mlsanityData to 14 Oct 2026

CollabLLM: From Passive Responders to Active Collaborators

arXiv 2502.00640 ↗First posted 2 Feb 2025cs.AIcited by 124

Not on the map. Why?

Cited by 40 in LLM agents and tool use, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Large Language Models are typically trained with next-turn rewards, limiting their ability to optimize for long-term interaction. As a result, they often respond passively to ambiguous or open-ended user requests, failing to help users reach their ultimate intents and leading to inefficient conversations. To address these limitations, we introduce CollabLLM, a novel and general training framework that enhances multiturn human-LLM collaboration. Its key innovation is a collaborative simulation that estimates the long-term contribution of responses using Multiturn-aware Rewards. By reinforcement fine-tuning these rewards, CollabLLM goes beyond responding to user requests, and actively uncovers user intent and offers insightful suggestions-a key step towards more human-centered AI. We also devise a multiturn interaction benchmark with three challenging tasks such as document creation. CollabLLM significantly outperforms our baselines with averages of 18.5% higher task performance and 46.3% improved interactivity by LLM judges. Finally, we conduct a large user study with 201 judges, where CollabLLM increases user satisfaction by 17.6% and reduces user spent time by 10.4%.

Key facts. Cited by 124 papers in the map (data through 14 Oct 2026). Builds on 41 of its 101 references that are in the map. First posted on arXiv 2 Feb 2025.

Builds on

41 of 101 references.

References · 41

  1. 2022Training language models to follow instructions with human feedbackcited by 15,971
  2. 2017Proximal Policy Optimization Algorithmscited by 15,215
  3. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,380
  4. 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,626
  5. 2023Direct Preference Optimization: Your Language Model is Secretly a Reward Modelcited by 8,065
  6. 2021Measuring Mathematical Problem Solving With the MATH Datasetcited by 5,371
  7. 2023A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questionscited by 1,601
  8. 2023Bias and Fairness in Large Language Models: A Surveycited by 639
  9. 2023RLAIF vs. RLHF: Scaling Reinforcement Learning from Human Feedback with AI Feedbackcited by 625
  10. 2024BigCodeBench: Benchmarking Code Generation with Diverse Function Calls and Complex Instructionscited by 546
  11. 2024ArCHer: Training Language Model Agents via Hierarchical Multi-Turn RLcited by 228
  12. 2018Neural Approaches to Conversational AIcited by 165
29 more
  1. 2023Rephrase and Respond: Let Large Language Models Ask Better Questions for Themselvescited by 123
  2. 2023Prompting and Evaluating Large Language Models for Proactive Dialogues: Clarification, Target-guided, and Non-collaborationcited by 116
  3. 2024STaR-GATE: Teaching Language Models to Ask Clarifying Questionscited by 104
  4. 2023Clarify When Necessary: Resolving Ambiguity Through Interaction with LMscited by 98
  5. 2023LMRL Gym: Benchmarks for Multi-Turn Reinforcement Learning with Language Modelscited by 88
  6. 2024Proactive Agent: Shifting LLM Agents from Reactive Responses to Active Assistancecited by 87
  7. 2024MT-Eval: A Multi-Turn Capabilities Evaluation Benchmark for Large Language Modelscited by 81
  8. 2023Plug-and-Play Policy Planner for Large Language Model Powered Dialogue Agentscited by 77
  9. 2024Multi-turn Reinforcement Learning from Preference Human Feedbackcited by 67
  10. 2024Direct Multi-Turn Preference Optimization for Language Agentscited by 64
  11. 2024Large Language Model Safety: A Holistic Surveycited by 59
  12. 2024Learning to Clarify: Multi-turn Conversations with Action-Based Contrastive Self-Trainingcited by 57
  13. 2019How to Build User Simulators to Train RL-based Dialog Systemscited by 46
  14. 2024Understanding User Experience in Large Language Model Interactionscited by 44
  15. 2023Tree of Clarifications: Answering Ambiguous Questions with Retrieval-Augmented Large Language Modelscited by 43
  16. 2024Into the Unknown Unknowns: Engaged Human Learning through Participation in Language Model Agent Conversationscited by 43
  17. 2023ClarifyGPT: Empowering LLM-based Code Generation with Intention Clarificationcited by 38
  18. 2023Zero-Shot Goal-Directed Dialogue via RL on Imagined Conversationscited by 38
  19. 2021Transferable Dialogue Systems and User Simulatorscited by 36
  20. 2023Controllable Mixed-Initiative Dialogue Generation through Promptingcited by 32
  21. 2023Unlocking the Potential of User Feedback: Leveraging Large Language Model as User Simulator to Enhance Dialogue Systemcited by 32
  22. 2024Regressing the Relative Future: Efficient Policy Optimization for Multi-turn RLHFcited by 30
  23. 2025A Survey on Multi-Turn Interaction Capabilities of Large Language Modelscited by 30
  24. 2023A Survey on Asking Clarification Questions Datasets in Conversational Systemscited by 28
  25. 2023Understanding Users' Dissatisfaction with ChatGPT Responses: Types, Resolving Tactics, and the Effect of Knowledge Levelcited by 26
  26. 2024CLARINET: Augmenting Language Models to Ask Clarification Questions for Retrievalcited by 20
  27. 2024Empowering Language Models with Active Inquiry for Deeper Understandingcited by 11
  28. 2023Asking More Informative Questions for Grounded Retrievalcited by 6
  29. 2023CIRCLE: Multi-Turn Query Clarifications with Reinforcement Learningcited by 4

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 30; 2026: 94.

