model
Fixed-Point Reasoning Model
modelactiveprovisional
fixed-point-reasoning-model-8e50321e·1 events·first seen 11h agoAliases: Fixed-Point Reasoning Model
Co-occurring entities
More like this (12)
Fixed-Point Reasoners: Stable and Adaptive Deep Looped TransformersPredicting Future Behaviors in Reasoning Models Enables Better SteeringReasoning Language ModelsWhen the Chain of Thought Knows Better: Failure Modes in Multi-Turn Reasoning Modelsfrontier reasoning modelsLarge Reasoning ModelsReasoning in Memory (RiM)mathematical reasoningDoes Reasoning Preserve Alignment? On the Trustworthiness of Large Reasoning ModelsAdaptive Parallel ReasoningBeyond the Commitment Boundary: Probing Epiphenomenal Chain-of-Thought in Large Reasoning ModelsEquilibrium Reasoners (EqR)
Recent events (1)
Fixed-Point Reasoning Model (FPRM): Stable looped Transformers with adaptive compute via fixed-point halting
Researchers introduce FPRM, a Transformer-based Fixed-Point Reasoning Model that uses fixed-point convergence as a halting mechanism in looped architectures, addressing signal propagation problems through pre-norm layers and residual scaling. Looped architectures provide inductive bias for compositional reasoning, but suffer from depth-induced signal degradation when halting is deferred; FPRM resolves this while enabling compute to scale with task difficulty. The model is evaluated on Sudoku, Maze, state-tracking, and ARC-AGI benchmarks. This contributes to the growing body of work on adaptive-compute and iterative-refinement architectures for reasoning.