mlsanityData to 7 Oct 2026

Hephaestus: Improving Fundamental Agent Capabilities of Large Language Models through Continual Pre-Training

arXiv 2502.06589 ↗First posted 10 Feb 2025cs.CL cs.AI cs.LGcited by 6

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

Abstract (arXiv)

Due to the scarcity of agent-oriented pre-training data, LLM-based autonomous agents typically rely on complex prompting or extensive fine-tuning, which often fails to introduce new capabilities while preserving strong generalizability. We introduce Hephaestus-Forge, the first large-scale pre-training corpus designed to enhance the fundamental capabilities of LLM agents in API function calling, intrinsic reasoning and planning, and adapting to environmental feedback. Hephaestus-Forge comprises 103B agent-specific data encompassing 76,537 APIs, including both tool documentation to introduce knowledge of API functions and function calling trajectories to strengthen intrinsic reasoning. To explore effective training protocols, we investigate scaling laws to identify the optimal recipe in data mixing ratios. By continual pre-training on Hephaestus-Forge, Hephaestus outperforms small- to medium-scale open-source LLMs and rivals commercial LLMs on three agent benchmarks, demonstrating the effectiveness of our pre-training corpus in enhancing fundamental agentic capabilities and generalization of LLMs to new tasks or environments.

Key facts. Cited by 6 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 72 of its 100 references that are in the map. First posted on arXiv 10 Feb 2025.

Builds on

72 of 100 references.

Closest ancestors · 10

Same direction, newest first

  1. 2024xLAM: A Family of Large Action Models to Empower AI Agent Systems5 Sep
  2. 2024AgentGym: Evolving Large Language Model-based Agents across Diverse Environments6 Jun
  3. 2024AgentOhana: Design Unified Data and Training Pipeline for Effective Agent Learning23 Feb
  4. 2024Learning From Failure: Integrating Negative Examples when Fine-tuning Large Language Models as Agents18 Feb
  5. 2023Agent Lumos: Unified and Modular Training for Open-Source Language Agents9 Nov
  6. 2023AgentTuning: Enabling Generalized Agent Abilities for LLMs19 Oct
  7. 2023Lemur: Harmonizing Natural Language and Code for Language Agents10 Oct
  8. 2023FireAct: Toward Language Agent Fine-tuning9 Oct
  9. 2023SwiftSage: A Generative Agent with Fast and Slow Thinking for Complex Interactive Tasks27 May
  10. 2023AdaPlanner: Adaptive Planning from Feedback with Language Models26 May

