mlsanityData to 7 Oct 2026

AgentOhana: Design Unified Data and Training Pipeline for Effective Agent Learning

arXiv 2402.15506 ↗First posted 23 Feb 2024cs.AI cs.CL cs.LGcited by 53

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 garnered significant research attention. However, fully harnessing the potential of LLMs for agent-based tasks presents inherent challenges due to the heterogeneous nature of diverse data sources featuring multi-turn trajectories. In this paper, we introduce AgentOhana as a comprehensive solution to address these challenges. textitAgentOhana aggregates agent trajectories from distinct environments, spanning a wide array of scenarios. It meticulously standardizes and unifies these trajectories into a consistent format, streamlining the creation of a generic data loader optimized for agent training. Leveraging the data unification, our training pipeline maintains equilibrium across different data sources and preserves independent randomness across devices during dataset partitioning and model training. Additionally, we present xLAM-v0.1, a large action model tailored for AI agents, which demonstrates exceptional performance across various benchmarks. Begin the exploration at urlhttps://github.com/SalesforceAIResearch/xLAM.

Key facts. Cited by 53 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 29 of its 39 references that are in the map. First posted on arXiv 23 Feb 2024.

Builds on

29 of 39 references.

Closest ancestors · 5

Same direction, newest first

  1. 2024AgentBoard: An Analytical Evaluation Board of Multi-turn LLM Agents24 Jan
  2. 2023AgentTuning: Enabling Generalized Agent Abilities for LLMs19 Oct
  3. 2023OpenAgents: An Open Platform for Language Agents in the Wild16 Oct
  4. 2023Lemur: Harmonizing Natural Language and Code for Language Agents10 Oct
  5. 2023BOLAA: Benchmarking and Orchestrating LLM-augmented Autonomous Agents11 Aug

Other references · 24

  1. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 12,865
  2. 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,393
  3. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
  4. 2023Direct Preference Optimization: Your Language Model is Secretly a Reward Modelcited by 7,916
  5. 2023Reflexion: Language Agents with Verbal Reinforcement Learningcited by 4,064
  6. 2018HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answeringcited by 3,686
  7. 2023Self-Refine: Iterative Refinement with Self-Feedbackcited by 3,317
  8. 2023Mistral 7Bcited by 3,065
  9. 2023Code Llama: Open Foundation Models for Codecited by 2,105
  10. 2023ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIscited by 1,880
  11. 2024Mixtral of Expertscited by 1,785
  12. 2023Mind2Web: Towards a Generalist Agent for the Webcited by 1,210
12 more
  1. 2022WebShop: Towards Scalable Real-World Web Interaction with Grounded Language Agentscited by 1,197
  2. 2020ALFWorld: Aligning Text and Embodied Environments for Interactive Learningcited by 1,143
  3. 2023The Flan Collection: Designing Data and Methods for Effective Instruction Tuningcited by 734
  4. 2024Self-Rewarding Language Modelscited by 654
  5. 2024DeepSeek LLM: Scaling Open-Source Language Models with Longtermismcited by 621
  6. 2023LMSYS-Chat-1M: A Large-Scale Real-World LLM Conversation Datasetcited by 449
  7. 2023ToolAlpaca: Generalized Tool Learning for Language Models with 3000 Simulated Casescited by 383
  8. 2023MINT: Evaluating LLMs in Multi-turn Interaction with Tools and Language Feedbackcited by 293
  9. 2024Direct Language Model Alignment from Online AI Feedbackcited by 257
  10. 2023CodeGen2: Lessons for Training LLMs on Programming and Natural Languagescited by 124
  11. 2023DRDT: Dynamic Reflection with Divergent Thinking for LLM-based Sequential Recommendationcited by 27
  12. 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: 19; 2025: 26; 2026: 8.

53 papers.

Sort:

By area:

