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。
Yuhao Wu, Jingyuan Zhang, Jiajun Shi +16 authors
HarnessDev evaluates agents by measuring their ability to build and iteratively improve execution infrastructure rather than final task outputs, revealing that self-built harnesses vary widely in capability and efficiency and transfer poorly across models.
Keke Lian, Bin Wang, Lei Zhang +18 authors
A.S.E is a repository-level benchmark for evaluating the security of AI-generated code, highlighting challenges in secure coding and the limitations of LLMs in real-world scenarios.
Grégoire Mialon, Clémentine Fourrier, Craig Swift +3 authors
GAIA benchmarks general AI assistants using real-world questions that challenge both reasoning and multi-modality handling, showcasing a significant gap between human and AI performance.
Khalil Hennara, Muhammad Hreden, Mohamed Motaism Hamed +3 authors
Mutarjim is a compact Arabic-English translation model that outperforms larger models on established benchmarks and achieves state-of-the-art performance on a new comprehensive Tarjama-25 benchmark.
Yang Wang, Chenghao Xiao, Chia-Yi Hsiao +4 authors
LLMs struggle with understanding the nuanced, context-dependent meanings of Drivelological text, which appears nonsensical but contains deeper semantic layers.
Mo Yu, Lemao Liu, Junjie Wu +5 authors
A study investigates whether large language models understand physical concepts through a grid-based task, showing that they significantly underperform compared to humans and highlighting the stochastic parrot phenomenon.
Shenzhi Wang, Le Yu, Chang Gao +15 authors
Token entropy patterns are crucial in RLVR, with high-entropy tokens significantly impacting reasoning performance and model optimization.
Zijian Wu, Xiangyan Liu, Xinyuan Zhang +12 authors
MCPMark is a comprehensive benchmark for evaluating MCP use in real-world workflows, featuring diverse tasks that require richer interactions with the environment, and reveals that current LLMs perform poorly on these tasks.
Anton Razzhigaev, Matvey Mikhalchuk, Temurbek Rahmatullaev +4 authors
Analysis of Large Language Models reveals that even minor tokens are crucial for context, and introduces LLM-Microscope for assessing token-level nonlinearity and contextual memory.
B. Y. Yan, Chaofan Li, Hongjin Qian +2 authors
GAM, a novel framework that employs JIT compilation principles, improves memory efficiency and task completion by leveraging a lightweight memorizer and researcher in conjunction with reinforcement learning.
Heejun Lee, Geon Park, Jaduk Suh +1 authors
InfiniteHiP is a novel LLM inference framework that enhances long-context processing with token pruning, RoPE adjustment, and host memory offloading, enabling faster and more memory-efficient operation.
Qiying Yu, Zheng Zhang, Ruofei Zhu +32 authors
The DAPO algorithm, which includes decoupled clip and dynamic sampling policy optimization, enables open-source, high-performance reinforcement learning training for large-scale language models, enhancing reproducibility in the field.
Zonghang Li, Tao Li, Wenjiao Feng +2 authors
Prima.cpp, a distributed inference system, enables running large language models on home devices using CPU/GPU and low memory, overcoming hardware limitations.
Ruofeng Yang, Yongcan Li, Shuai Li
ARIS is an open-source research harness that uses cross-model adversarial collaboration to ensure reliable long-term research outcomes through coordinated execution, orchestration, and assurance layers.
Yuzhang Tian, Jianbo Zhao, Haoyu Dong +8 authors
SpreadsheetLLM introduces SheetCompressor and Chain of Spreadsheet to enhance LLMs' performance on spreadsheet tasks through efficient encoding and understanding.
Chengsong Huang, Wenhao Yu, Xiaoyang Wang +6 authors
R-Zero is a self-evolving framework that autonomously generates and learns from its own training data, improving reasoning capabilities in LLMs without human-curated tasks.
Ganqu Cui, Yuchen Zhang, Jiacheng Chen +14 authors
Entropy dynamics in reinforcement learning with large language models are investigated to prevent policy entropy collapse and improve exploration.
Zhichao Wang, Dongyang Ma, Xinting Huang +6 authors
AutoDeco, a novel architecture, enables end-to-end generation by dynamically predicting decoding parameters, outperforming default strategies and achieving performance close to an oracle-tuned baseline.
Pei Zhou, Jay Pujara, Xiang Ren +7 authors
SELF-DISCOVER is a framework enabling LLMs to generate task-specific reasoning structures, enhancing performance on complex reasoning tasks with reduced computational cost.
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.
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