mlsanityData to 7 Oct 2026

AgentBank: Towards Generalized LLM Agents via Fine-Tuning on 50000+ Interaction Trajectories

arXiv 2410.07706 ↗First posted 10 Oct 2024cs.CL cs.AIcited by 56

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

Abstract (arXiv)

Fine-tuning on agent-environment interaction trajectory data holds significant promise for surfacing generalized agent capabilities in open-source large language models (LLMs). In this work, we introduce AgentBank, by far the largest trajectory tuning data collection featuring more than 50k diverse high-quality interaction trajectories which comprises 16 tasks covering five distinct agent skill dimensions. Leveraging a novel annotation pipeline, we are able to scale the annotated trajectories and generate a trajectory dataset with minimized difficulty bias. Furthermore, we fine-tune LLMs on AgentBank to get a series of agent models, Samoyed. Our comparative experiments demonstrate the effectiveness of scaling the interaction trajectory data to acquire generalized agent capabilities. Additional studies also reveal some key observations regarding trajectory tuning and agent skill generalization.

Key facts. Cited by 56 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 43 of its 60 references that are in the map. First posted on arXiv 10 Oct 2024.

Builds on

43 of 60 references.

Closest ancestors · 6

Same direction, newest first

  1. 2024Watch Every Step! LLM Agent Learning via Iterative Step-Level Process Refinement17 Jun
  2. 2024AgentOhana: Design Unified Data and Training Pipeline for Effective Agent Learning23 Feb
  3. 2024If LLM Is the Wizard, Then Code Is the Wand: A Survey on How Code Empowers Large Language Models to Serve as Intelligent Agents1 Jan
  4. 2023AgentTuning: Enabling Generalized Agent Abilities for LLMs19 Oct
  5. 2023Lemur: Harmonizing Natural Language and Code for Language Agents10 Oct
  6. 2023FireAct: Toward Language Agent Fine-tuning9 Oct

Other references · 37

  1. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  2. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 12,865
  3. 2021Training Verifiers to Solve Math Word Problemscited by 9,743
  4. 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,393
  5. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
  6. 2021Evaluating Large Language Models Trained on Codecited by 8,053
  7. 2020Measuring Massive Multitask Language Understandingcited by 7,768
  8. 2021Measuring Mathematical Problem Solving With the MATH Datasetcited by 5,203
  9. 2022Large Language Models are Zero-Shot Reasonerscited by 4,323
  10. 2021Finetuned Language Models Are Zero-Shot Learnerscited by 3,747
  11. 2018HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answeringcited by 3,686
  12. 2021Program Synthesis with Large Language Modelscited by 3,509
25 more
  1. 2022Scaling Instruction-Finetuned Language Modelscited by 2,997
  2. 2017TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehensioncited by 2,895
  3. 2023Code Llama: Open Foundation Models for Codecited by 2,105
  4. 2023WebArena: A Realistic Web Environment for Building Autonomous Agentscited by 1,908
  5. 2021Multitask Prompted Training Enables Zero-Shot Task Generalizationcited by 1,462
  6. 2023Mind2Web: Towards a Generalist Agent for the Webcited by 1,210
  7. 2022WebShop: Towards Scalable Real-World Web Interaction with Grounded Language Agentscited by 1,197
  8. 2020ALFWorld: Aligning Text and Embodied Environments for Interactive Learningcited by 1,143
  9. 2022Measuring and Narrowing the Compositionality Gap in Language Modelscited by 1,054
  10. 2022Super-NaturalInstructions: Generalization via Declarative Instructions on 1600+ NLP Taskscited by 858
  11. 2019ALFRED: A Benchmark for Interpreting Grounded Instructions for Everyday Taskscited by 773
  12. 2021Did Aristotle Use a Laptop? A Question Answering Benchmark with Implicit Reasoning Strategiescited by 736
  13. 2023WizardCoder: Empowering Code Large Language Models with Evol-Instructcited by 728
  14. 2019MathQA: Towards Interpretable Math Word Problem Solving with Operation-Based Formalismscited by 653
  15. 2023Instruction Tuning for Large Language Models: A Surveycited by 617
  16. 2023MAmmoTH: Building Math Generalist Models through Hybrid Instruction Tuningcited by 483
  17. 2023Language Models can Solve Computer Taskscited by 371
  18. 2023MINT: Evaluating LLMs in Multi-turn Interaction with Tools and Language Feedbackcited by 293
  19. 2023InterCode: Standardizing and Benchmarking Interactive Coding with Execution Feedbackcited by 229
  20. 2024Trial and Error: Exploration-Based Trajectory Optimization for LLM Agentscited by 194
  21. 2023TheoremQA: A Theorem-driven Question Answering datasetcited by 189
  22. 2023ReWOO: Decoupling Reasoning from Observations for Efficient Augmented Language Modelscited by 174
  23. 2017IQA: Visual Question Answering in Interactive Environmentscited by 154
  24. 2023Platypus: Quick, Cheap, and Powerful Refinement of LLMscited by 150
  25. 2021Visual Room Rearrangementcited by 101

