LLM Decision-Making

LLM: Large Language Model

This field examines how large language models make choices, use tools, ask for information, and act alone or with other agents, including in settings such as finance, healthcare, law, and strategic games. Researchers draw on behavioral economics and cognitive science, decision theory, reinforcement learning, and multi-agent methods, using controlled choice experiments and benchmarks that test constraints, calibration, fairness, and long-horizon performance. A central challenge is that correct answers or stated reasoning do not guarantee sound actions: choices can shift with framing, option order, context, and how evidence or costs are presented. Current work explores more reliable decision layers, explicit uncertainty and deferral, evidence-grounded rules, and tests that distinguish good outcomes from stable, human-aligned decision processes.

Latest papers

246 papers86 papers in the last four weeks, up 258% on the four weeks before. 0.5% of all new papers.

When the Top Answer Decides: Gender Bias in Decision Models
Oct 29, 2026Yeb HavingaGender Bias in Language Models Language Model Bias Evaluation
Independent Researcher
Robustness of Chatbot LLM Judgments of Presidential Actions and Hypothetical Reforms
Oct 29, 2026Oleg VasilyevLanguage Model Robustness LLM Decision-Making
Independent Researcher
SatOps-Decision: Low-Latency Discriminative Decisions for Onboard Satellite Communication Operations
Oct 28, 2026Lifan Mei, Yuxuan Li, Jiaxian Tu +1LLM Decision-Making Efficient Language Model Inference
Academy of AIAT, Xi’an Jiaotong-Liverpool University · Amazon, Inc.
Rare, Relevant, and Still Wrong: How Memory Fails LLM Group Decisions
Oct 27, 2026Anouar Imel, Imad Charradi, Abderrahman Sghir +1LLM Decision-Making Memory Management for LLM Agents
School of Information and Communication Engineering, University of Electronic Science and Technology of China (UESTC) · Xidian University · Nanjing University of Aeronautics and Astronautics +1
ThinkJev: One Thought, Every Budget for Calibrated Typed Decisions
Oct 27, 2026Xiaolu Ding, Kai Yang, Dongdong LiuLLM Decision-Making Efficient Language Model Reasoning
Fujian Bosssoft Co., Ltd., Fuzhou, China
OpenGray: a benchmark for evaluating the decisions of radiotherapy planning agents
Oct 27, 2026Humza Nusrat, Kundan ThindMedical AI Agents LLM Agent Evaluation
Department of Radiation Oncology, Henry Ford Health, Detroit, Michigan, USA · Department of Radiology, College of Human Medicine, Michigan State University, East Lansing, Michigan, USA
Learning to Formalize: Bridging Open-Ended Workloads and Fast Decision Models
Oct 27, 2026Chengxuan Pei, Ziyao Wang, Teng Mei +1LLM Decision-Making Robotic Manipulation
CUHK-Shenzhen · University of Tokyo · Kunlunxin Corporation
Decision Model Factory: Building Specialized Sovereign Decision Models
Oct 26, 2026Yuma IchikawaLLM Decision-Making Efficient Language Model Inference
Fujitsu Limited · RIKEN Center for AIP
TrustJev: Separating Policy Authority from Untrusted Evidence in LLM-Based Decisions
Oct 26, 2026Zhiwei Xu, Xuyang Liu, Xiaolin Peng +8LLM Decision-Making LLM Security
KLISS, BNRist, School of Software, Tsinghua University, Beijing, China · ChinaBond Finance and Information Technology Co., Ltd., Beijing, China
Entity Matching using Decision Models
Oct 25, 2026Aaron Steiner, Ralph Peeters, Christian BizerLLM Decision-Making
Data and Web Science Group, University of Mannheim, Mannheim, Germany
The Hitchhiker's Guide to System 1 Models: Fast Decision-Making Beyond LLMS
Oct 24, 2026Haggai RoitmanLanguage Model Calibration LLM Decision-Making
DMAIC-Bench: From Self-Reflection to Self-Restraint for Agents in Multi-Stage Analytical Tasks
Oct 23, 2026Shan Peng, Shuaiqi Cheng, Miao Peng +2LLM Decision-Making Process-Based Agent Evaluation
Xiwei Technology (Guangzhou) Co., Ltd. · The Hong Kong University of Science and Technology (Guangzhou)
Not All Information Is Worth Asking For: Decision-Informed Information Seeking with LLMs
Oct 23, 2026Seunghan Lee, Jun Seo, Junhyeok Kang +9LLM Decision-Making Value of Information
LG AI Research
Joint or Per-Option? Compact Encoders for Closed-Set Decisions from 17 Million to 1 Billion Parameters
Oct 22, 2026Tardelli Ronan Coelho StekelInput Order Sensitivity in Language Models LLM Decision-Making
Federal Institute of São Paulo (IFSP), São Paulo, Brazil
Same Probabilities, Different Advice: Gain-Loss Framing Effects in High-Stakes LLM Decision Support
Oct 21, 2026Yuyao Zhang, Yakun Cui, Han Zhu +3Framing Effects in Language Models AI-Assisted Decision Making
The Hong Kong University of Science and Technology, Hong Kong, China · Beihang University, Beijing, China
When Multiple Choices Are Correct: Asymmetric Probability Allocation in Jev and Other Decision Models
Oct 21, 2026Rushab MunotLLM Decision-Making LLM Reliability
Independent Researcher
DecisionPivot: A Diagnostic Benchmark for Decision Models in LLM Systems
Oct 20, 2026Xialie Zhuang, Mingcong Lei, Zunhai Su +7LLM Evaluation LLM Decision-Making
StartLux
WenSight-Decision-1 for Direct Decisions under E-commerce Rules
Oct 19, 2026Mingwen Liu, Jun Sun, Sichen WangLLM Decision-Making E-Commerce
WenSight AI Lab · TooChuang
Decision4Rec: A Jev-Inspired Framework of Decision Models on Knowledge and Active Graphs for Multi-Agent Recommender Systems
Oct 19, 2026Marco Polignano, Het Darshan Mehta, Pasquale Lops +2Recommender Systems Large Language Model-Based Recommendation
Università degli studi di Bari Aldo Moro, Piazza Umberto I, 70121 Bari, Italy · Otto-von-Guericke University, Universitätsplatz 2, 39106 Magdeburg, Germany · Leibniz Institute for Educational Media | Georg Eckert Institute, Freisestr. 1, 38118 Braunschweig, Germany
Truncated Reasoning Under a Budget: Evaluating System-1 Models as Decision-Makers
Oct 19, 2026Zhongyin Wang, Zhaoqian Xue, Junting Mu +4LLM Decision-Making Efficient Language Model Reasoning
University of Illinois Urbana-Champaign · University of Arizona · University of California, Irvine +3
Narrow Decision Models: A System-1 Architecture for Calibrated, Typed Decisions
Oct 18, 2026Carlos André Antunes, Aldry Albuquerque, Gabriel de Melo Schmith +7LLM Decision-Making Language Model Calibration
Softplan
P(Yes): 15 $\times$ Improvements via Test-Time Scaling of Decision Models
Oct 18, 2026Lev StamblerLLM Decision-Making Test-Time Scaling
Tear Labs · University of Maryland, College Park
System X: An LLM Decision Model That Replies from Its Own KV Cache
Oct 18, 2026Syed Usama Khalid Bukhari, Syed Safwan Khalid, Muhammad AamirLLM Decision-Making KV-Cache Reuse
Turing Logic LTD · University of Oxford
What Can't Jev Decide? Probing the Limits of One-Pass Decision Models
Oct 18, 2026Wang Yang, Xinpeng Li, Yanyan Zhang +8LLM Decision-Making LLM Reliability
Case Western Reserve University · NII LLMC (Japan) · Georgia Institute of Technology +1
Bellman Language Models: Solving the Recurring Decisions of LLM Agents
Oct 17, 2026Adarsh Vatsa, William EiersLLM Decision-Making LLM Agent Efficiency
Stevens Institute of Technology
Good Judgment, Bad Advice: Decision-Model Controllers Raise Agent Cost Without Improving Success
Oct 17, 2026Naman VatsLLM Agents LLM Agent Efficiency
Agents' Last Doubt: Knowing When to Act and When to Step Back in Tool-Using Agents
Oct 16, 2026Qisai Liu, Qingyue Jiao, Bangwei Guo +7Tool-Using Agents LLM Decision-Making
Iowa State University · University of Notre Dame · Rutgers University +2
Same Person, Different Advice: Auditing LLM Financial Advice with Repeated Risk-Tolerance Responses
Oct 16, 2026Soovadeep Bakshi, Apurba Bose, Aishwarya Bose +1LLM Auditing LLM Decision-Making
Independent Researcher
Intern-Decision: Efficient Multimodal Decision Making with Autoregressive Masked Language Modeling
Oct 15, 2026Tong Zhu, Zhe Xu, Zefeng He +7LLM Decision-Making Efficient Multimodal Inference
Shanghai AI Lab · Shanghai Jiao Tong University · Fudan University +1
Prism-1: Position- and Rival-Independent Scoring for System One Models
Oct 15, 2026Yao Long Teng, Jianguo Huang, Jiayi Cai +2LLM Decision-Making Permutation-Invariant Learning
Nanyang Technological University, Singapore

