paper-with-me

Papers

Training Large Reasoning Models Efficiently via Progressive Thought Encoding

2026-02-18 · Zeliang Zhang, Xiaodong Liu, Hao Cheng, Hao Sun, Chenliang Xu, Jianfeng Gao arxiv

Large reasoning models (LRMs) excel on complex problems but face a critical barrier to efficiency: reinforcement learning (RL) training requires long rollouts for outcome-based rewards, where autoregressive decoding dominates time and memory usage. While sliding-window cache strategies can bound memory, they disrupt long-context reasoning and degrade performance. We introduce Progressive Thought Encoding, a parameter-efficient fine-tuning method that enables LRMs to reason effectively under fixed-size caches. By progressively encoding intermediate reasoning into fixed-size vector representations, our approach eliminates the need to backpropagate through full-cache rollouts, thereby reducing memory usage, while maintaining constant memory during inference. Experiments on three models, including Qwen2.5-3B-Instruct, Qwen2.5-7B-Instruct, and DeepSeek-R1-Distill-Llama-8B, on six widely used challenging mathematical benchmarks show consistent gains: our method achieves +19.3% improvement over LoRA-based fine-tuning and +29.9% over LRMs without fine-tuning on average, with up to +23.4 accuracy improvement on AIME2024/2025 under the same tight cache budgets. These results demonstrate that Progressive Thought Encoding not only improves reasoning accuracy but also makes RL training of LRMs substantially more efficient and scalable under real-world memory constraints.

📄 PDF Abstract BibTeX arXiv:2602.16839

Code (0)

등록된 구현이 없습니다.

Tasks

parameter-efficient fine-tuningReinforcement Learning

Similar Papers 제목 키워드 기반

SCOUT: Teaching Pre-trained Language Models to Enhance Reasoning via Flow Chain-of-Thought

2025-05-30 · Guanghao Li, Wenhao Jiang, Mingfeng Chen, Yan Li 외

Chain of Thought (CoT) prompting improves the reasoning performance of large language models (LLMs) by encouraging step by step thinking. However, CoT-based methods depend on intermediate reasoning steps, which limits sc…

Audio-DeepThinker: Progressive Reasoning-Aware Reinforcement Learning for High-Quality Chain-of-Thought Emergence in Audio Language Models

2026-04-20 · Xiang He, Chenxing Li, Jinting Wang, Yan Rong 외 arxiv

Large Audio-Language Models (LALMs) have made significant progress in audio understanding, yet they primarily operate as perception-and-answer systems without explicit reasoning processes. Existing methods for enhancing …

Reinforcement Learning

ThinkDrive: Chain-of-Thought Guided Progressive Reinforcement Learning Fine-Tuning for Autonomous Driving

2026-01-08 · Chang Zhao, Zheming Yang, Yunqing Hu, Qi Guo 외 arxiv

With the rapid advancement of large language models (LLMs) technologies, their application in the domain of autonomous driving has become increasingly widespread. However, existing methods suffer from unstructured reason…

Reinforcement LearningAutonomous Driving

Latent Thoughts Tuning: Bridging Context and Reasoning with Fused Information in Latent Tokens

2026-02-10 · Weihao Liu, Dehai Min, Lu Cheng arxiv

While explicit Chain-of-Thought (CoT) equips Large Language Models (LLMs) with strong reasoning capabilities, it constrains the model's thoughts to a discrete vocabulary space. Recently, reasoning in continuous latent sp…

Keypoint-based Progressive Chain-of-Thought Distillation for LLMs

2024-05-25 · Kaituo Feng, Changsheng Li, Xiaolu Zhang, Jun Zhou 외

Chain-of-thought distillation is a powerful technique for transferring reasoning abilities from large language models (LLMs) to smaller student models. Previous methods typically require the student to mimic the step-by-…