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 1; 2025: 30; 2026: 25.

56 papers.

Sort:

By area:

  1. 2024Large Language Model-Brained GUI Agents: A Surveycited by 160
  2. 2025A Survey of Frontiers in LLM Reasoning: Inference Scaling, Learning to Reason, and Agentic Systemscited by 108
  3. 2025Understanding Software Engineering Agents: A Study of Thought-Action-Result Trajectoriescited by 75
  4. 2025Agent-R: Training Language Model Agents to Reflect via Iterative Self-Trainingcited by 74
  5. 2026Agent World Model: Infinity Synthetic Environments for Agentic Reinforcement Learningcited by 51
  6. 2025A Survey on the Optimization of Large Language Model-based Agentscited by 45
  7. 2025Distilling LLM Agent into Small Models with Retrieval and Code Toolscited by 41
  8. 2025MPO: Boosting LLM Agents with Meta Plan Optimizationcited by 36
  9. 2025Measuring Agents in Productioncited by 35
  10. 2025GenEnv: Difficulty-Aligned Co-Evolution Between LLM Agents and Environment Simulatorscited by 34
  11. 2025Understanding Code Agent Behaviour: An Empirical Study of Success and Failure Trajectoriescited by 30
  12. 2025ATLaS: Agent Tuning via Learning Critical Stepscited by 29
38 more
  1. 2026AgentProcessBench: Diagnosing Step-Level Process Quality in Tool-Using Agentscited by 28
  2. 2025The Lighthouse of Language: Enhancing LLM Agents via Critique-Guided Improvementcited by 19
  3. 2025A Goal Without a Plan Is Just a Wish: Efficient and Effective Global Planner Training for Long-Horizon Agent Taskscited by 17
  4. 2025Agent Data Protocol: Unifying Datasets for Diverse, Effective Fine-tuning of LLM Agentscited by 16
  5. 2025A Unified Agentic Framework for Evaluating Conditional Image Generationcited by 15
  6. 2025AssetOpsBench: Benchmarking AI Agents for Task Automation in Industrial Asset Operations and Maintenancecited by 15
  7. 2025SAND: Boosting LLM Agents with Self-Taught Action Deliberationcited by 14
  8. 2026CoEvolve: Training LLM Agents via Agent-Data Mutual Evolutioncited by 14
  9. 2026TrajAD: Trajectory Anomaly Detection for Trustworthy LLM Agentscited by 13
  10. 2025PilotRL: Training Language Model Agents via Global Planning-Guided Progressive Reinforcement Learningcited by 11
  11. 2025MobileA3gent: Training Mobile GUI Agents Using Decentralized Self-Sourced Data from Diverse Userscited by 10
  12. 2025Unleashing Embodied Task Planning Ability in LLMs via Reinforcement Learningcited by 9
  13. 2025Memento No More: Coaching AI Agents to Master Multiple Tasks via Hints Internalizationcited by 8
  14. 2025Agentic Knowledgeable Self-awarenesscited by 8
  15. 2025LatentEvolve: Self-Evolving Test-Time Scaling in Latent Spacecited by 8
  16. 2026Learning How to Remember: A Meta-Cognitive Management Method for Structured and Transferable Agent Memorycited by 8
  17. 2025Exploring Expert Failures Improves LLM Agent Tuningcited by 7
