mlsanityData to 14 Oct 2026

Husky: A Unified, Open-Source Language Agent for Multi-Step Reasoning

arXiv 2406.06469 ↗First posted 10 Jun 2024cs.AI cs.CL cs.LGcited by 16

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

Abstract (arXiv)

Language agents perform complex tasks by using tools to execute each step precisely. However, most existing agents are based on proprietary models or designed to target specific tasks, such as mathematics or multi-hop question answering. We introduce Husky, a holistic, open-source language agent that learns to reason over a unified action space to address a diverse set of complex tasks involving numerical, tabular, and knowledge-based reasoning. Husky iterates between two stages: 1) generating the next action to take towards solving a given task and 2) executing the action using expert models and updating the current solution state. We identify a thorough ontology of actions for addressing complex tasks and curate high-quality data to train expert models for executing these actions. Our experiments show that Husky outperforms prior language agents across 14 evaluation datasets. Moreover, we introduce HuskyQA, a new evaluation set which stress tests language agents for mixed-tool reasoning, with a focus on retrieving missing knowledge and performing numerical reasoning. Despite using 7B models, Husky matches or even exceeds frontier LMs such as GPT-4 on these tasks, showcasing the efficacy of our holistic approach in addressing complex reasoning problems. Our code and models are available at https://github.com/agent-husky/Husky-v1.

Key facts. Cited by 16 papers in the map (data through 14 Oct 2026). Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use. Builds on 53 of its 101 references that are in the map. First posted on arXiv 10 Jun 2024.

Builds on

53 of 101 references.

Closest ancestors · 3

Same direction, newest first

  1. 2023AgentTuning: Enabling Generalized Agent Abilities for LLMs19 Oct
  2. 2023FireAct: Toward Language Agent Fine-tuning9 Oct
  3. 2023Language Agent Tree Search Unifies Reasoning Acting and Planning in Language Models6 Oct

Other references · 50

  1. 2023GPT-4 Technical Reportcited by 18,396
  2. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 13,028
  3. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
  4. 2021Training Verifiers to Solve Math Word Problemscited by 10,109
  5. 2024DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Modelscited by 9,379
  6. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,695
  7. 2023Efficient Memory Management for Large Language Model Serving with PagedAttentioncited by 5,944
  8. 2021Measuring Mathematical Problem Solving With the MATH Datasetcited by 5,371
  9. 2023Reflexion: Language Agents with Verbal Reinforcement Learningcited by 4,276
  10. 2023Toolformer: Language Models Can Teach Themselves to Use Toolscited by 4,182
  11. 2018HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answeringcited by 3,754
  12. 2023Self-Refine: Iterative Refinement with Self-Feedbackcited by 3,442
38 more
  1. 2022Self-Instruct: Aligning Language Models with Self-Generated Instructionscited by 2,724
  2. 2023ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIscited by 1,947
  3. 2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflectioncited by 1,839
  4. 2021Multitask Prompted Training Enables Zero-Shot Task Generalizationcited by 1,470
  5. 2023Gorilla: Large Language Model Connected with Massive APIscited by 1,332
  6. 2019ZeRO: Memory Optimizations Toward Training Trillion Parameter Modelscited by 1,301
  7. 2023FActScore: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generationcited by 1,282
  8. 2023HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in Hugging Facecited by 1,190
  9. 2024DeepSeek-Coder: When the Large Language Model Meets Programming -- The Rise of Code Intelligencecited by 1,181
  10. 2022When Not to Trust Language Models: Investigating Effectiveness of Parametric and Non-Parametric Memoriescited by 1,128
  11. 2023GAIA: a benchmark for General AI Assistantscited by 1,128
  12. 2022Measuring and Narrowing the Compositionality Gap in Language Modelscited by 1,075
  13. 2022Language Models as Zero-Shot Planners: Extracting Actionable Knowledge for Embodied Agentscited by 1,035
  14. 2021MuSiQue: Multihop Questions via Single-hop Question Compositioncited by 916
  15. 2019DROP: A Reading Comprehension Benchmark Requiring Discrete Reasoning Over Paragraphscited by 903
  16. 2021Are NLP Models really able to Solve Simple Math Word Problems?cited by 878
  17. 2023CRITIC: Large Language Models Can Self-Correct with Tool-Interactive Critiquingcited by 783
  18. 2021Did Aristotle Use a Laptop? A Question Answering Benchmark with Implicit Reasoning Strategiescited by 743
  19. 2019MathQA: Towards Interpretable Math Word Problem Solving with Operation-Based Formalismscited by 662
  20. 2023API-Bank: A Comprehensive Benchmark for Tool-Augmented LLMscited by 591
  21. 2021FinQA: A Dataset of Numerical Reasoning over Financial Datacited by 562
  22. 2018The Web as a Knowledge-base for Answering Complex Questionscited by 410
  23. 2021TAT-QA: A Question Answering Benchmark on a Hybrid of Tabular and Textual Content in Financecited by 408
  24. 2023Chameleon: Plug-and-Play Compositional Reasoning with Large Language Modelscited by 356
  25. 2022Dynamic Prompt Learning via Policy Gradient for Semi-structured Mathematical Reasoningcited by 350
  26. 2019Analysing Mathematical Reasoning Abilities of Neural Modelscited by 335
  27. 2023ToRA: A Tool-Integrated Reasoning Agent for Mathematical Problem Solvingcited by 282
  28. 2021Symbolic Knowledge Distillation: from General Language Models to Commonsense Modelscited by 270
  29. 2023ToolkenGPT: Augmenting Frozen Language Models with Massive Tools via Tool Embeddingscited by 240
  30. 2023Camels in a Changing Climate: Enhancing LM Adaptation with Tulu 2cited by 229
  31. 2023PIXIU: A Large Language Model, Instruction Data and Evaluation Benchmark for Financecited by 222
  32. 2023ART: Automatic multi-step reasoning and tool-use for large language modelscited by 197
  33. 2023ReWOO: Decoupling Reasoning from Observations for Efficient Augmented Language Modelscited by 184
  34. 2021MultiModalQA: Complex Question Answering over Text, Tables and Imagescited by 179
  35. 2023ReST meets ReAct: Self-Improvement for Multi-Step Reasoning LLM Agentcited by 81
  36. 2024SciAgent: Tool-augmented Language Models for Scientific Reasoningcited by 70
  37. 2020IIRC: A Dataset of Incomplete Information Reading Comprehension Questionscited by 53
  38. 2023The ART of LLM Refinement: Ask, Refine, and Trustcited by 29

