mlsanityData to 14 Oct 2026

ComplLLM: Fine-tuning LLMs to Discover Complementary Signals for Decision-making

arXiv 2602.19458 ↗First posted 23 Feb 2026cs.AI cs.HCcited by 2

Not on the map. Why?

Abstract (arXiv)

Multi-agent decision pipelines can outperform single agent workflows when complementarity holds, i.e., different agents bring unique information to the table to inform a final decision. We propose ComplLLM, a post-training framework based on decision theory that fine-tunes a decision-assistant LLM using complementary information as reward to output signals that complement existing agent decisions. We validate ComplLLM on synthetic and real-world tasks involving domain experts, demonstrating how the approach recovers known complementary information and produces plausible explanations of complementary signals to support downstream decision-makers.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 34 of its 52 references that are in the map. First posted on arXiv 23 Feb 2026.

Builds on

34 of 52 references.

References · 34

  1. 2024DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Modelscited by 9,379
  2. 2019CheXpert: A Large Chest Radiograph Dataset with Uncertainty Labels and Expert Comparisoncited by 1,423
  3. 2022BERTopic: Neural topic modeling with a class-based TF-IDF procedurecited by 801
  4. 2020Does the Whole Exceed its Parts? The Effect of AI Explanations on Complementary Team Performancecited by 399
  5. 2025Cognitive Behaviors that Enable Self-Improving Reasoners, or, Four Habits of Highly Effective STaRscited by 377
  6. 2019Topic Modeling in Embedding Spacescited by 224
  7. 2017Autoencoding Variational Inference For Topic Modelscited by 169
  8. 2024CycleResearcher: Improving Automated Research via Automated Reviewcited by 148
  9. 2020Top2Vec: Distributed Representations of Topicscited by 126
  10. 2020Learning to Complement Humanscited by 124
  11. 2025OctoThinker: Mid-training Incentivizes Reinforcement Learning Scalingcited by 113
  12. 2024When combinations of humans and AI are useful: A systematic review and meta-analysiscited by 106
22 more
  1. 2019The Algorithmic Automation Problem: Prediction, Triage, and Human Effortcited by 101
  2. 2023DICES Dataset: Diversity in Conversational AI Evaluation for Safetycited by 86
  3. 2017Discovering Discrete Latent Topics with Neural Variational Inferencecited by 79
  4. 2021Differentiable Learning Under Triagecited by 76
  5. 2021Towards Unbiased and Accurate Deferral to Multiple Expertscited by 72
  6. 2024Hypothesis Generation with Large Language Modelscited by 71
  7. 2022Improving Expert Predictions with Conformal Predictioncited by 54
  8. 2021Role of Human-AI Interaction in Selective Predictioncited by 35
  9. 2022A Meta-Analysis of the Utility of Explainable Artificial Intelligence in Human-AI Decision-Makingcited by 29
  10. 2023Human-Aligned Calibration for AI-Assisted Decision Makingcited by 28
  11. 2025Sparse Autoencoders for Hypothesis Generationcited by 26
  12. 2023When to Show a Suggestion? Integrating Human Feedback in AI-Assisted Programmingcited by 25
  13. 2024Towards Human-AI Complementarity with Prediction Setscited by 25
  14. 2022A Taxonomy of Human and ML Strengths in Decision-Making to Investigate Human-ML Complementaritycited by 23
  15. 2024Explaining Datasets in Words: Statistical Models with Natural Language Parameterscited by 21
  16. 2023Effective Human-AI Teams via Learned Natural Language Rules and Onboardingcited by 20
  17. 2022Toward Supporting Perceptual Complementarity in Human-AI Collaboration via Reflection on Unobservablescited by 19
  18. 2022On the Effect of Information Asymmetry in Human-AI Teamscited by 17
  19. 2022Designing Closed Human-in-the-loop Deferral Pipelinescited by 11
  20. 2025Causal Inference on Outcomes Learned from Textcited by 8
  21. 2025Towards Human-AI Complementarity in Matching Taskscited by 7
  22. 2025Explanations are a Means to an End: Decision Theoretic Explanation Evaluationcited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026Algorithmic Feature Highlighting for Human-AI Decision-Makingcited by 0
  2. 2026Calibrating LLM Explanations to Human Decisions with Reinforcement Learningcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025LLMs are Greedy Agents: Effects of RL Fine-tuning on Decision-Making Abilities
  2. 2026Does RL Expand the Capability Boundary of LLM Agents? A PASS@(k,T) Analysis
  3. 2026LLM Agents for Deliberative Collaboration: A Study on Joint Decision Making Under Partial Observability
  4. 2026SynAct: Synergistic Active Feedback Learning for LLM Agents
  5. 2025LLM Agents Beyond Utility: An Open-Ended Perspective
  6. 2026RELIC: Revealed Principles for Learning Interpretable Composable Skills in Multi-Agent Planning
  7. 2025AgentCDM: Enhancing Multi-Agent Collaborative Decision-Making via ACH-Inspired Structured Reasoning
  8. 2025Unlocking the Power of Multi-Agent LLM for Reasoning: From Lazy Agents to Deliberation