technique
Reasoning in Memory (RiM)
techniqueactiveprovisional
reasoning-in-memory-rim--80e9a727·1 events·first seen 19d agoAliases: Reasoning in Memory (RiM)
Co-occurring entities
More like this (12)
Reasoning ImitationReasoning EnhancementGitOfThoughts: Version-Controlled Reasoning and Agent Memory You Can Replay, Diff, and MergeMemory InsightsAdaptive Parallel Reasoninglatent reasoningLarge Reasoning ModelsReasoning as Pattern Matching: Shared Mechanisms in Human and LLM Everyday ReasoningChain-of-Thought ReasoningReasoning Language ModelsMedCaseReasoningTool-Integrated Reasoning
Recent events (1)
Reasoning in Memory (RiM): Latent Reasoning via Working Memory Blocks in LLMs
RiM introduces a latent reasoning method that replaces autoregressive chain-of-thought token generation with fixed sequences of special 'memory block' tokens, allowing LLMs to perform internal computation without externalizing intermediate steps. These memory blocks are processed in a single forward pass rather than generated autoregressively, improving compute efficiency at test time. Training uses a two-stage curriculum: first grounding memory blocks by predicting explicit reasoning steps, then discarding step-level supervision and refining answers iteratively. Experiments across multiple model families and sizes show RiM matches or exceeds existing latent reasoning methods.