Turn-level best-of-N sampling improves LLM agent accuracy by 5-10%
Turn-level best-of-N sampling with generator-selector LLMs yields 5-10% accuracy gains and improved consistency on long-horizon tasks by selecting optimal actions at each step.
Stories per day · 30 days
3 RSS
4 stories, newest first · one card per story
Stories tagged #inference-scaling
Import AI 475: Swarm scaling; Google DeepMind watermarks biology; and the AI science economy
Import AI covers swarm scaling, a US AI-rules poll, DeepMind's SynthID Bio, and lab-automation benchmarks.
4
What Makes Recurrence Effective in Looped Language Models?
Looped language models gain reasoning from recurrence beyond training, but extra loops can hurt knowledge.
Stellar Colosseum: A Many-Agent Harness for Long-Horizon Research in Mathematics and Theoretical Computer Science
Stellar Colosseum, a many-agent harness for long-horizon math and TCS research, solves open problems and reaches 71% on TCS-Bench with Gemini models.