Constructing Pareto Frontiers of Optimal Reasoning Termination Methods for Overthinking in Reasoning Models
cs.AI
Submitted: 2026-10-09
Updated: 2026-10-09
Sources
- OptimalThinkingBench: Evaluating Over and Underthinking in LLMs
- LYNX: Learning Dynamic Exits for Confidence-Controlled Reasoning
- Training Language Models to Reason Efficiently
- Predictive Scheduling for Efficient Inference-Time Reasoning in Large Language Models
- Do NOT Think That Much for 2+3=? On the Overthinking of o1-Like LLMs
- The First Impression Problem: Internal Bias Triggers Overthinking in Reasoning Models
- Circular Reasoning: Understanding Self-Reinforcing Loops in Large Reasoning Models
- Missing Premise exacerbates Overthinking: Are Reasoning Models losing Critical Thinking Skill?
- Thinkless: LLM Learns When to Think
- Efficiently Scaling LLM Reasoning with Certaindex
- Inverse Scaling in Test-Time Compute
- Does Thinking More always Help? Mirage of Test-Time Scaling in Reasoning Models
- Mitigating Overthinking in Large Reasoning Language Models via Reasoning Path Deviation Monitoring
- Measuring Mathematical Problem Solving With the MATH Dataset
- ThinkPrune: Pruning Long Chain-of-Thought of LLMs via Reinforcement Learning
- LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code
- Think Only When You Need with Large Hybrid-Reasoning Models
- THINK-Bench: Evaluating Thinking Efficiency and Chain-of-Thought Quality of Large Reasoning Models
- ThinkSwitcher: When to Think Hard, When to Think Fast
- Plan and Budget: Effective and Efficient Test-Time Scaling on Reasoning Large Language Models
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Agents' Last Exam
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems