Models
Datasets
Spaces
Buckets new
Docs
Enterprise
Pricing
- Website
- Community
- Solutions
Log In
Sign Up

Collections

Discover the best community collections!

Collections including paper arxiv:2603.03205

Agent Safety and Prompt Injection Guardrails

Curated papers, models, datasets, and demos for AI-agent runtime safety, prompt injection, MCP security, and tool-call guardrails.

MCP Safety Audit: LLMs with the Model Context Protocol Allow Major Security Exploits

Paper • 2504.03767 • Published Apr 2, 2025 • 3
Prompt Injection Attacks on Agentic Coding Assistants: A Systematic Analysis of Vulnerabilities in Skills, Tools, and Protocol Ecosystems

Paper • 2601.17548 • Published Jan 24 • 1
ToolSafe: Enhancing Tool Invocation Safety of LLM-based agents via Proactive Step-level Guardrail and Feedback

Paper • 2601.10156 • Published Jan 15 • 26
Learning When to Act or Refuse: Guarding Agentic Reasoning Models for Safe Multi-Step Tool Use

Paper • 2603.03205 • Published Mar 3 • 13

Endless Terminals: Scaling RL Environments for Terminal Agents

Paper • 2601.16443 • Published Jan 23 • 20
Linear representations in language models can change dramatically over a conversation

Paper • 2601.20834 • Published Jan 28 • 21
Scaling Embeddings Outperforms Scaling Experts in Language Models

Paper • 2601.21204 • Published Jan 29 • 107
Teaching Models to Teach Themselves: Reasoning at the Edge of Learnability

Paper • 2601.18778 • Published Jan 26 • 44

Multi-Agent Infrastructure

Latent Collaboration in Multi-Agent Systems

Paper • 2511.20639 • Published Nov 25, 2025 • 131
Learning When to Act or Refuse: Guarding Agentic Reasoning Models for Safe Multi-Step Tool Use

Paper • 2603.03205 • Published Mar 3 • 13
Hyperagents

Paper • 2603.19461 • Published Mar 19 • 51
Code-as-Room: Generating 3D Rooms from Top-Down View Images via Agentic Code Synthesis

Paper • 2605.18451 • Published May 18 • 40

Large Language Models

Universal Deep Research: Bring Your Own Model and Strategy

Paper • 2509.00244 • Published Aug 29, 2025 • 14
The Landscape of Agentic Reinforcement Learning for LLMs: A Survey

Paper • 2509.02547 • Published Sep 2, 2025 • 238
Efficient Multi-modal Large Language Models via Progressive Consistency Distillation

Paper • 2510.00515 • Published Oct 1, 2025 • 41
DeepSearch: Overcome the Bottleneck of Reinforcement Learning with Verifiable Rewards via Monte Carlo Tree Search

Paper • 2509.25454 • Published Sep 29, 2025 • 147

Beyond Language Modeling: An Exploration of Multimodal Pretraining

Paper • 2603.03276 • Published Mar 3 • 108
Qwen3-Coder-Next Technical Report

Paper • 2603.00729 • Published Feb 28 • 66
Learning When to Act or Refuse: Guarding Agentic Reasoning Models for Safe Multi-Step Tool Use

Paper • 2603.03205 • Published Mar 3 • 13
AgentVista: Evaluating Multimodal Agents in Ultra-Challenging Realistic Visual Scenarios

Paper • 2602.23166 • Published Feb 26 • 46

MMGR: Multi-Modal Generative Reasoning

Paper • 2512.14691 • Published Dec 16, 2025 • 121
KlingAvatar 2.0 Technical Report

Paper • 2512.13313 • Published Dec 15, 2025 • 44
SemanticGen: Video Generation in Semantic Space

Paper • 2512.20619 • Published Dec 23, 2025 • 95
DataFlow: An LLM-Driven Framework for Unified Data Preparation and Workflow Automation in the Era of Data-Centric AI

Paper • 2512.16676 • Published Dec 18, 2025 • 226

QeRL: Beyond Efficiency -- Quantization-enhanced Reinforcement Learning for LLMs

Paper • 2510.11696 • Published Oct 13, 2025 • 183
Does Your Reasoning Model Implicitly Know When to Stop Thinking?

