CONDESION-BENCH: Conditional Decision-Making of Large Language Models in Compositional Action Space
On the map: LLM reasoning → Reasoning benchmarks and evaluation
Abstract (arXiv)
Large language models have been widely explored as decision-support tools in high-stakes domains due to their contextual understanding and reasoning capabilities. However, existing decision-making benchmarks rely on two simplifying assumptions: actions are selected from a finite set of pre-defined candidates, and explicit conditions restricting action feasibility are not incorporated into the decision-making process. These assumptions fail to capture the compositional structure of real-world actions and the explicit conditions that constrain their validity. To address these limitations, we introduce CONDESION-BENCH, a benchmark designed to evaluate conditional decision-making in compositional action space. In CONDESION-BENCH, actions are defined as allocations to decision variables and are restricted by explicit conditions at the variable, contextual, and allocation levels. By employing oracle-based evaluation of both decision quality and condition adherence, we provide a more rigorous assessment of LLMs as decision-support tools.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning. Builds on 21 of its 53 references that are in the map. First posted on arXiv 10 Apr 2026.
Builds on
21 of 53 references.
References · 21
- 2024The Llama 3 Herd of Modelscited by 14,715
- 2023G-Eval: NLG Evaluation using GPT-4 with Better Human Alignmentcited by 2,276
- 2025gpt-oss-120b & gpt-oss-20b Model Cardcited by 1,386
- 2017Constrained Policy Optimizationcited by 983
- 2013Bandits with Knapsackscited by 164
- 2023Foundation Models for Decision Making: Problems, Methods, and Opportunitiescited by 164
- 2023A Language Agent for Autonomous Drivingcited by 164
- 2021End-to-End Constrained Optimization Learning: A Surveycited by 157
- 2024Determinants of LLM-assisted Decision-Makingcited by 56
- 2023Large Language Models are Clinical Reasoners: Reasoning-Aware Diagnosis Framework with Prompt-Generated Rationalescited by 33
- 2024The Importance of Directional Feedback for LLM-based Optimizerscited by 26
- 2025PRINCIPLES: Synthetic Strategy Memory for Proactive Dialogue Agentscited by 15
9 more
- 2024Language Models are Alignable Decision-Makers: Dataset and Application to the Medical Triage Domaincited by 14
- 2025Large Language Models for Supply Chain Decisionscited by 13
- 2025DecisionFlow: Advancing Large Language Model as Principled Decision Makercited by 12
- 2024STRUX: An LLM for Decision-Making with Structured Explanationscited by 7
- 2025AIM-Bench: Evaluating Decision-making Biases of Agentic LLM as Inventory Managercited by 6
- 2022Constrained Policy Optimization for Controlled Self-Learning in Conversational AI Systemscited by 4
- 2024DeFine: Decision-Making with Analogical Reasoning over Factor Profilescited by 4
- 2024Offline Inverse Constrained Reinforcement Learning for Safe-Critical Decision Making in Healthcarecited by 4
- 2025Classical AI vs. LLMs for Decision-Maker Alignment in Health Insurance Choicescited by 1
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2025Enhancing Decision-Making of Large Language Models via Actor-Critic
- 2025DynaAct: Large Language Model Reasoning with Dynamic Action Spaces
- 2024Embodied Agent Interface: Benchmarking LLMs for Embodied Decision Making
- 2024GroundCocoa: A Benchmark for Evaluating Compositional & Conditional Reasoning in Language Models
- 2026Diagnosing and Improving Probabilistic Reasoning in Large Language Models
- 2025Syntactic Framing Fragility: An Audit of Robustness in LLM Ethical Decisions
- 2024Efficient Sequential Decision Making with Large Language Models
- 2024DeLLMa: Decision Making Under Uncertainty with Large Language Models