@lateinteraction: very cool work !!
Summary
Guowei Xu discusses limitations of Best-of-N and tree search methods for LLMs on hard reasoning problems, noting sparse verification signals and that candidates remain within the model's distribution.
View Cached Full Text
Cached at: 05/30/26, 06:43 PM
very cool work !!
Guowei Xu (@Kevin_GuoweiXu): 🚀 How should LLMs sample on hard reasoning problems during post-training and inference where direct rollouts rarely produce a correct answer?
Best-of-N (e.g., GRPO) and tree search share two limitations: 🔻 Verification signals are sparse 🔻 Candidates stay within the model’s
Similar Articles
@Kevin_GuoweiXu: How should LLMs sample on hard reasoning problems during post-training and inference where direct rollouts rarely produ…
Introduces BES (Bidirectional Evolutionary Search), a search framework for LLMs that combines forward candidate evolution with backward goal decomposition to improve sampling on hard reasoning problems during post-training and inference.
@burny_tech: A Survey on Latent Reasoning "Large Language Models (LLMs) have demonstrated impressive reasoning capabilities, especia…
This survey provides a comprehensive overview of latent reasoning in LLMs, exploring methods that perform multi-step inference in continuous hidden states without explicit token-level supervision.
Refining Over Resampling: Test-Time Self-Correction for LLM Reasoning
A new verifier-free breadth-depth refinement framework improves LLM reasoning at test time by sampling multiple rollouts, iteratively refining each via self-critique, and aggregating with majority voting. It consistently outperforms greedy decoding, majority voting, and verifier-based selection across several math benchmarks and open-weight models.
From 0-Order Selection to 2-Order Judgment: Combinatorial Hardening Exposes Compositional Failures in Frontier LLMs
This paper introduces LogiHard, a framework that uses combinatorial hardening to expose compositional failures in frontier LLMs, demonstrating significant accuracy drops in logical reasoning tasks.
@_avichawla: https://x.com/_avichawla/status/2088536550552605174
The article summarizes eight inference-time techniques to improve LLM reasoning, based on research from Google, OpenAI, and Anthropic, with tradeoffs and practical notes.