Trending Papers - Hugging Face

Submitted by

amael-apple

Submitted by

amael-apple

Agent READMEs: An Empirical Study of Context Files for Agentic Coding

Agentic coding tools receive goals written in natural language as input, break them down into specific tasks, and write or execute the actual code with minimal human intervention. Central to this process are agent context files ("READMEs for agents") that provide persistent, project-level instructions. In this paper, we conduct the first large-scale empirical study of 2,303 agent context files from 1,925 repositories to characterize their structure, maintenance, and content. We find that these files are not static documentation but complex, difficult-to-read artifacts that evolve like configuration code, maintained through frequent, small additions. Our content analysis of 16 instruction types shows that developers prioritize functional context, such as build and run commands (62.3%), implementation details (69.9%), and architecture (67.7%). We also identify a significant gap: non-functional requirements like security (14.5%) and performance (14.5%) are rarely specified. These findings indicate that while developers use context files to make agents functional, they provide few guardrails to ensure that agent-written code is secure or performant, highlighting the need for improved tooling and practices.

Agent READMEs: An Empirical Study of Context Files for Agentic Coding

Agentic coding tools receive goals written in natural language as input, break them down into specific tasks, and write or execute the actual code with minimal human intervention. Central to this process are agent context files ("READMEs for agents") that provide persistent, project-level instructions. In this paper, we conduct the first large-scale empirical study of 2,303 agent context files from 1,925 repositories to characterize their structure, maintenance, and content. We find that these files are not static documentation but complex, difficult-to-read artifacts that evolve like configuration code, maintained through frequent, small additions. Our content analysis of 16 instruction types shows that developers prioritize functional context, such as build and run commands (62.3%), implementation details (69.9%), and architecture (67.7%). We also identify a significant gap: non-functional requirements like security (14.5%) and performance (14.5%) are rarely specified. These findings indicate that while developers use context files to make agents functional, they provide few guardrails to ensure that agent-written code is secure or performant, highlighting the need for improved tooling and practices.

VibeVoice Technical Report

VibeVoice synthesizes long-form multi-speaker speech using next-token diffusion and a highly efficient continuous speech tokenizer, achieving superior performance and fidelity.

VibeVoice Technical Report

VibeVoice synthesizes long-form multi-speaker speech using next-token diffusion and a highly efficient continuous speech tokenizer, achieving superior performance and fidelity.

Submitted by

taesiri

Submitted by

taesiri

Submitted by

andito

Submitted by

andito

Submitted by

Cxxs

Submitted by

Cxxs

Submitted by

Paper99

Submitted by

Paper99

DeepCode: Open Agentic Coding

DeepCode, a fully autonomous framework, addresses the challenges of document-to-codebase synthesis by optimizing information flow through source compression, structured indexing, knowledge injection, and error correction, achieving state-of-the-art performance and surpassing human experts.

DeepCode: Open Agentic Coding

DeepCode, a fully autonomous framework, addresses the challenges of document-to-codebase synthesis by optimizing information flow through source compression, structured indexing, knowledge injection, and error correction, achieving state-of-the-art performance and surpassing human experts.

Step-GUI Technical Report

A self-evolving training pipeline with the Calibrated Step Reward System and GUI-MCP protocol improve GUI automation efficiency, accuracy, and privacy in real-world scenarios.

StepFun · Published on Dec 17, 2025

Step-GUI Technical Report

A self-evolving training pipeline with the Calibrated Step Reward System and GUI-MCP protocol improve GUI automation efficiency, accuracy, and privacy in real-world scenarios.

Submitted by

akhaliq

Submitted by

akhaliq

Submitted by

akhaliq

Submitted by

akhaliq

SAM 3: Segment Anything with Concepts

Segment Anything Model 3 achieves state-of-the-art performance in promptable concept segmentation and tracking by leveraging a unified model architecture with decoupled recognition and localization.

SAM 3: Segment Anything with Concepts

Segment Anything Model 3 achieves state-of-the-art performance in promptable concept segmentation and tracking by leveraging a unified model architecture with decoupled recognition and localization.

Submitted by

taesiri

Submitted by

taesiri

Submitted by

FrancisRing

Submitted by

FrancisRing

Memory in the Age of AI Agents

This survey provides an updated overview of agent memory research, distinguishing its forms, functions, and dynamics, and highlights emerging research directions.

Memory in the Age of AI Agents

This survey provides an updated overview of agent memory research, distinguishing its forms, functions, and dynamics, and highlights emerging research directions.

