Closest ancestors · 10

Same direction, newest first

  1. 2024Agent-FLAN: Designing Data and Methods of Effective Agent Tuning for Large Language Models19 Mar
  2. 2024AgentLite: A Lightweight Library for Building and Advancing Task-Oriented LLM Agent System23 Feb
  3. 2024AgentOhana: Design Unified Data and Training Pipeline for Effective Agent Learning23 Feb
  4. 2024AgentBoard: An Analytical Evaluation Board of Multi-turn LLM Agents24 Jan
  5. 2023AgentTuning: Enabling Generalized Agent Abilities for LLMs19 Oct
  6. 2023OpenAgents: An Open Platform for Language Agents in the Wild16 Oct
  7. 2023Lemur: Harmonizing Natural Language and Code for Language Agents10 Oct
  8. 2023FireAct: Toward Language Agent Fine-tuning9 Oct
  9. 2023BOLAA: Benchmarking and Orchestrating LLM-augmented Autonomous Agents11 Aug
  10. 2023AgentBench: Evaluating LLMs as Agents7 Aug

Other references · 30

  1. 2023GPT-4 Technical Reportcited by 18,132
  2. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,084
  3. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 13,958
  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. 2023Direct Preference Optimization: Your Language Model is Secretly a Reward Modelcited by 7,916
  7. 2023Reflexion: Language Agents with Verbal Reinforcement Learningcited by 4,064
  8. 2024Gemini 1.5: Unlocking multimodal understanding across millions of tokens of contextcited by 3,175
  9. 2023Code Llama: Open Foundation Models for Codecited by 2,105
  10. 2023WebArena: A Realistic Web Environment for Building Autonomous Agentscited by 1,908
  11. 2023ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIscited by 1,880
  12. 2024Mixtral of Expertscited by 1,785
18 more
  1. 2023Gorilla: Large Language Model Connected with Massive APIscited by 1,302
  2. 2023Mind2Web: Towards a Generalist Agent for the Webcited by 1,210
  3. 2022WebShop: Towards Scalable Real-World Web Interaction with Grounded Language Agentscited by 1,197
  4. 2024DeepSeek-Coder: When the Large Language Model Meets Programming -- The Rise of Code Intelligencecited by 1,154
  5. 2024DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Modelcited by 1,093
  6. 2023PyTorch FSDP: Experiences on Scaling Fully Sharded Data Parallelcited by 641
  7. 2024DeepSeek LLM: Scaling Open-Source Language Models with Longtermismcited by 621
  8. 2023API-Bank: A Comprehensive Benchmark for Tool-Augmented LLMscited by 574
  9. 2023ToolAlpaca: Generalized Tool Learning for Language Models with 3000 Simulated Casescited by 383
  10. 2023MINT: Evaluating LLMs in Multi-turn Interaction with Tools and Language Feedbackcited by 293
  11. 2023MetaTool Benchmark for Large Language Models: Deciding Whether to Use Tools and Which to Usecited by 209
  12. 2024APIGen: Automated Pipeline for Generating Verifiable and Diverse Function-Calling Datasetscited by 188
  13. 2024AnyTool: Self-Reflective, Hierarchical Agents for Large-Scale API Callscited by 121
  14. 2024Let Me Speak Freely? A Study on the Impact of Format Restrictions on Performance of Large Language Modelscited by 90
  15. 2023The Data Provenance Initiative: A Large Scale Audit of Dataset Licensing & Attribution in AIcited by 73
  16. 2023TAIL: Task-specific Adapters for Imitation Learning with Large Pretrained Modelscited by 48
  17. 2024Consent in Crisis: The Rapid Decline of the AI Data Commonscited by 45
  18. 2023DialogStudio: Towards Richest and Most Diverse Unified Dataset Collection for Conversational AIcited by 21

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 14; 2025: 64; 2026: 30.

108 papers.

Sort:

By area:

