Related papers: Agentic-R1: Distilled Dual-Strategy Reasoning

Language models rely on semantic priors to perform in-context learning, which leads to poor performance on tasks involving inductive reasoning. Instruction-tuning methods based on imitation learning can superficially enhance the in-context…

Recent research on knowledge distillation has increasingly focused on logit distillation because of its simplicity, effectiveness, and versatility in model compression. In this paper, we introduce Refined Logit Distillation (RLD) to address…

Large Language Model agents excel at solving complex tasks through iterative reasoning and tool use, but typically depend on ultra-large, costly backbones. Existing distillation approaches train smaller students to imitate full teacher…

Reasoning models think out loud, but much of what they say is noise. We introduce CRISP (Compressed Reasoning via Iterative Self-Policy Distillation), a method that teaches models to reason more concisely by distilling their own concise…

Vision-based deep reinforcement learning (RL) typically obtains performance benefit by using high capacity and relatively large convolutional neural networks (CNN). However, a large network leads to higher inference costs (power, latency,…

Recently, long-thought reasoning models achieve strong performance on complex reasoning tasks, but often incur substantial inference overhead, making efficiency a critical concern. Our empirical analysis reveals that the benefit of using…

When distilling reasoning from large language models (LLMs) into smaller ones, teacher rationales for similar problems often vary wildly in structure and strategy. Like a chef who makes the same dish differently each time, this…

Distilling Chain-of-Thought (CoT) reasoning from large language models into compact student models presents a fundamental challenge: teacher rationales are often too verbose for smaller models to faithfully reproduce. Existing approaches…

Multi-agent debate has been shown to improve reasoning in large language models (LLMs). However, it is compute-intensive, requiring generation of long transcripts before answering questions. To address this inefficiency, we develop a…

Policy distillation in deep reinforcement learning provides an effective way to transfer control policies from a larger network to a smaller untrained network without a significant degradation in performance. However, policy distillation is…

Large reasoning models achieve strong performance on complex tasks through long chain-of-thought (CoT) trajectories, but directly transferring such reasoning processes to smaller models remains challenging. A key difficulty is that not all…

Policy distillation, which transfers a teacher policy to a student policy has achieved great success in challenging tasks of deep reinforcement learning. This teacher-student framework requires a well-trained teacher model which is…

Knowledge Distillation (KD) transfers knowledge from a large teacher model to a smaller student by aligning their predictive distributions. However, conventional KD formulations - typically based on Kullback-Leibler divergence - assume that…

Existing chain-of-thought (CoT) distillation methods can effectively transfer reasoning abilities to base models but suffer from two major limitations: excessive verbosity of reasoning traces and inadequate adaptability to problem…

Large Language Models (LLMs) have made significant strides in problem-solving by incorporating reasoning processes. However, this enhanced reasoning capability results in an increased number of output tokens during inference, leading to…

Large language models (LLMs) have significantly advanced various natural language processing tasks, but deploying them remains computationally expensive. Knowledge distillation (KD) is a promising solution, enabling the transfer of…

Knowledge distillation has been widely used to compress existing deep learning models while preserving the performance on a wide range of applications. In the specific context of Automatic Speech Recognition (ASR), distillation from…

Large Language Models (LLMs) have transformed listwise document reranking by enabling global reasoning over candidate sets, yet single models often struggle to balance fine-grained relevance scoring with holistic cross-document analysis. We…

Multiagent reinforcement learning algorithms (MARL) have been demonstrated on complex tasks that require the coordination of a team of multiple agents to complete. Existing works have focused on sharing information between agents via…

Large language models (LLMs) excel in complex reasoning tasks, and distilling their reasoning capabilities into smaller models has shown promise. However, we uncover an interesting phenomenon, which we term the Small Model Learnability Gap:…