Subject
5 entries
Paper
Bookmarks
The Rise and Potential of LLM-Based Agents: A Survey
An 86-page survey paper by Zhiheng Xi et al. comprehensively mapping the architecture, capabilities, and applications of LLM-based agents — establishing the planning/memory/tool-use framework that became the standard way to think about agent components. The field's foundational survey document.
PDFTriage: Question Answering over Long, Structured Documents
PDFTriage is a method for question answering over long, structured PDF documents that uses the document's structure (pages, sections, tables of contents) as a triage layer before retrieval — letting the LLM navigate the document intelligently rather than relying on flat embedding search.
Arxiv Paper 2309.08963
An arxiv paper from September 2023 saved alongside the LLM agent survey and RAG papers from the same day — likely in the LLM reasoning, agents, or retrieval space based on context. Content unavailable from the bookmark.
Landmark Attention: Random-Access Infinite Context
Landmark Attention paper extending LLaMA 7B to 32k token context by using landmark tokens to represent blocks of input, enabling attention-based retrieval of relevant blocks rather than attending over all tokens. Achieves near-GPT-4 context length through architectural change rather than longer pretraining.
The Alignment Problem from a Deep Learning Perspective
The Alignment Problem from a Deep Learning Perspective (Ngo, Chan, Mindermann, 2022) — frames AI alignment as a problem of specification, robustness, and assurance in deep learning systems. An influential restatement of alignment concerns in terms of modern ML rather than AGI thought experiments.