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 8; 2025: 3; 2026: 5.

16 papers.

Sort:

By area:

  1. 2024DINO-X: A Unified Vision Model for Open-World Object Detection and Understandingcited by 89
  2. 2024Cocoa: Co-Planning and Co-Execution with AI Agentscited by 39
  3. 2024Agent-Oriented Planning in Multi-Agent Systemscited by 36
  4. 2025CER: Confidence Enhanced Reasoning in LLMscited by 17
  5. 2025A2Flow: Automating Agentic Workflow Generation via Self-Adaptive Abstraction Operatorscited by 14
  6. 2024TART: An Open-Source Tool-Augmented Framework for Explainable Table-based Reasoningcited by 10
  7. 2026Quantifying Trust: Financial Risk Management for Trustworthy AI Agentscited by 8
  8. 2024CoverBench: A Challenging Benchmark for Complex Claim Verificationcited by 6
  9. 2024Knowledge Graph Modeling-Driven Large Language Model Operating System (LLM OS) for Task Automation in Process Engineering Problem-Solvingcited by 4
  10. 2025EmbodiedAgent: A Scalable Hierarchical Approach to Overcome Practical Challenge in Multi-Robot Controlcited by 3
  11. 2026Do Agents Need to Plan Step-by-Step? Rethinking Planning Horizon in Data-Centric Tool Callingcited by 3
  12. 2026How to Steer Your Multi-Agent System: Human-LLM Collaborative Planningcited by 2
4 more
  1. 2024MATATA: Weakly Supervised End-to-End MAthematical Tool-Augmented Reasoning for Tabular Applicationscited by 1
  2. 2024Towards Adaptive Mechanism Activation in Language Agentcited by 0
  3. 2026DeALOG: Decentralized Multi-Agents Log-Mediated Reasoning Frameworkcited by 0
  4. 2026The Periodic Table of LLM Reasoning: A Structured Survey of Reasoning Paradigms, Methods, and Failure Modescited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024KG-Agent: An Efficient Autonomous Agent Framework for Complex Reasoning over Knowledge Graph
  2. 2025AgentMath: Empowering Mathematical Reasoning for Large Language Models via Tool-Augmented Agent
  3. 2023Corex: Pushing the Boundaries of Complex Reasoning through Multi-Model Collaboration
  4. 2024Sibyl: Simple yet Effective Agent Framework for Complex Real-world Reasoning
  5. 2025Distilling LLM Agent into Small Models with Retrieval and Code Tools
  6. 2025THOR: Tool-Integrated Hierarchical Optimization via RL for Mathematical Reasoning
  7. 2025Code-enabled language models can outperform reasoning models on diverse tasks
  8. 2025Tree of Agents: Improving Long-Context Capabilities of Large Language Models through Multi-Perspective Reasoning