SwS: Self-aware Weakness-driven Problem Synthesis in Reinforcement Learning for LLM Reasoning
This addresses the scalability issue in reinforcement learning for LLM reasoning by improving training efficiency without external knowledge distillation, though it is incremental as it builds on existing RLVR methods.
The paper tackles the problem of inefficient problem synthesis for training large language models (LLMs) in reinforcement learning by introducing a self-aware weakness-driven framework that identifies model deficiencies and synthesizes targeted problems, resulting in average performance gains of 10.0% and 7.7% on reasoning benchmarks.
Reinforcement Learning with Verifiable Rewards (RLVR) has proven effective for training large language models (LLMs) on complex reasoning tasks, such as mathematical problem solving. A prerequisite for the scalability of RLVR is a high-quality problem set with precise and verifiable answers. However, the scarcity of well-crafted human-labeled math problems and limited-verification answers in existing distillation-oriented synthetic datasets limit their effectiveness in RL. Additionally, most problem synthesis strategies indiscriminately expand the problem set without considering the model's capabilities, leading to low efficiency in generating useful questions. To mitigate this issue, we introduce a Self-aware Weakness-driven problem Synthesis framework (SwS) that systematically identifies model deficiencies and leverages them for problem augmentation. Specifically, we define weaknesses as questions that the model consistently fails to learn through its iterative sampling during RL training. We then extract the core concepts from these failure cases and synthesize new problems to strengthen the model's weak areas in subsequent augmented training, enabling it to focus on and gradually overcome its weaknesses. Without relying on external knowledge distillation, our framework enables robust generalization byempowering the model to self-identify and address its weaknesses in RL, yielding average performance gains of 10.0% and 7.7% on 7B and 32B models across eight mainstream reasoning benchmarks.