  1. 2024OS-ATLAS: A Foundation Action Model for Generalist GUI Agentscited by 370
  2. 2024WebRL: Training LLM Web Agents via Self-Evolving Online Curriculum Reinforcement Learningcited by 243
  3. 2024APIGen: Automated Pipeline for Generating Verifiable and Diverse Function-Calling Datasetscited by 188
  4. 2024OS-Genesis: Automating GUI Agent Trajectory Construction via Reverse Task Synthesiscited by 155
  5. 2024AgentGym: Evolving Large Language Model-based Agents across Diverse Environmentscited by 120
  6. 2024xLAM: A Family of Large Action Models to Empower AI Agent Systemscited by 108
  7. 2025PlanGenLLMs: A Modern Survey of LLM Planning Capabilitiescited by 82
  8. 2024AgentGen: Enhancing Planning Abilities for Large Language Model based Agent via Environment and Task Generationcited by 80
  9. 2025SEAgent: Self-Evolving Computer Use Agent with Autonomous Learning from Experiencecited by 68
  10. 2025AgentGym-RL: Training LLM Agents for Long-Horizon Decision Making through Multi-Turn Reinforcement Learningcited by 68
  11. 2024Agent Planning with World Knowledge Modelcited by 66
  12. 2024The Dawn of GUI Agent: A Preliminary Case Study with Claude 3.5 Computer Usecited by 62
38 more
  1. 2024ExACT: Teaching AI Agents to Explore with Reflective-MCTS and Exploratory Learningcited by 61
  2. 2024AgentBank: Towards Generalized LLM Agents via Fine-Tuning on 50000+ Interaction Trajectoriescited by 56
  3. 2025AgentRefine: Enhancing Agent Generalization through Refinement Tuningcited by 51
  4. 2024Multi-modal Agent Tuning: Building a VLM-Driven Agent for Efficient Tool Usagecited by 49
  5. 2024NESTFUL: A Benchmark for Evaluating LLMs on Nested Sequences of API Callscited by 45
  6. 2025A Survey on the Optimization of Large Language Model-based Agentscited by 45
  7. 2024From Multimodal LLMs to Generalist Embodied Agents: Methods and Lessonscited by 42
  8. 2025Distilling LLM Agent into Small Models with Retrieval and Code Toolscited by 41
  9. 2024DynaSaur: Large Language Agents Beyond Predefined Actionscited by 30
  10. 2025ATLaS: Agent Tuning via Learning Critical Stepscited by 29
  11. 2025AgentRM: Enhancing Agent Generalization with Reward Modelingcited by 25
  12. 2024ReAct Meets ActRe: When Language Agents Enjoy Training Data Autonomycited by 22
  13. 2024Can We Rely on LLM Agents to Draft Long-Horizon Plans? Let's Take TravelPlanner as an Examplecited by 22
  14. 2025Agent Data Protocol: Unifying Datasets for Diverse, Effective Fine-tuning of LLM Agentscited by 16
  15. 2025Truly Self-Improving Agents Require Intrinsic Metacognitive Learningcited by 13
  16. 2024RuleR: Improving LLM Controllability by Rule-based Data Recyclingcited by 11
  17. 2025Advancing Language Multi-Agent Learning with Credit Re-Assignment for Interactive Environment Generalizationcited by 11
  18. 2025PilotRL: Training Language Model Agents via Global Planning-Guided Progressive Reinforcement Learningcited by 11
  19. 2025Evolving in Tasks: Empowering the Multi-modality Large Language Model as the Computer Use Agentcited by 10
  20. 2026HATS: Hardness-Aware Trajectory Synthesis for GUI Agentscited by 9
  21. 2025CuES: A Curiosity-driven and Environment-grounded Synthesis Framework for Agentic RLcited by 8
  22. 2025Exploring Expert Failures Improves LLM Agent Tuningcited by 7
  23. 2025Advancing and Benchmarking Personalized Tool Invocation for LLMscited by 7
  24. 2025Hephaestus: Improving Fundamental Agent Capabilities of Large Language Models through Continual Pre-Trainingcited by 6
  25. 2025Cerebrum (AIOS SDK): A Platform for Agent Development, Deployment, Distribution, and Discoverycited by 6
  26. 2025ActionStudio: A Lightweight Framework for Data and Training of Large Action Modelscited by 6
  27. 2025LAM SIMULATOR: Advancing Data Generation for Large Action Model Training via Online Exploration and Trajectory Feedbackcited by 6
  28. 2026PABU: Progress-Aware Belief Update for Efficient LLM Agentscited by 6
  29. 2025Uncertainty in Action: Confidence Elicitation in Embodied Agentscited by 5
  30. 2024DroidCall: A Dataset for LLM-powered Android Intent Invocationcited by 4
  31. 2025Language Models can Self-Improve at State-Value Estimation for Better Searchcited by 4
  32. 2025FedMABench: Benchmarking Mobile Agents on Decentralized Heterogeneous User Datacited by 3
  33. 2025VLM Q-Learning: Aligning Vision-Language Models for Interactive Decision-Makingcited by 3
  34. 2026Supervised Fine-Tuning versus Reinforcement Learning: A Study of Post-Training Methods for Large Language Modelscited by 3
  35. 2026Not All Skills Help: Measuring and Repairing Agent Knowledgecited by 3
  36. 2025NAACL2025 Tutorial: Adaptation of Large Language Modelscited by 2
  37. 2025Bridging the Capability Gap: Joint Alignment Tuning for Harmonizing LLM-based Multi-Agent Systemscited by 1
  38. 2026HippoCamp: Benchmarking Contextual Agents on Personal Computerscited by 1

50 most cited of 53 All 53 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2026OpenThoughts-Agent: Data Recipes for Agentic Models
  2. 2025AgentSwift: Efficient LLM Agent Design via Value-guided Hierarchical Search
  3. 2026Exploring Autonomous Agentic Data Engineering for Model Specialization
  4. 2025DeepAnalyze: Agentic Large Language Models for Autonomous Data Science
  5. 2024Offline Training of Language Model Agents with Functions as Learnable Weights
  6. 2025Scaling Agents via Continual Pre-training
  7. 2026daVinci-Dev: Agent-native Mid-training for Software Engineering
  8. 2025Graph-Augmented Large Language Model Agents: Current Progress and Future Prospects