✳flâneur — a map of the web's best reading
Stream of Search (SoS): Learning to Search in Language
arxiv.org · 8,064 words · saved by 4 readers
N/A
# link_15cpla8i8o7.pdf ## Metadata - PDFFormatVersion=1.5 - IsLinearized=false - IsAcroFormPresent=false - IsXFAPresent=false - IsCollectionPresent=false - IsSignaturesPresent=false - CreationDate=D:20240408000238Z - Creator=LaTeX with hyperref - ModDate=D:20240408000238Z - Custom.PTEX.Fullbanner=This is pdfTeX, Version 3.141592653-2.6-1.40.25 (TeX Live 2023) kpathsea version 6.3.5 - Producer=pdfTeX-1.40.25 - Trapped=False ## Contents ### Page 1 Stream of Search (SoS): Learning to Search in LanguageKanishk Gandhi∗Stanford UniversityDenise LeeStanford UniversityGabriel GrandMITMuxin LiuHarve
Explore this link on the map →saved by
related reading
- DeepSeek-R1arxiv.org
- Composer2.pdfcursor.com
- Self-Adapting Language Modelsarxiv.org
- the-illusion-of-thinking.pdfml-site.cdn-apple.com
- o1 and Reasoning | AndoLogsblog.ando.ai
- Language Models can Solve Computer Tasksarxiv.org
- Reasoning as Trajectoriesslhleosun.github.io
- State of RL for reasoning LLMs | A. Weersaweers.de
- Beyond Semantics: The Unreasonable Effectiveness of Reasonless Intermediate Tokensarxiv.org
- The Unintelligibility is Ours: Notes on Chain of Thought1a3orn.com
- Chroma Context-1: Training a Self-Editing Search Agent | Chromatrychroma.com
- Language Modelinglena-voita.github.io