paper-with-me

홈 › Papers

Reinforcement Learning for Reasoning in Small LLMs: What Works and What Doesn't

2025-03-20 · Quy-Anh Dang, Chris Ngo

Enhancing the reasoning capabilities of large language models (LLMs) typically relies on massive computational resources and extensive datasets, limiting accessibility for resource-constrained settings. Our study investigates the potential of reinforcement learning (RL) to improve reasoning in small LLMs, focusing on a 1.5-billion-parameter model, DeepSeek-R1-Distill-Qwen-1.5B, under strict constraints: training on 4 NVIDIA A40 GPUs (48 GB VRAM each) within 24 hours. Adapting the Group Relative Policy Optimization (GRPO) algorithm and curating a compact, high-quality mathematical reasoning dataset, we conducted three experiments to explore model behavior and performance. Our results demonstrate rapid reasoning gains - e.g., AMC23 accuracy rising from 63% to 80% and AIME24 reaching 46.7%, surpassing o1-preview - using only 7,000 samples and a $42 training cost, compared to thousands of dollars for baseline models. However, challenges such as optimization instability and length constraints emerged with prolonged training. These findings highlight the efficacy of RL-based fine-tuning for small LLMs, offering a cost-effective alternative to large-scale approaches. We release our code and datasets as open-source resources, providing insights into trade-offs and laying a foundation for scalable, reasoning-capable LLMs in resource-limited environments. All are available at https://github.com/knoveleng/open-rs.

📄 PDF Abstract BibTeX arXiv:2503.16219

Code (1)

knoveleng/open-rs 공식 구현 pytorch

Tasks

Mathematical ReasoningReinforcement Learning (RL)

Similar Papers 제목 키워드 기반

The Challenge of Teaching Reasoning to LLMs Without RL or Distillation

2025-07-14 · Wei Du, Branislav Kisacanin, George Armstrong, Shubham Toshniwal 외 arxiv

Reasoning-capable language models achieve state-of-the-art performance in diverse complex tasks by generating long, explicit Chain-of-Thought (CoT) traces. While recent works show that base models can acquire such reason…

Reinforcement LearningPrompt Engineering

Think2SQL: Reinforce LLM Reasoning Capabilities for Text2SQL

2025-04-21 · Simone Papicchio, Simone Rossi, Luca Cagliero, Paolo Papotti

Large Language Models (LLMs) have shown impressive capabilities in transforming natural language questions about relational databases into SQL queries. Despite recent improvements, small LLMs struggle to handle questions…

Reinforcement Learning (RL)Zero-Shot Learning

Contextual Integrity in LLMs via Reasoning and Reinforcement Learning

2025-05-29 · Guangchen Lan, Huseyin A. Inan, Sahar Abdelnabi, Janardhan Kulkarni 외

As the era of autonomous agents making decisions on behalf of users unfolds, ensuring contextual integrity (CI) -- what is the appropriate information to share while carrying out a certain task -- becomes a central quest…

reinforcement-learningReinforcement LearningReinforcement Learning (RL)

ReaLM: Reflection-Enhanced Autonomous Reasoning with Small Language Models

2025-08-17 · Yuanfeng Xu, Zehui Dai, Jian Liang, Jiapeng Guan 외 arxiv

Small Language Models (SLMs) are a cost-effective alternative to Large Language Models (LLMs), but often struggle with complex reasoning due to their limited capacity and a tendency to produce mistakes or inconsistent an…

Reinforcement Learning

xRouter: Training Cost-Aware LLMs Orchestration System via Reinforcement Learning

2025-10-09 · Cheng Qian, Zuxin Liu, Shirley Kokane, Akshara Prabhakar 외 arxiv

Modern LLM deployments confront a widening cost-performance spectrum: premium models deliver strong reasoning but are expensive, while lightweight models are economical yet brittle on complex tasks. Static escalation rul…

Reinforcement Learning