mlsanityData to 7 Oct 2026

Towards Rationality in Language and Multimodal Agents: A Survey

arXiv 2406.00252 ↗First posted 1 Jun 2024cs.AI cs.CL cs.CVcited by 15

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

Abstract (arXiv)

This work discusses how to build more rational language and multimodal agents and what criteria define rationality in intelligent systems. Rationality is the quality of being guided by reason, characterized by decision-making that aligns with evidence and logical principles. It plays a crucial role in reliable problem-solving by ensuring well-grounded and consistent solutions. Despite their progress, large language models (LLMs) often fall short of rationality due to their bounded knowledge space and inconsistent outputs. In response, recent efforts have shifted toward developing multimodal and multi-agent systems, as well as integrating modules like external tools, programming codes, symbolic reasoners, utility function, and conformal risk controls rather than relying solely on a single LLM for decision-making. This paper surveys state-of-the-art advancements in language and multimodal agents, assesses their role in enhancing rationality, and outlines open challenges and future research directions. We maintain an open repository at https://github.com/bowen-upenn/Agent_Rationality.

Key facts. Cited by 15 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 135 of its 209 references that are in the map. First posted on arXiv 1 Jun 2024.

Builds on

135 of 209 references.

Closest ancestors · 8

Same direction, newest first

  1. 2024Large Language Model Evaluation Via Multi AI Agents: Preliminary results1 Apr
  2. 2024Benchmark Self-Evolving: A Multi-Agent Framework for Dynamic LLM Evaluation18 Feb
  3. 2024AgentBoard: An Analytical Evaluation Board of Multi-turn LLM Agents24 Jan
  4. 2024Large Language Models Are Neurosymbolic Reasoners17 Jan
  5. 2024Small LLMs Are Weak Tool Learners: A Multi-LLM Agent14 Jan
  6. 2024Exploring Large Language Model based Intelligent Agents: Definitions, Methods, and Prospects7 Jan
  7. 2023ChatEval: Towards Better LLM-based Evaluators through Multi-Agent Debate14 Aug
  8. 2023MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework1 Aug

Other references · 127

  1. 2017Attention Is All You Needcited by 59,932
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  3. 2022Training language models to follow instructions with human feedbackcited by 15,712
  4. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  5. 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,393
  6. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,601
  7. 2021Measuring Mathematical Problem Solving With the MATH Datasetcited by 5,203
  8. 2023Improved Baselines with Visual Instruction Tuningcited by 4,362
  9. 2023Toolformer: Language Models Can Teach Themselves to Use Toolscited by 4,072
  10. 2022Robust Speech Recognition via Large-Scale Weak Supervisioncited by 3,972
  11. 2021On the Opportunities and Risks of Foundation Modelscited by 3,961
  12. 2018HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answeringcited by 3,686
38 more
  1. 2022Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedbackcited by 3,634
  2. 2023Generative Agents: Interactive Simulacra of Human Behaviorcited by 3,500
  3. 2023Lost in the Middle: How Language Models Use Long Contextscited by 3,383
  4. 2023Self-Refine: Iterative Refinement with Self-Feedbackcited by 3,317
  5. 2024Gemini 1.5: Unlocking multimodal understanding across millions of tokens of contextcited by 3,175
  6. 2023InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuningcited by 2,855
  7. 2023Sparks of Artificial General Intelligence: Early experiments with GPT-4cited by 2,579
  8. 2020Learning to summarize from human feedbackcited by 2,562
  9. 2019ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Taskscited by 2,219
  10. 2023G-Eval: NLG Evaluation using GPT-4 with Better Human Alignmentcited by 2,205
  11. 2018CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledgecited by 1,793
  12. 2023Improving Factuality and Reasoning in Language Models through Multiagent Debatecited by 1,739
  13. 2021WebGPT: Browser-assisted question-answering with human feedbackcited by 1,722
  14. 2023A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questionscited by 1,582
  15. 2023Mind2Web: Towards a Generalist Agent for the Webcited by 1,210
  16. 2022WebShop: Towards Scalable Real-World Web Interaction with Grounded Language Agentscited by 1,197
  17. 2021Fantastically Ordered Prompts and Where to Find Them: Overcoming Few-Shot Prompt Order Sensitivitycited by 1,122
  18. 2023Large Language Models are not Fair Evaluatorscited by 1,050
  19. 2023Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debatecited by 995
  20. 2019VL-BERT: Pre-training of Generic Visual-Linguistic Representationscited by 954
  21. 2023Can LLMs Express Their Uncertainty? An Empirical Evaluation of Confidence Elicitation in LLMscited by 946
  22. 2023A Multitask, Multilingual, Multimodal Evaluation of ChatGPT on Reasoning, Hallucination, and Interactivitycited by 888
  23. 2023Large Language Models Can Be Easily Distracted by Irrelevant Contextcited by 820
  24. 2022PaLI: A Jointly-Scaled Multilingual Language-Image Modelcited by 762
  25. 2023Can Large Language Models Be an Alternative to Human Evaluations?cited by 729
  26. 2023Aligning Large Multimodal Models with Factually Augmented RLHFcited by 703
  27. 2018Object Hallucination in Image Captioningcited by 661
  28. 2024LLM Evaluators Recognize and Favor Their Own Generationscited by 651
  29. 2024A Survey on the Memory Mechanism of Large Language Model based Agentscited by 622
  30. 2020Knowledge Graphscited by 619
  31. 2023RLAIF vs. RLHF: Scaling Reinforcement Learning from Human Feedback with AI Feedbackcited by 615
  32. 2022AudioLM: a Language Modeling Approach to Audio Generationcited by 611
  33. 2023ViperGPT: Visual Inference via Python Execution for Reasoningcited by 591
  34. 2024GPT-4V(ision) is a Generalist Web Agent, if Groundedcited by 547
  35. 2023SpeechGPT: Empowering Large Language Models with Intrinsic Cross-Modal Conversational Abilitiescited by 518
  36. 2023Are Emergent Abilities of Large Language Models a Mirage?cited by 515
  37. 2022Image as a Foreign Language: BEiT Pretraining for All Vision and Vision-Language Taskscited by 510
  38. 2022Visual Programming: Compositional visual reasoning without trainingcited by 507

