Trends · 研究趋势
数据来自 Hugging Face 论文的 AI 提取关键词,按月统计研究方向的增长与热度。
Pengyi Li, Matvey Skripkin, Alexander Zubrey +2 authors
Reinforcement Learning via Self-Confidence (RLSC) improves large language model accuracy using the model's confidence as a reward signal, eliminating the need for human labels or reward engineering.
Zhiyuan Liang, Dongwen Tang, Yuhao Zhou +11 authors
Drag-and-Drop LLMs generate task-specific parameters through prompt-conditioned parameter generation, achieving significant efficiency gains and cross-domain generalization without per-task training.
Jingdi Lei, Di Zhang, Junxian Li +7 authors
A lightweight memory mechanism called δ-mem enhances large language models by augmenting a frozen attention backbone with a compact associative memory state that provides low-rank corrections to attention computations.
Kimi Team, Angang Du, Bofei Gao +91 authors
A multi-modal LLM trained with reinforcement learning achieves state-of-the-art reasoning performance across various benchmarks by utilizing long context scaling and effective policy optimization methods.
Weizhen Li, Jianbo Lin, Zhuosong Jiang +27 authors
Chain-of-Agents (CoA) paradigm enables end-to-end complex problem-solving in LLMs through dynamic agent activation, improving performance via multi-agent distillation and agentic reinforcement learning.
Jiaru Zou, Xiyuan Yang, Ruizhong Qiu +10 authors
LatentMAS enables efficient, lossless collaboration among LLM agents in latent space, improving performance and reducing computational costs compared to text-based methods.
Hongjin Su, Shizhe Diao, Ximing Lu +13 authors
A small orchestrator using ToolOrchestra method coordinates various intelligent tools with reinforcement learning, achieving higher accuracy and efficiency in solving complex tasks like Humanity's Last Exam compared to larger models.
Siming Huang, Tianhao Cheng, Jason Klein Liu +16 authors
OpenCoder is a top-tier open-access code LLM that provides comprehensive reproducible resources, including data, pipelines, and protocols, to advance code AI research.
Ali Slim, Haydar Hamieh, Jawad Kotaich +5 authors
QuanBench+ evaluates large language models on quantum code generation across multiple frameworks using functional testing and repair-based feedback, revealing significant progress but persistent dependence on framework-specific knowledge.
Minju Seo, Jinheon Baek, Seongyun Lee +1 authors
PaperCoder is a multi-agent LLM framework that converts machine learning papers into functional code repositories through planning, analysis, and generation stages.
Justin Zhao, Timothy Wang, Wael Abid +7 authors
LoRA fine-tuning reduces computational resources while maintaining high performance across various tasks and models, and LoRAX allows for efficient deployment of multiple LLMs on a single GPU.
Bowen Ye, Rang Li, Qibin Yang +10 authors
Claw-Eval addresses limitations in agent benchmarks by providing comprehensive evaluation across multiple modalities with trajectory-aware grading and safety assessments.
Liangcai Su, Zhen Zhang, Guangyu Li +19 authors
AgentFounder, a deep research agent model incorporating Agentic Continual Pre-training, achieves state-of-the-art performance in agentic tasks while maintaining strong tool-use ability.
Yongheng Zhang, Ziang Liu, Jiaxuan Zhu +17 authors
Large Language Models are evolving from conversational systems to integrated AI colleagues with enhanced reasoning capabilities and persistent work environments.
Elisei Rykov, Kseniia Petrushina, Maksim Savkin +6 authors
PsiloQA, a multilingual dataset with span-level hallucinations, enhances hallucination detection in large language models across 14 languages using an automated pipeline and encoder-based models.
Jizhan Fang, Xinle Deng, Haoming Xu +9 authors
LightMem, a memory system inspired by human memory, enhances LLMs by efficiently managing historical interaction information, improving accuracy and reducing computational costs.
Yiran Ding, Li Lyna Zhang, Chengruidong Zhang +5 authors
LongRoPE extends pre-trained LLMs' context window to 2048k tokens with minimal fine-tuning costs and maintains original performance.
Kuang-Huei Lee, Ian Fischer, Yueh-Hua Wu +4 authors
Mind Evolution, an evolutionary search strategy using a language model, outperforms other inference methods in natural language planning tasks by generating, recombining, and refining candidate responses.
Xinlei Yu, Gen Li, Qingyi Si +13 authors
DOPD addresses privilege illusion in on-policy distillation by dynamically routing token-level supervision between teacher and student policies based on advantage gaps and probabilities, improving capability transfer in large and vision-language models.
Ryan Wong, Jiawei Wang, Junjie Zhao +10 authors
WideSearch is a new benchmark evaluating the reliability of automated search agents in large-scale information collection tasks, revealing significant deficiencies in current systems.
北京市昌平区探索星信息技术及软件开发工作室
京ICP备2026059466号