mlsanityData to 7 Oct 2026

AvaTaR: Optimizing LLM Agents for Tool Usage via Contrastive Reasoning

arXiv 2406.11200 ↗First posted 17 Jun 2024cs.LG cs.CLcited by 69

On the map: LLM reasoning → Multimodal reasoning

also in 1 more
Abstract (arXiv)

Large language model (LLM) agents have demonstrated impressive capabilities in utilizing external tools and knowledge to boost accuracy and reduce hallucinations. However, developing prompting techniques that enable LLM agents to effectively use these tools and knowledge remains a heuristic and labor-intensive task. Here, we introduce AvaTaR, a novel and automated framework that optimizes an LLM agent to effectively leverage provided tools, improving performance on a given task. During optimization, we design a comparator module to iteratively deliver insightful and comprehensive prompts to the LLM agent by contrastively reasoning between positive and negative examples sampled from training data. We demonstrate AvaTaR on four complex multimodal retrieval datasets featuring textual, visual, and relational information, and three general question-answering (QA) datasets. We find AvaTaR consistently outperforms state-of-the-art approaches across all seven tasks, exhibiting strong generalization ability when applied to novel cases and achieving an average relative improvement of 14% on the Hit@1 metric for the retrieval datasets and 13% for the QA datasets. Code and dataset are available at https://github.com/zou-group/avatar.

Key facts. Cited by 69 papers in the map (data through 7 Oct 2026). Placed in Multimodal reasoning, one of 17 directions in LLM reasoning. Builds on 42 of its 59 references that are in the map. First posted on arXiv 17 Jun 2024.

Builds on

42 of 59 references.

References · 42

  1. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  2. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
  3. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,601
  4. 2023Toolformer: Language Models Can Teach Themselves to Use Toolscited by 4,072
  5. 2023Reflexion: Language Agents with Verbal Reinforcement Learningcited by 4,064
  6. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,779
  7. 2018HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answeringcited by 3,686
  8. 2023Self-Refine: Iterative Refinement with Self-Feedbackcited by 3,317
  9. 2020REALM: Retrieval-Augmented Language Model Pre-Trainingcited by 2,126
  10. 2023ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIscited by 1,880
  11. 2021WebGPT: Browser-assisted question-answering with human feedbackcited by 1,722
  12. 2015Flickr30k Entities: Collecting Region-to-Phrase Correspondences for Richer Image-to-Sentence Modelscited by 1,352
30 more
  1. 2023Gorilla: Large Language Model Connected with Massive APIscited by 1,302
  2. 2021Improving language models by retrieving from trillions of tokenscited by 1,278
  3. 2023HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in Hugging Facecited by 1,173
  4. 2022Inner Monologue: Embodied Reasoning through Planning with Language Modelscited by 1,057
  5. 2022Language Models as Zero-Shot Planners: Extracting Actionable Knowledge for Embodied Agentscited by 1,029
  6. 2022Large Language Models Are Human-Level Prompt Engineerscited by 1,020
  7. 2023Teaching Large Language Models to Self-Debugcited by 963
  8. 2023Graph of Thoughts: Solving Elaborate Problems with Large Language Modelscited by 873
  9. 2023ExpeL: LLM Agents Are Experiential Learnerscited by 814
  10. 2023API-Bank: A Comprehensive Benchmark for Tool-Augmented LLMscited by 574
  11. 2021QA-GNN: Reasoning with Language Models and Knowledge Graphs for Question Answeringcited by 386
  12. 2022RLPrompt: Optimizing Discrete Text Prompts with Reinforcement Learningcited by 361
  13. 2023Is ChatGPT Good at Search? Investigating Large Language Models as Re-Ranking Agentscited by 356
  14. 2023Check Your Facts and Try Again: Improving Large Language Models with External Knowledge and Automated Feedbackcited by 351
  15. 2023Large Language Models for Information Retrieval: A Surveycited by 331
  16. 2023AgentTuning: Enabling Generalized Agent Abilities for LLMscited by 319
  17. 2022Demonstrate-Search-Predict: Composing retrieval and language models for knowledge-intensive NLPcited by 316
  18. 2023Large Language Models are Zero-Shot Rankers for Recommender Systemscited by 307
  19. 2023ToolQA: A Dataset for LLM Question Answering with External Toolscited by 273
  20. 2023FireAct: Toward Language Agent Fine-tuningcited by 247
  21. 2023GPT4Tools: Teaching Large Language Model to Use Tools via Self-instructioncited by 245
  22. 2023MetaTool Benchmark for Large Language Models: Deciding Whether to Use Tools and Which to Usecited by 209
  23. 2024Agent AI: Surveying the Horizons of Multimodal Interactioncited by 167
  24. 2023Hypothesis Search: Inductive Reasoning with Language Modelscited by 119
  25. 2023Retroformer: Retrospective Large Language Agents with Policy Gradient Optimizationcited by 110
  26. 2023WebCPM: Interactive Web Search for Chinese Long-form Question Answeringcited by 93
  27. 2023MindAgent: Emergent Gaming Interactioncited by 87
  28. 2023Hierarchical Prompting Assists Large Language Model on Web Navigationcited by 36
  29. 2023Outline, Then Details: Syntactically Guided Coarse-To-Fine Code Generationcited by 27
  30. 2024Triad: A Framework Leveraging a Multi-Role LLM-based Agent to Solve Knowledge Base Question Answeringcited by 18

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 6; 2025: 40; 2026: 23.

69 papers.

Sort:

By area:

  1. 2025Model Context Protocol (MCP): Landscape, Security Threats, and Future Research Directionscited by 257
  2. 2025Large Language Model Agent: A Survey on Methodology, Applications and Challengescited by 194
  3. 2025Deep Research Agents: A Systematic Examination And Roadmapcited by 122
  4. 2025Deep Research: A Survey of Autonomous Research Agentscited by 63
  5. 2025A Survey of LLM-Driven AI Agent Communication: Protocols, Security Risks, and Defense Countermeasurescited by 54
  6. 2026Taming Various Privilege Escalation in LLM-Based Agent Systems: A Mandatory Access Control Frameworkcited by 50
  7. 2025LLM-based Agents Suffer from Hallucinations: A Survey of Taxonomy, Methods, and Directionscited by 49
  8. 2025A Survey on the Optimization of Large Language Model-based Agentscited by 45
  9. 2025ContextAgent: Context-Aware Proactive LLM Agents with Open-World Sensory Perceptionscited by 44
  10. 2025Towards Agentic RAG with Deep Reasoning: A Survey of RAG-Reasoning Systems in LLMscited by 40
  11. 2025AgentArmor: Enforcing Program Analysis on Agent Runtime Trace to Defend Against Prompt Injectioncited by 39
  12. 2025From Language to Action: A Review of Large Language Models as Autonomous Agents and Tool Userscited by 32
38 more
  1. 2025A Survey of Large Language Model Empowered Agents for Recommendation and Search: Towards Next-Generation Information Retrievalcited by 31
  2. 2024BattleAgentBench: A Benchmark for Evaluating Cooperation and Competition Capabilities of Language Models in Multi-Agent Systemscited by 26
  3. 2024Knowledge-Aware Query Expansion with Large Language Models for Textual and Relational Retrievalcited by 24
  4. 2024Aviary: training language agents on challenging scientific taskscited by 23
  5. 2025Optimas: Optimizing Compound AI Systems with Globally Aligned Local Rewardscited by 23
  6. 2025Heterogeneous Swarms: Jointly Optimizing Model Roles and Weights for Multi-LLM Systemscited by 22
  7. 2025O2-Searcher: A Searching-based Agent Model for Open-Domain Open-Ended Question Answeringcited by 22
  8. 2025ToolScope: Enhancing LLM Agent Tool Use through Tool Merging and Context-Aware Filteringcited by 19
  9. 2025ToolVQA: A Dataset for Multi-step Reasoning VQA with External Toolscited by 13
  10. 2025SHIELDA: Structured Handling of Exceptions in LLM-Driven Agentic Workflowscited by 12
  11. 2025Automated Composition of Agents: A Knapsack Approach for Agentic Component Selectioncited by 10
  12. 2025Mixture of Structural-and-Textual Retrieval over Text-rich Graph Knowledge Basescited by 9
  13. 2025TPS-Bench: Evaluating AI Agents' Tool Planning & Scheduling Abilities in Compounding Taskscited by 9
  14. 2025Memento No More: Coaching AI Agents to Master Multiple Tasks via Hints Internalizationcited by 8
