TERMINATOR: Learning Optimal Exit Points for Early Stopping in Chain-of-Thought Reasoning
cs.LG, cs.AI, cs.CL
Submitted: 2026-03-13
Updated: 2026-11-13
Terminology
Sources
- Evaluating Large Language Models Trained on Code
- Compressed Chain of Thought: Efficient Reasoning Through Dense Representations
- Efficiently Scaling LLM Reasoning with Certaindex
- Deep Think with Confidence
- How Far Are We from Optimal Reasoning Efficiency?
- Training Large Language Models to Reason in a Continuous Latent Space
- OpenCoder: The Open Cookbook for Top-Tier Code Large Language Models
- Scalable Best-of-N Selection for Large Language Models via Self-Certainty
- Critical Thinking: Which Kinds of Complexity Govern Optimal Reasoning Length?
- Ministral 3
- Answer Convergence as a Signal for Early Stopping in Reasoning
- AdaCoT: Pareto-Optimal Adaptive Chain-of-Thought Triggering via Reinforcement Learning
- O1-Pruner: Length-Harmonizing Fine-Tuning for O1-Like Reasoning Pruning
- Early Stopping Chain-of-thoughts in Large Language Models
- s1: Simple test-time scaling
- Demystifying Reasoning Dynamics with Mutual Information: Thinking Tokens are Information Peaks in LLM Reasoning
- Sample More to Think Less: Group Filtered Policy Optimization for Concise Reasoning
- Entropy After </Think> for reasoning model early exiting
- From Efficiency to Adaptivity: A Deeper Look at Adaptive Reasoning in Large Language Models
- Qwen3 Technical Report
Related papers
- A Physics-Regulated Neural Framework for Learning 3D Grain Growth Dynamics
- FlexMoE: Learning One-for-All Multi-Budget Expert Pruning for Flexible MoE Deployment
- OptiMind: Improving Small Language Models for Optimization Modeling through Formulation Guidance and Multi-Turn Learning
- Staying in the Sweet Spot: Boost Reasoning Evolution via Responsive Rollout Difficulty Manipulation
- Examining the Impact of Data and Training Methods on Emergent and Subliminal Misalignment
- Rethinking Black-Box On-Policy Distillation: A Rubric-based Analysis