When Agents Slow Down: Understanding LLM Agents' Test-Time Strategies via Elo-per-token Analysis
5
[AINews] OpenAI reports Navier-Stokes singularity find in 88 hours using Astra-next, roughly 10,000 agents and 130B tokens (>$40M), a contender for second ever Millennium Prize awarded
15 min1
Studying Without a Syllabus: Task-Agnostic Environment Preprocessing
An Open Recipe for IMO Gold: Training Nemotron for Olympiad Mathematics
A*-Thought-V2: Efficient Latent Reasoning via Geometric Dynamics of LLM
Rethinking Indirect Prompt Injection as a Test-Time Search Problem
What Else Needs Fixing? Exploring Cost-Effective Test-Time Compute for Revision Propagation in Artifacts Generated Through Conversation
