15 citations · 19 across the 16 of their papers we have counts for
3 papers · 1 filter
Same Beliefs, Different Policies: Learning Reusable Representations for Early Stopping in LLM Reasoning
Jingwei Ni, Dmitry Abulkhanov, Vladislav Smirnov +5
Reasoning LLMs often continue reasoning after reaching a correct answer, wasting computation and sometimes replacing it with an incorrect one. Deciding when to stop is a metareason…
Bayesian control for coding agents
Theodore Papamarkou, Vladislav Smirnov, Viktor Mazanov +4
Modern coding agents pair LLM generators with various tools, including cheap diagnostics and expensive verifiers. The tool-use decisions are typically governed by orchestrators tha…
ReProbe: Efficient Test-Time Scaling of Multi-Step Reasoning by Probing Internal States of Large Language Models
Jingwei Ni, Ekaterina Fadeeva, Tianyi Wu +8
LLMs can solve complex tasks by generating long, multi-step reasoning chains. Test-time scaling (TTS) can further improve performance by sampling multiple variants of intermediate…