Oct 29, 2026J/K move · Enter open · S save

When the Top Answer Decides: Gender Bias in Decision Models

Yeb Havinga

Independent Researcher

Gender Bias in Language Models Language Model Bias Evaluation LLM Decision-Making

Open paper AskPDF arXiv

Decision models are language models built to route, classify and triage: they return option probabilities from one forward pass, and an application acts on the top answer. They are offered off the shelf, trained for the decision format rather than for fairness or any one application, and we found no bias measurement in their cards. We test TypeSafe's closed Jev and five open decision models on gender-swapped yes/no decisions about people (Tamkin et al., 2023), BBQ, StereoSet and the gender-bias studies of Fulgu and Capraro (2024). Five of the six give women significantly more favourable answers than men (+0.05 to +0.10 in log-odds), and a gender swap changes 1-3.5% of top answers (Jev's partly through its call-to-call variation). The makers' recommended confidence gate removes many biased commitments but raises the stereotyped share of those it keeps in ambiguous BBQ gender questions (granite-switch 0.76 to 0.85, pplx 0.81 to 1.00). Probes show gender preferences in the same models: all six rate violence for a greater good as more acceptable against a man than against a woman, and two default to "girl" when forced to guess a child's gender without a cue. Decision-level and probability-level measures differ, so audits should read a model as its application does.