How Does Reasoning Flow? Tracing Attention-Induced Information Flow for Targeted RL in LLMs (opens in new tab)  🎮Reinforcement Learning  Content type: Academic

Token-level credit assignment remains a key obstacle for reinforcement learning (RL) in large language models (LLMs), where RL recipes typically treat all tokens equally, failing to distinguish decisive reasoning steps from routine formatting or fluent filler. Recent attempts leverage model-internal signals to assign finer-grained credit, but these are often point-wise heuristics that ignore the global structure of information propagation. We pr...