Tracked topic
Large language models are machine learning models trained to predict and generate text and other language-based outputs.
…Test-Time Co-Evolution of Topology and Capability in LLM-based Multi-Agent Systems Published on May 10 Submitted by Xinyu Lin on May 13 Authors: , , , , , , Abstract Test-time co-evolution framework…
Papers arxiv:2606.02578 Mitigating Perceptual Judgment Bias in Multimodal LLM-as-a-Judge via Perceptual Perturbation and Reward Modeling Published on Jun 1 Submitted by Seojeong Park on Jun 3 KAIST…
…From In-Context Textual Skills to In-Weight Latent Skills for LLM Agents Published on Jun 4 Submitted by Tianyi Xu on Jun 9 Authors: Aofan Yu , Chenyu Zhou , , , , , , , , , Abstract LatentSkill enables…
…Automatically Auditing the Open Skill Ecosystem for LLM Agents Published on May 28 Submitted by jiahao ying on Jun 1 Authors: Jiahao Ying , Boxian Ai , , , Abstract OpenSkillEval is an automatic evaluation framework…
…Generated by Qwen/Qwen2.5-Coder-32B-Instruct LLM agents are evolving from conversational chatbots to operational tools in real-world workspaces. In local agentic harnesses, an LLM can read and write…
…supervised encoders substantially outperform zero-shot LLMs on real-time termination prediction , while next-action prediction remains only moderately successful even for strong LLMs . Taken together, these results show that current models…
…Behavioral Side Effects and Mechanistic Divergence Across LLM Jailbreaks (2026) LLUMI: Improving LLM Writing Assistance for Mental Health Support with Online Community Feedback (2026) Inform, Coach, Relate, Listen: Auditing LLM Caregiving Support…
…Mixture of Indexer Sparse Attention for Long-Context LLM Inference Published on May 8 Submitted by mengfanxu on May 11 Peking University Authors: , , , , , , Abstract MISA replaces the dense token-wise indexing in…
…AI-generated summary Self-evolving LLMs excel in verifiable domains but struggle in open-ended tasks, where reliance on proxy LLM judges introduces capability bottlenecks and reward hacking . To overcome this, we…
…Yet, recent progress in LLM coding has focused on well-defined tasks such as feature implementation, bug fixing, and competitive programming . Open-ended coding remains a weak spot for LLMs, largely because…