Energy-Based Reasoners: Recurrent Reasoners Should Be Energy-Based Models
William Xingxu Chen · hf · 2026-11-18
The paper proposes Energy-Based Reasoners: modeling looped latent reasoning as an energy-based model. A learned energy function's gradient refines reasoning states step by step, while its value serves as a stopping signal telling the model when to exit the loop. Exploration-based training further improves both performance and efficiency.
Related event: Energy-Based Reasoners: Learning When to Stop in Recurrent Reasoning(3 posts)→
More from Research
- Interpretability solved—then what? Najoung Kim proposes filtering for recurrent constructs — najoungkim · 2026-11-19
- New preprint asks: if interpretability is "solved," what does it mean for the science of human language? — najoungkim · 2026-11-19
- Map of tabular foundation models shows only two are fully open — GaelVaroquaux · 2026-11-19
- Google open-sources TPU codesign guide: 8 principles for LLM/MoE performance — rseroter · 2026-11-19
- TMol was the 'secret weapon' behind RFD4-Proteina, researchers reveal — AllThingsApx · 2026-11-19
- Microsoft Research podcast: Eric Horvitz and Eric Topol on AI reshaping medicine — erichorvitz · 2026-11-19