✳flâneur — a map of the web's best reading
1b44b878bb782e6954cd888628510e90-Paper-Conference.pdf
proceedings.neurips.cc · 9,087 words · saved by 1 readers
N/A
# link_rxvocr3tgy.pdf ## Metadata - PDFFormatVersion=1.5 - IsLinearized=true - IsAcroFormPresent=false - IsXFAPresent=false - IsCollectionPresent=false - IsSignaturesPresent=false - CreationDate=D:20231027175428Z - Creator=LaTeX with hyperref - ModDate=D:20231027175428Z - Custom.PTEX.Fullbanner=This is pdfTeX, Version 3.141592653-2.6-1.40.24 (TeX Live 2022) kpathsea version 6.3.4 - Producer=pdfTeX-1.40.24 - Trapped=False ## Contents ### Page 1 Reflexion: Language Agents with Verbal Reinforcement LearningNoah ShinnNortheastern Universitynoahshinn024@gmail.comFederico CassanoNortheastern Univ
Explore this link on the map →saved by
related reading
- LLM Powered Autonomous Agents | Lil'Loglilianweng.github.io
- [2303.11366] Reflexion: Language Agents with Verbal Reinforcement Learningarxiv.org
- Language Models can Solve Computer Tasksarxiv.org
- Composer2.pdfcursor.com
- DeepSeek-R1arxiv.org
- Explore | alphaXivalphaxiv.org
- [2507.19457] GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learningarxiv.org
- Andrej Karpathy — AGI is still a decade awaydwarkesh.com
- Can LLMs Critique and Iterate on Their Own Outputs? | Eric Jangevjang.com
- o1 and Reasoning | AndoLogsblog.ando.ai
- Meta-Prompt: A Simple Self-Improving Language Agentnoahgoodman.substack.com
- MirrorCode: Evidence AI can already do some weeks-long coding tasks | Epoch AIepoch.ai