Other references · 62

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2020Language Models are Few-Shot Learnerscited by 32,199
  3. 2023GPT-4 Technical Reportcited by 18,132
  4. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
  5. 2024The Llama 3 Herd of Modelscited by 14,192
  6. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 12,865
  7. 2021Training Verifiers to Solve Math Word Problemscited by 9,743
  8. 2024DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Modelscited by 8,851
  9. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
  10. 2021Evaluating Large Language Models Trained on Codecited by 8,053
  11. 2020Measuring Massive Multitask Language Understandingcited by 7,768
  12. 2020Scaling Laws for Neural Language Modelscited by 6,411
38 more
  1. 2023Toolformer: Language Models Can Teach Themselves to Use Toolscited by 4,072
  2. 2019HellaSwag: Can a Machine Really Finish Your Sentence?cited by 4,018
  3. 2018HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answeringcited by 3,686
  4. 2024Gemini 1.5: Unlocking multimodal understanding across millions of tokens of contextcited by 3,175
  5. 2022Training Compute-Optimal Large Language Modelscited by 2,927
  6. 2023Code Llama: Open Foundation Models for Codecited by 2,105
  7. 2023ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIscited by 1,880
  8. 2022Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Themcited by 1,767
  9. 2023Is Your Code Generated by ChatGPT Really Correct? Rigorous Evaluation of Large Language Models for Code Generationcited by 1,332
  10. 2023Gorilla: Large Language Model Connected with Massive APIscited by 1,302
  11. 2020ALFWorld: Aligning Text and Embodied Environments for Interactive Learningcited by 1,143
  12. 2024The FineWeb Datasets: Decanting the Web for the Finest Text Data at Scalecited by 1,104
  13. 2024DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Modelcited by 1,093
  14. 2023LIMA: Less Is More for Alignmentcited by 1,080
  15. 2022CodeGen: An Open Large Language Model for Code with Multi-Turn Program Synthesiscited by 876
  16. 2023API-Bank: A Comprehensive Benchmark for Tool-Augmented LLMscited by 574
  17. 2024StarCoder 2 and The Stack v2: The Next Generationcited by 484
  18. 2023GPT-4 Is Too Smart To Be Safe: Stealthy Chat with LLMs via Ciphercited by 401
  19. 2023ToolAlpaca: Generalized Tool Learning for Language Models with 3000 Simulated Casescited by 383
  20. 2022PlanBench: An Extensible Benchmark for Evaluating Large Language Models on Planning and Reasoning about Changecited by 372
  21. 2016FastText.zip: Compressing text classification modelscited by 331
  22. 2023Multi-step Jailbreaking Privacy Attacks on ChatGPTcited by 320
  23. 2023EmbodiedGPT: Vision-Language Pre-Training via Embodied Chain of Thoughtcited by 276
  24. 2023ToolQA: A Dataset for LLM Question Answering with External Toolscited by 273
  25. 2023ToolkenGPT: Augmenting Frozen Language Models with Massive Tools via Tool Embeddingscited by 238
  26. 2023Proving Test Set Contamination in Black Box Language Modelscited by 227
  27. 2021New Insights on Reducing Abrupt Representation Change in Online Continual Learningcited by 215
  28. 2024ToolACE: Winning the Points of LLM Function Callingcited by 204
  29. 2024Advancing LLM Reasoning Generalists with Preference Treescited by 191
  30. 2024APIGen: Automated Pipeline for Generating Verifiable and Diverse Function-Calling Datasetscited by 188
  31. 2023OpenWebMath: An Open Dataset of High-Quality Mathematical Web Textcited by 151
  32. 2024OpenMathInstruct-1: A 1.8 Million Math Instruction Tuning Datasetcited by 143
  33. 2023TaskBench: Benchmarking Large Language Models for Task Automationcited by 138
  34. 2023RestGPT: Connecting Large Language Models with Real-World RESTful APIscited by 129
  35. 2023ToolChain*: Efficient Action Space Navigation in Large Language Models with A* Searchcited by 103
  36. 2023T-Eval: Evaluating the Tool Utilization Capability of Large Language Models Step by Stepcited by 91
  37. 2024Planning, Creation, Usage: Benchmarking LLMs for Comprehensive Tool Utilization in Real-World Complex Scenarioscited by 85
  38. 2024Pandora: Towards General World Model with Natural Language Actions and Video Statescited by 83

50 most cited of 62 All 62 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 4; 2026: 2.

6 papers.

  1. 2025AgentRL: Scaling Agentic Reinforcement Learning with a Multi-Turn, Multi-Task Frameworkcited by 58
  2. 2025ScaleMCP: Dynamic and Auto-Synchronizing Model Context Protocol Tools for LLM Agentscited by 36
  3. 2025MemTool: Optimizing Short-Term Memory Management for Dynamic Tool Calling in LLM Agent Multi-Turn Conversationscited by 21
  4. 2025WorkForceAgent-R1: Incentivizing Reasoning Capability in LLM-based Web Agents via Reinforcement Learningcited by 7
  5. 2026Entropy Pacing Policy Optimization for Multi-Task Agentic Reinforcement Learningcited by 0
  6. 2026When Does Action Credit Need Updating?cited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025AgentFrontier: Expanding the Capability Frontier of LLM Agents with ZPD-Guided Data Synthesis
  2. 2024Enhancing the General Agent Capabilities of Low-Parameter LLMs through Tuning and Multi-Branch Reasoning
  3. 2025Youtu-LLM: Unlocking the Native Agentic Potential for Lightweight Large Language Models
  4. 2024Offline Training of Language Model Agents with Functions as Learnable Weights
  5. 2024Agent-FLAN: Designing Data and Methods of Effective Agent Tuning for Large Language Models
  6. 2023A Survey on Large Language Model based Autonomous Agents
  7. 2024Small LLMs Are Weak Tool Learners: A Multi-LLM Agent
  8. 2024AgentQuest: A Modular Benchmark Framework to Measure Progress and Improve LLM Agents