NeurIPS 2026 reviews are up: reviews, scores, rebuttals and meta-reviews for 7,877 papers. See the highest rated
acceptodds: the papers of ICLR 2027
277 results for “keyword:"decision making"” in ICLR 2027. 59 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]UserToolBench: A User-Profile-Hidden Benchmark for Personalized Decision Making in Tool-Use LLMs▼1.2k1.67
[PDF]Fusing Optimization Proxies and Reinforcement Learning for Multistage Stochastic Optimization▲3.0k2.33
[PDF]How a World Model Forms: Separating World Knowledge from Behavioral Competence in Sokoban Transformers▼1.2k1.67
[PDF]Knowing When to Defer: Training Language Models to Generate an Answer and Its Confidence Level Together for the Thresholds That Matter▼1361.33
[PDF]Learning the Maximum Tolerated Dose for Continuous Toxicity via Monotone Bayesian Trees▼1.2k1.67
[PDF]Co-Evolving Trees and Control Policies: Bridging Posterior Optimality and Online Efficiency in Speculative Decoding▼5.8k2.33
[PDF]Beyond Decision Agreement: Evaluating Reinforcement Learning Policy Behavior and Outcomes in Power-System Balancing▼1.2k1.67
[PDF]Measuring Internal Uncertainty in Language Model Agents: A Multi-Method Triangulation Approach▼4.3k2.00
[PDF]Beyond Patient-Level Triage: Pre-Arrival Care Navigation under Shared, Limited Capacity▼4.3k2.00
[PDF]StopTheDream: Outcome-Grounded Candidate Comparison for Adaptive Search in World-Model Planning▲3952.67
[PDF]Think or Act? State-Conditioned Representation Steering for Strategic Tool Use in Language Agents▲4.6k3.00
[PDF]Where Can Risk Be Repaired? Evidence Acquisition and Escalation for Selective Clinical LLM Decision-Making▼13k2.00
[PDF]Personalized but Unchecked: Safe Personalization Requires Conditional Control in Medical Advice▼1.2k1.67
[PDF]Dual-Resolution Recursive Energy for Selective Deliberation in Sequential Decision Making▼4.5k2.67
[PDF]Maximin-Sufficient Learning under Strategic Feedback in Zero-Sum Games with an Informed Opponent▼4.3k2.00
[PDF]ReTranDrive: A Reinforced Transition-Aware Framework for Vision-Language-Action Autonomous Driving▼4.3k2.00
Withdrawn or desk rejected (59)
[PDF]CasePath: An Agentic, Process-First Architecture for Determining Evidence RequirementsWithdrawn1.00
[PDF]VeriLoop: Multimodal Fact Verification as an Agentic Closed-Loop Sequential Decision ProcessWithdrawn1.67