  1. 2024OS-ATLAS: A Foundation Action Model for Generalist GUI Agentscited by 370
  2. 2025ToolRL: Reward is All Tool Learning Needscited by 342
  3. 2024Aguvis: Unified Pure Vision Agents for Autonomous GUI Interactioncited by 271
  4. 2025Small Language Models are the Future of Agentic AIcited by 254
  5. 2024ShowUI: One Vision-Language-Action Model for GUI Visual Agentcited by 226
  6. 2026GDPO: Group reward-Decoupled Normalization Policy Optimization for Multi-reward RL Optimizationcited by 175
  7. 2024Large Language Model-Brained GUI Agents: A Surveycited by 160
  8. 2025APIGen-MT: Agentic Pipeline for Multi-Turn Data Generation via Simulated Agent-Human Interplaycited by 158
  9. 2024Aria-UI: Visual Grounding for GUI Instructionscited by 136
  10. 2025Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systemscited by 125
  11. 2025MCP-Universe: Benchmarking Large Language Models with Real-World Model Context Protocol Serverscited by 89
  12. 2025UserBench: An Interactive Gym Environment for User-Centric Agentscited by 69
38 more
  1. 2024The Dawn of GUI Agent: A Preliminary Case Study with Claude 3.5 Computer Usecited by 62
  2. 2024ExACT: Teaching AI Agents to Explore with Reflective-MCTS and Exploratory Learningcited by 61
  3. 2024Hammer: Robust Function-Calling for On-Device Language Models via Function Maskingcited by 53
  4. 2025Towards General Agentic Intelligence via Environment Scalingcited by 51
  5. 2024MMLU-CF: A Contamination-free Multi-task Language Understanding Benchmarkcited by 41
  6. 2025Magnet: Multi-turn Tool-use Data Synthesis and Distillation via Graph Translationcited by 37
  7. 2024Benchmarking Agentic Workflow Generationcited by 36
  8. 2025When2Call: When (not) to Call Toolscited by 36
  9. 2026Nemotron 3 Super: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoningcited by 33
  10. 2026Tool-R0: Self-Evolving LLM Agents for Tool-Learning from Zero Datacited by 31
  11. 2025MUA-RL: Multi-turn User-interacting Agent Reinforcement Learning for agentic tool usecited by 30
  12. 2025Self-Improving LLM Agents at Test-Timecited by 30
  13. 2024ToolFlow: Boosting LLM Tool-Calling Through Natural and Coherent Dialogue Synthesiscited by 27
  14. 2025Procedural Environment Generation for Tool-Use Agentscited by 21
  15. 2025Enterprise Deep Research: Steerable Multi-Agent Deep Research for Enterprise Analyticscited by 20
  16. 2025SpaceTools: Tool-Augmented Spatial Reasoning via Double Interactive RLcited by 20
  17. 2024Large Action Models: From Inception to Implementationcited by 18
  18. 2024ToolScan: A Benchmark for Characterizing Errors in Tool-Use LLMscited by 17
  19. 2025On the Robustness of Agentic Function Callingcited by 17
  20. 2025Don't Just Fine-tune the Agent, Tune the Environmentcited by 17
  21. 2025Tool Zero: Training Tool-Augmented LLMs via Pure RL from Scratchcited by 17
  22. 2025ToolRM: Outcome Reward Models for Tool-Calling Large Language Modelscited by 16
  23. 2025Agent Data Protocol: Unifying Datasets for Diverse, Effective Fine-tuning of LLM Agentscited by 16
  24. 2025Dyna-Think: Synergizing Reasoning, Acting, and World Model Simulation in AI Agentscited by 14
  25. 2025MIP against Agent: Malicious Image Patches Hijacking Multimodal OS Agentscited by 12
  26. 2025Failure Makes the Agent Stronger: Enhancing Accuracy through Structured Reflection for Reliable Tool Interactionscited by 12
  27. 2025Optimizing Agentic Language Model Inference via Speculative Tool Callscited by 11
  28. 2025Technical Report of TeleChat2, TeleChat2.5 and T1cited by 10
  29. 2025ToolACE-R: Model-aware Iterative Training and Adaptive Refinement for Tool Learningcited by 9
  30. 2025Multi-Mission Tool Bench: Assessing the Robustness of LLM based Agents through Related and Dynamic Missionscited by 9
  31. 2025A Desideratum for Conversational Agents: Capabilities, Challenges, and Future Directionscited by 9
  32. 2025MedOrch: Medical Diagnosis with Tool-Augmented Reasoning Agents for Flexible Extensibilitycited by 9
  33. 2025Aegis: Taxonomy and Optimizations for Overcoming Agent-Environment Failures in LLM Agentscited by 9
  34. 2025ResT: Reshaping Token-Level Policy Gradients for Tool-Use Large Language Modelscited by 9
  35. 2025Agentic Workflows for Conversational Human-AI Interaction Designcited by 8
  36. 2025FinGAIA: A Chinese Benchmark for AI Agents in Real-World Financial Domaincited by 8
  37. 2025Advancing and Benchmarking Personalized Tool Invocation for LLMscited by 7
  38. 2025ToolACE-DEV: Self-Improving Tool Learning via Decomposition and EVolutioncited by 7

50 most cited of 108 All 108 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2023The Rise and Potential of Large Language Model Based Agents: A Survey
  2. 2025From Language to Action: A Review of Large Language Models as Autonomous Agents and Tool Users
  3. 2023A Survey on Large Language Model based Autonomous Agents
  4. 2025From LLM Reasoning to Autonomous AI Agents: A Comprehensive Review
  5. 2024Coalitions of Large Language Models Increase the Robustness of AI Agents
  6. 2024AgentGym: Evolving Large Language Model-based Agents across Diverse Environments
  7. 2025Large Language Model Agent: A Survey on Methodology, Applications and Challenges
  8. 2025Pre-Act: Multi-Step Planning and Reasoning Improves Acting in LLM Agents