Fast Best-of-N Decoding via Speculative Rejection (2024 · 50 citations)
Best-of-N aligns an LLM at inference time without retraining. It samples many candidate answers and keeps the one a reward model rates highest. It can rival post-training methods such as RLHF or DPO, but competitive N values run into the thousands, which would need many accelerators. The authors observe that reward…
A Survey of Self-Evolving Agents: What, When, How, and Where to Evolve on the Path to Artificial Super Intelligence (2025 · 36 citations)
Today's LLMs are essentially frozen once trained. They cannot update their own parameters or behavior when they meet unfamiliar tasks, shifting knowledge, or changing interaction settings, and this becomes a serious limitation when agents work in open, interactive environments. This survey does not introduce new data…
Harnessing the Reasoning Economy: A Survey of Efficient Reasoning for Large Language Models (2025 · 16 citations)
Large Reasoning Models such as OpenAI o1, DeepSeek R1 and QwQ solve hard math and coding problems by producing long chains of thought.

Co-authors here

12 of 25 co-authors with a page, the most papers together first.

Venues

Where their works here were published, the most works first, with the editions of those that have a page.

Papers of our library cite their works 98 times (of the 149,439 papers whose bibliographies we read); 44 citing papers with a page here →.

Updated 3 November 2026