BLADE: Boundary-Expanded and Layer-Adaptive Dynamic Exit for Efficient LLM Reasoning
Keshu Fu, Keqin Peng, Jun Bai, Shuhan Qin, Chen Li, Junzhu Liang, Yefei Chen, Jiaqi Li, Yuanxin Ouyang
cs.CL
Submitted: 2026-07-31
Comments: 8 pages
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- LYNX: Learning Dynamic Exits for Confidence-Controlled Reasoning
- Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation
- Do NOT Think That Much for 2+3=? On the Overthinking of o1-Like LLMs
- Training Verifiers to Solve Math Word Problems
- Mitigating Overthinking in Large Reasoning Language Models via Reasoning Path Deviation Monitoring
- Structured Reasoning for Large Language Models
- Revisiting Overthinking in Long Chain-of-Thought from the Perspective of Self-Doubt
- Native Parallel Reasoner: Reasoning in Parallelism via Self-Distilled Reinforcement Learning
- Qwen3 Technical Report
- Your Dense Retriever is Secretly an Expeditious Reasoner
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