Tracked topic
Large language models are machine learning models trained to predict and generate text and other language-based outputs.
Papers arxiv:2606.17053 Context-Aware RL for Agentic and Multimodal LLMs Published on Jun 15 Submitted by py xu on Jun 19 Princeton University Authors: Peiyang Xu , , , , , , Abstract ContextRL enhances long…
Papers arxiv:2605.12978 Useful Memories Become Faulty When Continuously Updated by LLMs Published on May 13 Submitted by Dylan on May 13 University of Illinois at Urbana-Champaign Authors: , , , , , , Abstract Recent…
…Four Axioms of Thought Representation in LLMs Published on May 7 Submitted by Fahd Seddik on Jun 29 #1 Paper of the day University of British Columbia - Okanagan Campus Authors: Fahd Seddik…
…Failure-Aware Meta-Agentic Framework for Open-Source LLMs in Interactive Tool Use Environments Published on Apr 28 Submitted by Amir on Apr 30 Authors: Amir Saeidi , , , , , , Abstract Failure-Aware Meta-Agentic…
…Our construction pipeline rejects 70.3% of LLM -generated candidates at a search-based external-verification stage, calibrating how unreliable industrial QA remains after LLM -only filtering.Our evaluation decouples raw correctness…
…Towards Delegation Intelligence in Agentic LLMs for Long-Horizon Deep Research Published on Jun 8 Submitted by Quan Chen on Jun 10 SearchSwarm Authors: , Quan Chen , , , , , , , , Abstract A large language model trained…
Papers arxiv:2606.01682 Off-the-Shelf LLMs as Process Scorers: Training-Free Alternative to PRMs for Mathematical Reasoning Published on Jun 1 Submitted by Atoosa Chegini on Jun 2 University of…
Papers arxiv:2605.30039 Domain-Specific Data Synthesis for LLMs via Minimal Sufficient Representation Learning Published on May 29 Submitted by Hang Yu on Jun 3 Authors: Tong Ye , , , , , , , , Abstract DOMINO enables…
Papers arxiv:2606.10646 How Does Reasoning Flow? Tracing Attention-Induced Information Flow for Targeted RL in LLMs Published on Jun 9 Submitted by Yang Li (SJTU & SII) on Jun 10 alibaba…
Judge Arena: Benchmarking LLMs as Evaluators