Tracked topic
Large language models are machine learning models trained to predict and generate text and other language-based outputs.
…Liangqi Yuan , , , , Abstract Collaborative intelligence enables multiple distributed LLMs to work together across devices and clouds to provide high-quality responses under diverse resource constraints. AI-generated summary Large language models (LLMs…
…View arXiv page View PDF Add to collection Community Autonomous training for large language models (LLMs) is entering a new era. Rather than relying on a static recipe, EvoTrainer enables LLM policies…
…An Optimizing Compiler for Structured LLM Workflows Published on May 13 Submitted by Junyan Li on May 14 University of Massachusetts Amherst Authors: , , , , Abstract FlowCompile is a structured LLM workflow compiler that…
…Text-Guided Flow Matching in Activation Space for Versatile LLM Steering Published on May 28 Submitted by yingdong shi on May 29 ShanghaiTech University Authors: , , , , , , Abstract UniSteer uses text-guided activation flow…
Papers arxiv:2606.09821 Rethinking the Divergence Regularization in LLM RL Published on Jun 8 Submitted by Xiangxin Zhou on Jun 10 Tencent-Hunyuan-Multimodal-RL Authors: , Xiangxin Zhou , Penghui Qi , , , Tianyu…
Papers arxiv:2605.09271 Shaping Schema via Language Representation as the Next Frontier for LLM Intelligence Expanding Published on May 10 Submitted by zhiqin yang on May 12 Authors: , , , , , Abstract Language representation…
…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…