Nice Fold or Hero Call: Learning Budget-Efficient Thinking under Policy-Dependent Solvability
cs.AI
Submitted: 2026-05-12
Updated: 2026-09-25
Code: https://github.com/houqiii/BET
Terminology
Sources
- L1: Controlling How Long A Reasoning Model Thinks With Reinforcement Learning
- Don't Think Longer, Think Wisely: Optimizing Thinking Dynamics for Large Reasoning Models
- Training Language Models to Reason Efficiently
- Large Language Monkeys: Scaling Inference Compute with Repeated Sampling
- Demystifying Long Chain-of-Thought Reasoning in LLMs
- Aware First, Think Less: Dynamic Boundary Self-Awareness Drives Extreme Reasoning Efficiency in Large Language Models
- Do NOT Think That Much for 2+3=? On the Overthinking of o1-Like LLMs
- VeriThinker: Learning to Verify Makes Reasoning Model Efficient
- OpenAI o1 System Card
- Omni-MATH: A Universal Olympiad Level Mathematic Benchmark For Large Language Models
- DeepMath-103K: A Large-Scale, Challenging, Decontaminated, and Verifiable Mathematical Dataset for Advancing Reasoning
- LoRA: Low-Rank Adaptation of Large Language Models
- AdaCtrl: Towards Adaptive and Controllable Reasoning via Difficulty-Aware Budgeting
- Mitigating Overthinking in Large Reasoning Models via Manifold Steering
- Let's Verify Step by Step
- QFFT, Question-Free Fine-Tuning for Adaptive Reasoning
- DiffAdapt: Difficulty-Adaptive Reasoning for Token-Efficient LLM Inference
- O1-Pruner: Length-Harmonizing Fine-Tuning for O1-Like Reasoning Pruning
- A Survey of Efficient Reasoning for Large Reasoning Models: Language, Multimodality, and Beyond
- GPQA: A Graduate-Level Google-Proof Q&A Benchmark
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
- 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
- VSAL: A Vision Solver with Adaptive Layouts for Graph Property Detection