Internalizing LLM Reasoning via Discovery and Replay of Latent Actions
Builds a library of activation edits from successful and failed reasoning traces, then selects edits during generation. Uses short lookahead checks to steer ongoing written reasoning, rather than replacing the trace with a sequence of hidden-state steps.
First public: · Added to this list: October 22, 2026
Explore this approach
Analysis and evaluation — Measure how well these methods work, investigate what their internal computation does, and identify where they fail. This includes experiments, studies of model internals, and mathematical results.