  15. 2024CAMPHOR: Collaborative Agents for Multi-input Planning and High-Order Reasoning On Devicecited by 6
  16. 2024RiTeK: A Dataset for Large Language Models Complex Reasoning over Textual Knowledge Graphs in Medicinecited by 6
  17. 2026Uncertainty-Aware Clarification in LLM Agents with Information Gaincited by 6
  18. 2025GraphRAFT: Retrieval Augmented Fine-Tuning for Knowledge Graphs on Graph Databasescited by 5
  19. 2025DICE: Dynamic In-Context Example Selection in LLM Agents via Efficient Knowledge Transfercited by 5
  20. 2026AEM: Adaptive Entropy Modulation for Multi-Turn Agentic Reinforcement Learningcited by 5
  21. 2025Towards Pervasive Distributed Agentic Generative AI -- A State of The Artcited by 4
  22. 2026Optimizing Agentic Workflows using Meta-toolscited by 4
  23. 2026Learning to Rewrite Tool Descriptions for Reliable LLM-Agent Tool Usecited by 4
  24. 2026JTPRO: A Joint Tool-Prompt Reflective Optimization Framework for Language Agentscited by 4
  25. 2024Multi-Field Adaptive Retrievalcited by 3
  26. 2025GATE: Graph-based Adaptive Tool Evolution Across Diverse Taskscited by 3
  27. 2025AgentDR: Dynamic Recommendation with Implicit Item-Item Relations via LLM-based Agentscited by 3
  28. 2025ShapeCraft: LLM Agents for Structured, Textured and Interactive 3D Modelingcited by 3
  29. 2026Vinedresser3D: Agentic Text-guided 3D Editingcited by 3
  30. 2025Querying Databases with Function Callingcited by 2
  31. 2025Self Iterative Label Refinement via Robust Unlabeled Learningcited by 2
  32. 2025Autofocus Retrieval: An Effective Pipeline for Multi-Hop Question Answering With Semi-Structured Knowledgecited by 2
  33. 2025OMAC: A Holistic Optimization Framework for LLM-Based Multi-Agent Collaborationcited by 2
  34. 2025A Red Teaming Roadmap Towards System-Level Safetycited by 2
  35. 2026JudgeFlow: Agentic Workflow Optimization via Block Judgecited by 2
  36. 2026Autonomous Knowledge Graph Exploration with Adaptive Breadth-Depth Retrievalcited by 2
  37. 2025MATRIX: Multimodal Agent Tuning for Robust Tool-Use Reasoningcited by 1
  38. 2025A Multidisciplinary Design and Optimization (MDO) Agent Driven by Large Language Modelscited by 1

50 most cited of 69 All 69 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2023Large Language Model (LLM) as a System of Multiple Expert Agents: An Approach to solve the Abstraction and Reasoning Corpus (ARC) Challenge
  2. 2025MMAT-1M: A Large Reasoning Dataset for Multimodal Agent Tuning
  3. 2024Large Multimodal Agents: A Survey
  4. 2025Rethinking Information Synthesis in Multimodal Question Answering A Multi-Agent Perspective
  5. 2026MC-Search: Evaluating and Enhancing Multimodal Agentic Search with Structured Long Reasoning Chains
  6. 2025A Survey of Large Language Model Agents for Question Answering
  7. 2024MLLM-Tool: A Multimodal Large Language Model For Tool Agent Learning
  8. 2024HAMMR: HierArchical MultiModal React agents for generic VQA