Post-Reasoning boosts LLM accuracy by reversing the usual answer-after-reasoning order, delivering mean relative gains of 17.37% across 117 model-benchmark pairs with zero extra cost.
DRP: Distilled Reasoning Pruning with Skill-aware Step Decomposition for Efficient Large Reasoning Models
10 Pith papers cite this work. Polarity classification is still indexing.
10
Pith papers citing it
abstract
While Large Reasoning Models (LRMs) have demonstrated success in complex reasoning tasks through long chain-of-thought (CoT) reasoning, their inference often involves excessively verbose reasoning traces, resulting in substantial inefficiency. To address this, we propose Distilled Reasoning Pruning (DRP), a hybrid framework that combines inference-time pruning with tuning-based distillation, two widely used strategies for efficient reasoning. DRP uses a teacher model to perform skill-aware step decomposition and content pruning, and then distills the pruned reasoning paths into a student model, enabling it to reason both efficiently and accurately. Across several challenging mathematical reasoning datasets, we find that models trained with DRP achieve substantial improvements in token efficiency without sacrificing accuracy. Specifically, DRP reduces average token usage on GSM8K from 917 to 328 while improving accuracy from 91.7% to 94.1%, and achieves a 43% token reduction on AIME with no performance drop. Further analysis shows that aligning the reasoning structure of training CoTs with the student's reasoning capacity is critical for effective knowledge transfer and performance gains.
citation-role summary
background 3
citation-polarity summary
roles
background 3polarities
background 3representative citing papers
TOPD improves on-policy distillation for LLM reasoning by using near-future guidance to identify divergent states, raising average accuracy from 47.8% to 52.2% on math benchmarks including AIME24 and AIME25.
Rock Tokens in on-policy distillation persist at high loss, account for up to 18% of outputs, absorb large gradient norms, but add negligible value to reasoning performance.
MUSE decouples reconstruction and semantic learning in visual tokenization via topological orthogonality, yielding SOTA generation quality and improved semantic performance over its teacher model.
MOSAIC combines frozen-LLM semantic embeddings with hierarchical consistency objectives to report up to 3.4% AUC gains on knowledge-tracing benchmarks including a new MOOC dataset.
DriftGuard introduces multi-monitor safety-aware drift detection paired with hard-mix selective adaptation, reporting toxic recall gains to 0.8777 on Civil Comments and 0.8523 on DynaHate under temporal and cross-dataset shifts.
ActorMind is a four-agent chain-of-thought framework that emulates human actors to produce spontaneous, emotion-infused speech responses for role-playing scenarios.
A survey organizing techniques to achieve efficient reasoning in LLMs by shortening chain-of-thought outputs.
IMAGINE uses adaptive schema-imagery via dynamic multimodal prototypes to incorporate implicit semantics into composed video retrieval, claiming SOTA results on CVR and CIR benchmarks.
Reinforcement learning is advanced for communication-efficient federated optimization and for preference-aligned, contextually safe policies in large language models.
citing papers explorer
No citing papers match the current filters.