124 papers.

Sort:

By area:

  1. 2025VAGEN: Reinforcing World Model Reasoning for Multi-Turn VLM Agentscited by 62
  2. 2025Training Proactive and Personalized LLM Agentscited by 46
  3. 2025Structured Uncertainty guided Clarification for LLM Agentscited by 41
  4. 2026HumanLM: Simulating Users with State Alignment Beats Response Imitationcited by 37
  5. 2025LLM-Based Human-Agent Collaboration and Interaction Systems: A Surveycited by 29
  6. 2025When One LLM Drools, Multi-LLM Collaboration Rulescited by 28
  7. 2025Can LLM Agents Simulate Multi-Turn Human Behavior? Evidence from Real Online Customer Behavior Datacited by 28
  8. 2025BED-LLM: Intelligent Information Gathering with LLMs and Bayesian Experimental Designcited by 24
  9. 2026AMemGym: Interactive Memory Benchmarking for Assistants in Long-Horizon Conversationscited by 20
  10. 2025BIRD-INTERACT: Re-imagining Text-to-SQL Evaluation for Large Language Models via Lens of Dynamic Interactionscited by 19
  11. 2026SWE-Together: Evaluating Coding Agents in Interactive User Sessionscited by 18
  12. 2026Calibrate-Then-Act: Cost-Aware Exploration in LLM Agentscited by 17
38 more
  1. 2025Teaching Language Models To Gather Information Proactivelycited by 14
  2. 2026When Users Change Their Mind: Evaluating Interruptible Agents in Long-Horizon Web Navigationcited by 14
  3. 2025TOM-SWE: User Mental Modeling For Software Engineering Agentscited by 13
  4. 2025The Collaboration Gap: Exploration and Benchmarking of Open-World Agentic Cooperationcited by 13
  5. 2025ToMAP: Training Opponent-Aware LLM Persuaders with Theory of Mindcited by 12
  6. 2026Value of Information: A Framework for Human-Agent Communicationcited by 12
  7. 2026InfoPO: Information-Driven Policy Optimization for User-Centric Agentscited by 12
  8. 2026Quantifying the Utility of User Simulators for Building Collaborative LLM Assistantscited by 10
  9. 2026Human-AI Co-design for Clinical Prediction Modelscited by 9
  10. 2026Breaking Contextual Inertia: Reinforcement Learning with Single-Turn Anchors for Stable Multi-Turn Interactioncited by 9
  11. 2025A Taxonomy of Prompt Defects in LLM Systemscited by 8
  12. 2025Moloch's Bargain: Emergent Misalignment When LLMs Compete for Audiencescited by 8
  13. 2026Learning Decentralized LLM Collaboration with Multi-Agent Actor Criticcited by 8
  14. 2026MLReplicate: Benchmarking Autonomous Research Systems for Machine Learning Reproducibilitycited by 8
  15. 2026MultiSessionCollab: Learning User Preferences with Memory to Improve Long-Term Collaborationcited by 7
  16. 2026PrefIx: Understand and Adapt to User Preference in Human-Agent Interactioncited by 7
  17. 2026Learning Next Action Predictors from Human-Computer Interactioncited by 7
  18. 2025Expert Preference-based Evaluation of Automated Related Work Generationcited by 6
  19. 2026DiscoverLLM: From Executing Intents to Discovering Themcited by 6
  20. 2026Measuring and Mitigating the Distributional Gap Between Real and Simulated User Behaviorscited by 6
  21. 2025Beyond Passive Critical Thinking: Fostering Proactive Questioning to Enhance Human-AI Collaborationcited by 5
  22. 2025Learning Steerable Clarification Policies with Collaborative Self-playcited by 5
  23. 2026PERM: Psychology-grounded Empathetic Reward Modeling for Large Language Modelscited by 5
  24. 2026DeepInnovator: Triggering the Innovative Capabilities of LLMscited by 5
  25. 2025Towards Pervasive Distributed Agentic Generative AI -- A State of The Artcited by 4
  26. 2025Reducing Belief Deviation in Reinforcement Learning for Active Reasoningcited by 4
  27. 2025Adamas: Hadamard Sparse Attention for Efficient Long-Context Inferencecited by 4
  28. 2026Feedback by Design: Understanding and Overcoming User Feedback Barriers in Conversational Agentscited by 4
  29. 2026Synthetic Interaction Data for Scalable Personalization in Large Language Modelscited by 4
  30. 2026Implicit Turn-Wise Policy Optimization for Proactive User-LLM Interactioncited by 4
  31. 2026GUIDE: A Benchmark for Understanding and Assisting Users in Open-Ended GUI Taskscited by 4
  32. 2026Ask Early, Ask Late, Ask Right: When Does Clarification Timing Matter for Long-Horizon Agents?cited by 4
  33. 2025FURINA: A Fully Customizable Role-Playing Benchmark via Scalable Multi-Agent Collaboration Pipelinecited by 3
  34. 2025ProMediate: A Socio-cognitive framework for evaluating proactive agents in multi-party negotiationcited by 3
  35. 2025Grounded in Reality: Learning and Deploying Proactive LLM from Offline Logscited by 3
  36. 2026Cold-Start Personalization via Training-Free Priors from Structured World Modelscited by 3
  37. 2026Vinedresser3D: Agentic Text-guided 3D Editingcited by 3
  38. 2026CRAFT: Grounded Multi-Agent Coordination Under Partial Informationcited by 3

50 most cited of 124 All 124 (JSON)