Tracked topic
Large language models are machine learning models trained to predict and generate text and other language-based outputs.
…Contrastive Skill Distillation for LLM Agents Published on Aug 4 Submitted by Qiming Shi on Aug 6 Zhejiang University Authors: , , , , , , , Abstract SKILL-KD improves weaker LLM agents by distilling teacher-student trajectory…
…Generated by Qwen/Qwen2.5-Coder-32B-Instruct Reinforcement learning (RL) has become a dominant post-training paradigm , enabling large language models (LLMs) to learn from rewards. We observe that societal regulations…
…Evaluating Persona-Sensitive Influencing in Persuasive Dialogues Published on Jun 1 Submitted by 韩沛煊 on Jun 3 Authors: , , , , , Abstract LLMs demonstrate limited effectiveness in persuasive conversation despite generating coherent arguments, with user…
…Model-Aware Skill Alignment for LLM Agents Published on May 29 Submitted by jianxiangyu on Jun 2 Authors: , , , , , Abstract Model-aware skill alignment framework adapts skills to different backbones through hierarchical evolution…
…The rise of large language models (LLMs) offers a promising direction for sequential behavior prediction , yet LLMs struggle with latent behavioral pattern induction and model-intrinsic cognitive biases when tackling long-horizon…
Papers arxiv:2605.30260 How LoRA Remembers? A Parametric Memory Law for LLM Finetuning Published on May 28 Submitted by Ningyu Zhang on May 29 AGI Lab Authors: , , , , , , Ningyu Zhang Abstract Research…
…Resolution-Adaptive KV Cache with Hierarchical Semantic Memory for Long-Context LLM Inference Published on Jun 30 Submitted by Amirhossein Abaskohi on Jul 7 Microsoft Authors: , , , Abstract SeKV introduces a resolution-adaptive…
…A Benchmark for Evaluating Multilingual LLM Safety in South Asia (2026) ML-Bench&Guard: Policy-Grounded Multilingual Safety Benchmark and Guardrail for Large Language Models (2026) HarmChip: Evaluating Hardware Security Centric LLM…
Papers arxiv:2606.07867 The Cold-Start Safety Gap in LLM Agents Published on Jun 5 Submitted by Chung-En, Sun on Jun 12 Authors: Chung-En Sun , , Abstract Tool-calling language…
Papers arxiv:2606.28186 Cognitive Episodes in LLM Reasoning Traces Enable Interpretable Human Item Difficulty Prediction Published on Jun 26 Submitted by Ming Li on Jun 30 Authors: , , , , , , Abstract Epi2Diff framework transforms…