  18. 2025ActionStudio: A Lightweight Framework for Data and Training of Large Action Modelscited by 6
  19. 2025PLAN-TUNING: Post-Training Language Models to Learn Step-by-Step Planning for Complex Problem Solvingcited by 6
  20. 2026PABU: Progress-Aware Belief Update for Efficient LLM Agentscited by 6
  21. 2026LMEB: Long-horizon Memory Embedding Benchmarkcited by 6
  22. 2026RoboAgent: Chaining Basic Capabilities for Embodied Task Planningcited by 6
  23. 2026What Do Agents Learn from Trajectory-SFT: Semantics or Interfaces?cited by 4
  24. 2026LLM4Cov: Execution-Aware Agentic Learning for High-coverage Testbench Generationcited by 4
  25. 2025Matrix: Peer-to-Peer Multi-Agent Synthetic Data Generation Frameworkcited by 3
  26. 2026Supervised Fine-Tuning versus Reinforcement Learning: A Study of Post-Training Methods for Large Language Modelscited by 3
  27. 2026PACT: Privileged Trace Co-Training for Multi-Turn Tool-Use Agentscited by 3
  28. 2026IntentCUA: Learning Intent-level Representations for Skill Abstraction and Multi-Agent Planning in Computer-Use Agentscited by 2
  29. 2026MagicAgent: Towards Generalized Agent Planningcited by 2
  30. 2026StraTA: Incentivizing Agentic Reinforcement Learning with Strategic Trajectory Abstractioncited by 2
  31. 2025Disentangling Exploration of Large Language Models by Optimal Exploitationcited by 1
  32. 2025S3LoRA: Safe Spectral Sharpness-Guided Pruning in Adaptation of Agent Plannercited by 1
  33. 2025Bridging the Capability Gap: Joint Alignment Tuning for Harmonizing LLM-based Multi-Agent Systemscited by 1
  34. 2025COACH: Collaborative Agents for Contextual Highlighting -- A Multi-Agent Framework for Sports Video Analysiscited by 1
  35. 2026EO-Gym: A Multimodal, Interactive Environment for Earth Observation Agentscited by 1
  36. 2026RoboEvolve: Co-Evolving Planner-Simulator for Robotic Manipulation with Limited Datacited by 1
  37. 2026Plans You Can Check: Verifier-Grounded Learning of an Open-Weight Planner for Executable Video-Editingcited by 1
  38. 2026NeoHorse-1: Towards Recursive Self-Improvement via Agentic Post-Training with Routing Harnesscited by 1

50 most cited of 56 All 56 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025TRAJECT-Bench:A Trajectory-Aware Benchmark for Evaluating Agentic Tool Use
  2. 2026Long-Horizon Agent Trajectory Attribution: A Unified Benchmark and Fine-Grained Annotation Framework
  3. 2024AgentGym: Evolving Large Language Model-based Agents across Diverse Environments
  4. 2026Beyond Quantity: Trajectory Diversity Scaling for Code Agents
  5. 2025AgentRefine: Enhancing Agent Generalization through Refinement Tuning
  6. 2024Learning From Failure: Integrating Negative Examples when Fine-tuning Large Language Models as Agents
  7. 2023AgentBench: Evaluating LLMs as Agents
  8. 2024Agent-FLAN: Designing Data and Methods of Effective Agent Tuning for Large Language Models