In Pursuit of Pixel Supervision for Visual Pre-training

Pixio, an enhanced masked autoencoder, demonstrates competitive performance across various downstream tasks using pixel-space self-supervised learning, outperforming latent-space approaches.

Submitted by

LiheYoung

Self-Supervised Prompt Optimization

A self-supervised framework optimizes prompts for both closed and open-ended tasks by evaluating LLM outputs without external references, reducing costs and required data.

Self-Supervised Prompt Optimization

A self-supervised framework optimizes prompts for both closed and open-ended tasks by evaluating LLM outputs without external references, reducing costs and required data.

Submitted by

taesiri

Submitted by

taesiri

Submitted by

rmurthy

Submitted by

rmurthy

Submitted by

wanderkid

Submitted by

wanderkid

Submitted by

taesiri

Submitted by

taesiri

Submitted by

akhaliq

Submitted by

akhaliq

Submitted by

Wayne-King

Submitted by

Wayne-King

Submitted by

Yhmeng1106

Submitted by

Yhmeng1106

Towards Scalable Pre-training of Visual Tokenizers for Generation

A unified visual tokenizer pre-training framework (VTP) improves generative performance by optimizing image-text contrastive, self-supervised, and reconstruction losses, leading to better scaling properties and higher zero-shot accuracy and faster convergence.

MiniMax · Published on Dec 15, 2025

Towards Scalable Pre-training of Visual Tokenizers for Generation

A unified visual tokenizer pre-training framework (VTP) improves generative performance by optimizing image-text contrastive, self-supervised, and reconstruction losses, leading to better scaling properties and higher zero-shot accuracy and faster convergence.

Submitted by

Snyhlxde

Submitted by

Snyhlxde

LightRAG: Simple and Fast Retrieval-Augmented Generation

LightRAG improves Retrieval-Augmented Generation by integrating graph structures for enhanced contextual awareness and efficient information retrieval, achieving better accuracy and response times.

Submitted by

AdinaY

Submitted by

AdinaY

Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory

Mem0, a memory-centric architecture with graph-based memory, enhances long-term conversational coherence in LLMs by efficiently extracting, consolidating, and retrieving information, outperforming existing memory systems in terms of accuracy and computational efficiency.

Submitted by

akhaliq

Submitted by

Weiyun1025

Submitted by

Weiyun1025

Submitted by

xw-eric

Submitted by

xw-eric

Submitted by

xw-eric

Submitted by

xw-eric

The Unreasonable Effectiveness of Scaling Agents for Computer Use

Behavior Best-of-N (bBoN) improves the reliability and success rates of computer-use agents by generating and selecting among multiple rollouts using behavior narratives, achieving state-of-the-art performance on OSWorld and strong generalization to different operating systems.

Simular · Published on Oct 2, 2025

The Unreasonable Effectiveness of Scaling Agents for Computer Use

Behavior Best-of-N (bBoN) improves the reliability and success rates of computer-use agents by generating and selecting among multiple rollouts using behavior narratives, achieving state-of-the-art performance on OSWorld and strong generalization to different operating systems.

Single-stream Policy Optimization

Single-stream Policy Optimization (SPO) improves policy-gradient training for Large Language Models by eliminating group-based issues and providing a stable, low-variance learning signal, leading to better performance and efficiency.

Tencent · Published on Sep 16, 2025

Single-stream Policy Optimization

Single-stream Policy Optimization (SPO) improves policy-gradient training for Large Language Models by eliminating group-based issues and providing a stable, low-variance learning signal, leading to better performance and efficiency.

LongCat-Video Technical Report

LongCat-Video, a 13.6B parameter video generation model based on the Diffusion Transformer framework, excels in efficient and high-quality long video generation across multiple tasks using unified architecture, coarse-to-fine generation, and block sparse attention.

LongCat · Published on Oct 25, 2025

LongCat-Video Technical Report

LongCat-Video, a 13.6B parameter video generation model based on the Diffusion Transformer framework, excels in efficient and high-quality long video generation across multiple tasks using unified architecture, coarse-to-fine generation, and block sparse attention.

Submitted by

taesiri

Submitted by

taesiri

Submitted by

yulunliu

Submitted by

yulunliu

Submitted by

Jiasheng1110

Submitted by

Jiasheng1110

Submitted by

mervenoyan

Submitted by

mervenoyan

Submitted by

dyyyyyyyy

Submitted by

dyyyyyyyy

Submitted by

wenbowen

Submitted by

wenbowen

Submitted by

Jeff-Wang

Submitted by

Jeff-Wang

Submitted by

Owen777

Submitted by

Owen777