PulseAugur
实时 22:03:23
实体 LLM

LLM

PulseAugur coverage of LLM — every cluster mentioning LLM across labs, papers, and developer communities, ranked by signal.

Show in brief
总计 · 30天
1271
90 天内 1271
发布 · 30天
0
90 天内 0
论文 · 30天
763
90 天内 763
层级分布 · 90 天
关系
时间线
  1. 2026-05-25 research_milestone Researchers introduce a multi-agent LLM system for generating physics-constrained constitutive models. 来源
  2. 2026-05-22 research_milestone Researchers published a paper detailing a new multi-agent LLM approach for generating physics-constrained constitutive models. 来源
  3. 2026-05-21 research_milestone Development of a multi-agent LLM that learns to defer to human input. 来源
  4. 2026-05-15 research_milestone A paper details the use of an LLM-guided tree search algorithm for scientific discovery, specifically in optimizing photovoltaic structures. 来源
  5. 2026-05-14 research_milestone A new paper proposes a method combining LLMs with neural processes for text-conditioned regression. 来源
  6. 2026-05-13 research_milestone A new paper reveals that prior harmful actions can steer LLM decisions toward unsafe actions, especially when consistency is emphasized. 来源
  7. 2026-05-11 research_milestone Researchers proposed a new framework for formally evaluating LLM guardrail classifiers. 来源
情绪 · 30 天

25 天有情绪数据

最近 · 第 2/10 页 · 共 200 条
  1. TOOL · CL_48974 ·

    LLM agents automate clinical scoring system construction

    Researchers have developed AgentScore, a novel method for automatically constructing clinical scoring systems using LLM agents. This approach addresses the challenge of creating interpretable and deployable clinical gui…

  2. TOOL · CL_48829 ·

    LLM agent tool-call traffic detection framework uses graph neural networks

    Researchers have developed a novel framework for detecting attacks within the tool-call traffic of Large Language Model (LLM) agents. This system represents agent sessions as graphs, incorporating sentence-embedding fea…

  3. TOOL · CL_48827 ·

    New benchmark tests LLM agents on circuit design challenges

    Researchers have developed PostEDA-Bench, a new benchmark designed to evaluate the performance of Large Language Model (LLM) agents in the final stages of circuit design. This benchmark addresses limitations in existing…

  4. TOOL · CL_48812 ·

    New attack framework exposes LLM grading agent vulnerabilities

    Researchers have developed a new framework called GradingAttack to expose security vulnerabilities in large language model (LLM) based educational grading agents. The study introduces token-level and prompt-level attack…

  5. TOOL · CL_48801 ·

    Reinforcement learning optimizes knowledge graph retrieval for LLMs

    Researchers have developed KG-R1, a novel framework that uses reinforcement learning to optimize knowledge-graph retrieval-augmented generation (KG-RAG) systems. Unlike existing methods that employ fixed pipelines of mu…

  6. TOOL · CL_48725 ·

    New taxonomy identifies prevalent 'LLM code smells' in software

    Researchers have developed a new taxonomy and detection method for "LLM code smells," which are poor integration practices of large language models in software systems. Their static analysis tool, SpecDetect4LLM, was ev…

  7. TOOL · CL_48712 ·

    LLMs struggle with geopolitical coercion in Greenland sovereignty simulation

    Researchers have developed a novel AI stress test using the Greenland sovereignty dispute to evaluate geopolitical decision-making in large language models. The study simulated thousands of games where eight frontier LL…

  8. MEME · CL_48415 ·

    User seeks participants for LLM Turing Test website

    A user has created a website designed as a Turing Test to gather data on human versus AI detection of LLM responses. The project involves users playing rounds where they are matched with either a human or one of four la…

  9. TOOL · CL_47456 ·

    Guide released for running local LLMs on Windows hardware

    A new guide offers advice on selecting hardware for running large language models locally on Windows and Intel-based systems. It covers essential components like GPUs and other hardware considerations for users interest…

  10. COMMENTARY · CL_47372 ·

    Developers grapple with multi-provider LLM integration challenges

    Developers are increasingly using multiple large language models (LLMs) from different providers, leading to complex integration challenges. Simple API wrappers often fall short of addressing the core needs for managing…

  11. TOOL · CL_47373 ·

    Developer calibrates LLM judge for realistic ad script scoring

    A developer created a system to generate ad scripts, where the LLM initially assigned overly high scores to the generated hooks. To address this, the developer implemented a three-layer approach within the system prompt…

  12. COMMENTARY · CL_47326 ·

    AI researcher warns of 'mad LLM disease' from self-generated data

    An AI researcher has coined the term "mad LLM disease" to describe a phenomenon where large language models degrade when they are trained on their own generated output. This concept is compared to mad cow disease, which…

  13. TOOL · CL_47333 ·

    Python pipeline uses LLMs for structured data extraction from markdown

    This article details a Python pipeline designed to extract structured data from unstructured markdown documents using large language models. It emphasizes the limitations of traditional markdown parsers for semantic con…

  14. TOOL · CL_47293 ·

    LLM proxy adds recovery endpoint to prevent agent progress loss

    A new Go-based LLM proxy called Trooper has introduced a novel recovery endpoint designed to prevent agents from losing progress during multi-agent workflows. Unlike traditional proxies that simply retry requests or fal…

  15. TOOL · CL_47065 ·

    RAG pipeline evaluation framework addresses retrieval and generation failures

    This article outlines a comprehensive framework for evaluating Retrieval-Augmented Generation (RAG) pipelines, emphasizing the need to assess both the retrieval and generation components independently. It highlights com…

  16. TOOL · CL_47052 ·

    ByteDance study: Question-answering outperforms transcription for LLM document training

    A ByteDance study demonstrates that a 7B parameter model can effectively process and answer questions about lengthy, image-rich documents. This approach, which involves the model learning by answering questions and loca…

  17. TOOL · CL_47074 ·

    New AI architecture integrates LLMs with Oracle EBS without core rewrite

    A new architectural approach has been developed to integrate generative AI with monolithic enterprise systems like Oracle E-Business Suite (EBS) without altering the core legacy code. This method involves creating a lig…

  18. COMMENTARY · CL_46992 ·

    Lisp, Scheme projects reveal mixed stances on AI code contributions

    A recent survey of Lisp and Scheme programming projects reveals varying stances on the use of AI-generated code. As of May 2026, many projects have established policies, with some strictly prohibiting LLM contributions …

  19. TOOL · CL_46965 ·

    Skillpunk architecture distributes AI intelligence away from LLM orchestrators

    The Skillpunk architecture proposes a shift from centralized LLM orchestrators to a distributed model where individual skills possess autonomy. Unlike current LLM integrations that treat tool calls as one-off events, Sk…

  20. TOOL · CL_46927 ·

    VS Code extension streamlines Markdown writing with smart paste and sync

    A developer created a VS Code extension called Marksmith to improve the Markdown writing experience by addressing common workflow frustrations. The extension features 'Smart Paste' to automatically format copied tables …