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.

Very Large-Scale Multi-Agent Simulation in AgentScope

Enhancements to the AgentScope platform improve scalability, efficiency, and ease of use for large-scale multi-agent simulations through distributed mechanisms, flexible environments, and user-friendly tools.

Submitted by

akhaliq

Submitted by

taesiri

Submitted by

taesiri

Submitted by

taesiri

Submitted by

taesiri

Submitted by

yyamada

Submitted by

yyamada

Hyperagents

Hyperagents represent a self-referential framework that integrates task and meta-agents into a single editable program, enabling metacognitive self-modification and open-ended improvement across diverse computational domains.

Hyperagents

Hyperagents represent a self-referential framework that integrates task and meta-agents into a single editable program, enabling metacognitive self-modification and open-ended improvement across diverse computational domains.

Submitted by

daixufang

Submitted by

daixufang

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

ethanchern

Submitted by

ethanchern

Multi-Agent Collaboration via Evolving Orchestration

A centralized orchestrator dynamically directs LLM agents via reinforcement learning, achieving superior multi-agent collaboration in varying tasks with reduced computational costs.

Multi-Agent Collaboration via Evolving Orchestration

A centralized orchestrator dynamically directs LLM agents via reinforcement learning, achieving superior multi-agent collaboration in varying tasks with reduced computational costs.

AutoDev: Automated AI-Driven Development

AutoDev is an AI-driven software development framework that automates complex engineering tasks within a secure Docker environment, achieving high performance in code and test generation.

AutoDev: Automated AI-Driven Development

AutoDev is an AI-driven software development framework that automates complex engineering tasks within a secure Docker environment, achieving high performance in code and test generation.

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

taesiri

Submitted by

taesiri

Submitted by

akhaliq

Submitted by

akhaliq

Submitted by

Huaxiu

Submitted by

Huaxiu

Submitted by

Wyattz23

Submitted by

Wyattz23

Submitted by

akhaliq

Submitted by

akhaliq

Submitted by

youganglyu

Submitted by

youganglyu

Position: Agentic Evolution is the Path to Evolving LLMs

Large language models face limitations in adapting to changing real-world environments, necessitating a new approach called agentic evolution that treats deployment-time improvement as a goal-directed optimization process.

Position: Agentic Evolution is the Path to Evolving LLMs

Large language models face limitations in adapting to changing real-world environments, necessitating a new approach called agentic evolution that treats deployment-time improvement as a goal-directed optimization process.

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

kpzhang996

Submitted by

kpzhang996

Submitted by

andito

Submitted by

andito

Memento-Skills: Let Agents Design Agents

A generalist language model agent system autonomously designs and improves task-specific agents through memory-based reinforcement learning with stateful prompts and skill libraries.

Memento-Skills: Let Agents Design Agents

A generalist language model agent system autonomously designs and improves task-specific agents through memory-based reinforcement learning with stateful prompts and skill libraries.

OpenClaw-RL: Train Any Agent Simply by Talking

OpenClaw-RL framework enables policy learning from diverse next-state signals across multiple interaction modalities using asynchronous training with PRM judges and hindsight-guided distillation.

OpenClaw-RL: Train Any Agent Simply by Talking

OpenClaw-RL framework enables policy learning from diverse next-state signals across multiple interaction modalities using asynchronous training with PRM judges and hindsight-guided distillation.

Submitted by

taesiri

Submitted by

taesiri

Submitted by

akhaliq

Submitted by

akhaliq

Submitted by

akhaliq

Submitted by

akhaliq

Submitted by

Virgilllll

Submitted by

Virgilllll

PixelSmile: Toward Fine-Grained Facial Expression Editing

A diffusion framework called PixelSmile is introduced that disentangles facial expression semantics through symmetric joint training and contrastive learning to enable precise, controllable, and fine-grained expression editing with robust identity preservation.

PixelSmile: Toward Fine-Grained Facial Expression Editing

A diffusion framework called PixelSmile is introduced that disentangles facial expression semantics through symmetric joint training and contrastive learning to enable precise, controllable, and fine-grained expression editing with robust identity preservation.

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.

MemOS: A Memory OS for AI System

MemOS, a memory operating system for Large Language Models, addresses memory management challenges by unifying plaintext, activation-based, and parameter-level memories, enabling efficient storage, retrieval, and continual learning.

MemOS: A Memory OS for AI System

MemOS, a memory operating system for Large Language Models, addresses memory management challenges by unifying plaintext, activation-based, and parameter-level memories, enabling efficient storage, retrieval, and continual learning.

LTX-2: Efficient Joint Audio-Visual Foundation Model

LTX-2 is an open-source audiovisual diffusion model that generates synchronized video and audio content using a dual-stream transformer architecture with cross-modal attention and classifier-free guidance.

Submitted by

taesiri

Submitted by

bertjiazheng

Submitted by

bertjiazheng

Qwen3-TTS Technical Report

The Qwen3-TTS series presents advanced multilingual text-to-speech models with voice cloning and controllable speech generation capabilities, utilizing dual-track LM architecture and specialized speech tokenizers for efficient streaming synthesis.

Qwen

· Published on Jan 22, 2026

Qwen3-TTS Technical Report

The Qwen3-TTS series presents advanced multilingual text-to-speech models with voice cloning and controllable speech generation capabilities, utilizing dual-track LM architecture and specialized speech tokenizers for efficient streaming synthesis.

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.

Submitted by

wchengad

Submitted by

wchengad

Submitted by

florinshum

Submitted by

florinshum

Fish Audio S2 Technical Report

Fish Audio S2 is an open-source text-to-speech system with multi-speaker capabilities, multi-turn generation, and instruction-following control through natural-language descriptions, utilizing a multi-stage training approach and production-ready inference engine.

Fish Audio S2 Technical Report

Fish Audio S2 is an open-source text-to-speech system with multi-speaker capabilities, multi-turn generation, and instruction-following control through natural-language descriptions, utilizing a multi-stage training approach and production-ready inference engine.

Cybersecurity AI: Humanoid Robots as Attack Vectors

The Unitree G1 humanoid robot is vulnerable to BLE provisioning protocol exploits, exfiltrates sensor data, and can be repurposed for active cyber operations, highlighting the need for improved security standards in commercial robotics.

Cybersecurity AI: Humanoid Robots as Attack Vectors

The Unitree G1 humanoid robot is vulnerable to BLE provisioning protocol exploits, exfiltrates sensor data, and can be repurposed for active cyber operations, highlighting the need for improved security standards in commercial robotics.

Submitted by

syxbb

Submitted by

syxbb