rSIM: Incentivizing Reasoning Capabilities of LLMs via Reinforced Strategy Injection
Large language models (LLMs) are post-trained through reinforcement learning (RL) to evolve into Reasoning Language Models (RLMs), where the hallmark of this advanced reasoning is ``aha'' moments when they start to perform strategies, such as self-reflection and deep thinking, within chain of thoughts (CoTs). Motivated by this, this paper proposes a novel reinforced strategy injection mechanism (rSIM), that enables any LLM to become an RLM by employing a small planner to guide the LLM's CoT through the adaptive injection of reasoning strategies. To achieve this, the planner (leader agent) is jointly trained with an LLM (follower agent) using multi-agent RL (MARL), based on a leader-follower framework and straightforward rule-based rewards. Experimental results show that rSIM enables Qwen2.5-0.5B to become an RLM and significantly outperform Qwen2.5-14B. Moreover, the planner is generalizable: it only needs to be trained once and can be applied as a plug-in to substantially improve the reasoning capabilities of existing LLMs. In addition, the planner supports continual learning across various tasks, allowing its planning abilities to gradually improve and generalize to a wider range of problems.
Code (0)
등록된 구현이 없습니다.
Tasks
Reinforcement LearningContinual LearningSimilar Papers 제목 키워드 기반
Reinforced Internal-External Knowledge Synergistic Reasoning for Efficient Adaptive Search Agent
Retrieval-augmented generation (RAG) is a common strategy to reduce hallucinations in Large Language Models (LLMs). While reinforcement learning (RL) can enable LLMs to act as search agents by activating retrieval capabi…
RAGReinforcement Learning (RL)RetrievalRetrieval-augmented GenerationIncentivizing Reasoning from Weak Supervision
Large language models (LLMs) have demonstrated impressive performance on reasoning-intensive tasks, but enhancing their reasoning abilities typically relies on either reinforcement learning (RL) with verifiable signals o…
reinforcement-learningReinforcement LearningReinforcement Learning (RL)VideoRFT: Incentivizing Video Reasoning Capability in MLLMs via Reinforced Fine-Tuning
Reinforcement fine-tuning (RFT) has shown great promise in achieving humanlevel reasoning capabilities of Large Language Models (LLMs), and has recently been extended to MLLMs. Nevertheless, reasoning about videos, which…
Reinforcement Learning (RL)mSCoRe: a $M$ultilingual and Scalable Benchmark for $S$kill-based $Co$mmonsense $Re$asoning
Recent advancements in reasoning-reinforced Large Language Models (LLMs) have shown remarkable capabilities in complex reasoning tasks. However, the mechanism underlying their utilization of different human reasoning ski…
Incentivizing Reasoning for Advanced Instruction-Following of Large Language Models
Existing large language models (LLMs) face challenges of following complex instructions, especially when multiple constraints are present and organized in paralleling, chaining, and branching structures. One intuitive so…
Instruction FollowingReinforcement Learning (RL)