Aware First, Think Less: Dynamic Boundary Self-Awareness Drives Extreme Reasoning Efficiency in Large Language Models
Recent advancements in large language models (LLMs) have greatly improved their capabilities on complex reasoning tasks through Long Chain-of-Thought (CoT). However, this approach often results in substantial redundancy, impairing computational efficiency and causing significant delays in real-time applications. To improve the efficiency, current methods often rely on human-defined difficulty priors, which do not align with the LLM's self-awared difficulty, leading to inefficiencies. In this paper, we introduce the Dynamic Reasoning-Boundary Self-Awareness Framework (DR. SAF), which enables models to dynamically assess and adjust their reasoning depth in response to problem complexity. DR. SAF integrates three key components: Boundary Self-Awareness Alignment, Adaptive Reward Management, and a Boundary Preservation Mechanism. These components allow models to optimize their reasoning processes, balancing efficiency and accuracy without compromising performance. Our experimental results demonstrate that DR. SAF achieves a 49.27% reduction in total response tokens with minimal loss in accuracy. The framework also delivers a 6.59x gain in token efficiency and a 5x reduction in training time, making it well-suited to resource-limited settings. During extreme training, DR. SAF can even surpass traditional instruction-based models in token efficiency with more than 16% accuracy improvement.
Code (0)
등록된 구현이 없습니다.
Tasks
Computational EfficiencySimilar Papers 제목 키워드 기반
Think about boundary: Fusing multi-level boundary information for landmark heatmap regression
Although current face alignment algorithms have obtained pretty good performances at predicting the location of facial landmarks, huge challenges remain for faces with severe occlusion and large pose variations, etc. On …
Face AlignmentregressionSocial Structure Matters in 3D Human-Human Interaction Generation
Although text-to-motion generation has achieved strong progress in synthesizing realistic single-person motions from language, extending it to text-driven 3D human-human interaction (HHI) remains non-trivial, as HHI requ…
Rethinking Monocular Depth Embedding for Generalized Stereo Matching
Generally, monocular methods capture rich contextual priors but lack geometric precision, whereas stereo methods are geometrically accurate yet struggle in textureless and occluded regions. Several approaches attempt to …
Data AugmentationIncentivizing Dual Process Thinking for Efficient Large Language Model Reasoning
Large reasoning models (LRMs) have demonstrated strong performance on complex reasoning tasks, but often suffer from overthinking, generating redundant content regardless of task difficulty. Inspired by the dual process …
Language ModelingLanguage ModellingLarge Language Modelreinforcement-learning+1To Retrieve or To Think? Cross-Boundary Context Evolution for Multi-hop Complex Reasoning
Current context augmentation methods, such as retrieval-augmented generation, play a crucial role in bridging a model's internal knowledge boundary and external evidence for multi-hop reasoning. However, they often follo…