Selective Reasoning for Typed Decision Models: When to Start, Read, and Stop

cs.CL

Submitted: 2026-10-14

Updated: 2026-10-14

Comments: 24 pages, 4 figures. Both authors contributed equally. Code and evaluation materials: https://github.com/binzheng-joey/selective-reasoning

Code: https://github.com/binzheng-joey/selective-reasoning

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Sources

• LYNX: Learning Dynamic Exits for Confidence-Controlled Reasoning
• Reasoning Theater: Disentangling Model Beliefs from Chain-of-Thought
• Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge
• When Does Learning to Stop Help? A Cost-Aware Study of Early Exits in Reasoning Models
• BLADE: Boundary-Expanded and Layer-Adaptive Dynamic Exit for Efficient LLM Reasoning
• Don't Overthink it. Preferring Shorter Thinking Chains for Improved LLM Reasoning
• Dynamic Early Exit in Reasoning Models

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering