Tracked topic
Large language models are machine learning models trained to predict and generate text and other language-based outputs.
…Enhancing knowledge graph traversal/retrieval with planning mechanism for Personalized LLM Agents Published on May 13 Submitted by Mikhail Menschikov on May 14 Skoltech Authors: Mikhail Menschikov , , , , , , , , , , Abstract PersonalAI 2.0 enhances…
Papers arxiv:2605.27354 Guiding LLM Post-training Data Engineering with Model Internals from Sparse Autoencoders Published on May 26 Submitted by Xiaozhi Wang on May 28 Authors: Yi Jing , , , , , , Xiaozhi Wang…
…Evaluating LLM Agents for Forward-Looking AI Research Judgment Published on Jun 4 Submitted by BruceLyu on Jun 5 Authors: , , , , Abstract ForeSci is a temporally controlled benchmark that evaluates LLM agents' ability…
…A Survey on the Evolution of LLM Agent Memory Mechanisms Published on May 7 Submitted by Hongzhan Lin on May 11 Authors: , , , , , , , , Abstract Large language model agents rely on memory mechanisms that…
…Fine-tuning a 4-billion-parameter LLM on BioTool yields substantial improvements in biomedical tool-calling performance, outperforming cutting-edge commercial LLMs such as GPT-5.1. Furthermore, human expert evaluations demonstrate…
Papers arxiv:2605.13941 EvolveMem:Self-Evolving Memory Architecture via AutoResearch for LLM Agents Published on May 13 Submitted by JiaqiLiu on May 15 Authors: Jiaqi Liu , , , , , , Abstract EvolveMem enables adaptive memory…
…AI-generated summary Watermarking for large language models (LLMs) is a promising approach for detecting LLM-generated text and enabling responsible deployment. However, existing watermarking methods are often vulnerable to semantic-invariant…
…In this paper, we formalise deployment-time learning (DTL) as the third stage in the LLM lifecycle that enables LLM agents to improve from experience during deployment without modifying model parameters. We…
…A Library-OS-Inspired Runtime for Long-Running, Capability-Controlled LLM Agents Published on Jun 2 Submitted by Yingqi Zhang on Jun 4 Tsinghua University Authors: Yingqi Zhang Abstract Agent libOS provides…
…Meno and Friends in a Judge-Orchestrated LLM Ensemble for Faithful Multi-Turn Response Generation Published on May 6 Submitted by Ivan Bondarenko on May 8 Novosibirsk State University Authors: Ivan Bondarenko…