50 most cited of 127 All 127 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 6; 2025: 2; 2026: 7.

15 papers.

Sort:

By area:

  1. 2024MMSearch: Benchmarking the Potential of Large Models as Multi-modal Search Enginescited by 98
  2. 2024Evaluating Modern Approaches in 3D Scene Reconstruction: NeRF vs Gaussian-Based Methodscited by 16
  3. 2026Seeing Is Not Screening: Multimodal Hidden Instruction Attacks on Agent Skill Scannerscited by 5
  4. 2026ProMMSearchAgent: A Generalizable Multimodal Search Agent Trained with Process-Oriented Rewardscited by 4
  5. 2025Deliberate Planning in Language Models with Symbolic Representationcited by 3
  6. 2024Balancing Rigor and Utility: Mitigating Cognitive Biases in Large Language Models for Multiple-Choice Questionscited by 2
  7. 2026When Agents Evolve, Institutions Followcited by 1
  8. 2024Pre-trained Graphformer-based Ranking at Web-scale Search (Extended Abstract)cited by 0
  9. 2024Generative Pre-trained Ranking Model with Over-parameterization at Web-Scale (Extended Abstract)cited by 0
  10. 2024Bridging the Gap: Representation Spaces in Neuro-Symbolic AIcited by 0
  11. 2025GeoGrid-Bench: Can Foundation Models Understand Multimodal Gridded Geo-Spatial Data?cited by 0
  12. 2026SSL: Sweet Spot Learning for Differentiated Guidance in Agentic Optimizationcited by 0
3 more
  1. 2026SemBench: A Universal Semantic Framework for LLM Evaluationcited by 0
  2. 2026LLM Consumer Behavior Theory: Foundations of a Novel Research Fieldcited by 0
  3. 2026DeAR: Decentralized Agentic Reasoning via Capability Grounding and Collaborative Thought Navigationcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024Comparing Rationality Between Large Language Models and Humans: Insights and Open Questions
  2. 2025A Survey on Agentic Multimodal Large Language Models
  3. 2024STEER: Assessing the Economic Rationality of Large Language Models
  4. 2024Unlocking the Wisdom of Large Language Models: An Introduction to The Path to Artificial General Intelligence
  5. 2025LLM-based Agentic Reasoning Frameworks: A Survey from Methods to Scenarios
  6. 2026A Survey on Foundations and Frontiers of Multimodal Agentic Frameworks: Techniques and Applications
  7. 2025Agentic Large Language Models, a survey
  8. 2025Language-Informed Synthesis of Rational Agent Models for Grounded Theory-of-Mind Reasoning On-The-Fly