Paper • 2602.08354 • Published Feb 9 • 138
Learning When to Act or Refuse: Guarding Agentic Reasoning Models for Safe Multi-Step Tool Use

Paper • 2603.03205 • Published Mar 3 • 13
π-StepNFT: Wider Space Needs Finer Steps in Online RL for Flow-based VLAs

Paper • 2603.02083 • Published Mar 2 • 9

Agent Safety and Prompt Injection Guardrails

Curated papers, models, datasets, and demos for AI-agent runtime safety, prompt injection, MCP security, and tool-call guardrails.

MCP Safety Audit: LLMs with the Model Context Protocol Allow Major Security Exploits

Paper • 2504.03767 • Published Apr 2, 2025 • 3
Prompt Injection Attacks on Agentic Coding Assistants: A Systematic Analysis of Vulnerabilities in Skills, Tools, and Protocol Ecosystems

Paper • 2601.17548 • Published Jan 24 • 1
ToolSafe: Enhancing Tool Invocation Safety of LLM-based agents via Proactive Step-level Guardrail and Feedback

Paper • 2601.10156 • Published Jan 15 • 26
Learning When to Act or Refuse: Guarding Agentic Reasoning Models for Safe Multi-Step Tool Use

Paper • 2603.03205 • Published Mar 3 • 13

Beyond Language Modeling: An Exploration of Multimodal Pretraining

Paper • 2603.03276 • Published Mar 3 • 108
Qwen3-Coder-Next Technical Report

Paper • 2603.00729 • Published Feb 28 • 66
Learning When to Act or Refuse: Guarding Agentic Reasoning Models for Safe Multi-Step Tool Use

Paper • 2603.03205 • Published Mar 3 • 13
AgentVista: Evaluating Multimodal Agents in Ultra-Challenging Realistic Visual Scenarios

Paper • 2602.23166 • Published Feb 26 • 46

Endless Terminals: Scaling RL Environments for Terminal Agents

Paper • 2601.16443 • Published Jan 23 • 20
Linear representations in language models can change dramatically over a conversation

Paper • 2601.20834 • Published Jan 28 • 21
Scaling Embeddings Outperforms Scaling Experts in Language Models

Paper • 2601.21204 • Published Jan 29 • 107
Teaching Models to Teach Themselves: Reasoning at the Edge of Learnability

Paper • 2601.18778 • Published Jan 26 • 44

MMGR: Multi-Modal Generative Reasoning

Paper • 2512.14691 • Published Dec 16, 2025 • 121
KlingAvatar 2.0 Technical Report

Paper • 2512.13313 • Published Dec 15, 2025 • 44
SemanticGen: Video Generation in Semantic Space

Paper • 2512.20619 • Published Dec 23, 2025 • 95
DataFlow: An LLM-Driven Framework for Unified Data Preparation and Workflow Automation in the Era of Data-Centric AI

Paper • 2512.16676 • Published Dec 18, 2025 • 226

Multi-Agent Infrastructure

Latent Collaboration in Multi-Agent Systems

Paper • 2511.20639 • Published Nov 25, 2025 • 131
Learning When to Act or Refuse: Guarding Agentic Reasoning Models for Safe Multi-Step Tool Use

Paper • 2603.03205 • Published Mar 3 • 13
Hyperagents

Paper • 2603.19461 • Published Mar 19 • 51
Code-as-Room: Generating 3D Rooms from Top-Down View Images via Agentic Code Synthesis

Paper • 2605.18451 • Published May 18 • 40

QeRL: Beyond Efficiency -- Quantization-enhanced Reinforcement Learning for LLMs

Paper • 2510.11696 • Published Oct 13, 2025 • 183
Does Your Reasoning Model Implicitly Know When to Stop Thinking?

Paper • 2602.08354 • Published Feb 9 • 138
Learning When to Act or Refuse: Guarding Agentic Reasoning Models for Safe Multi-Step Tool Use

Paper • 2603.03205 • Published Mar 3 • 13
π-StepNFT: Wider Space Needs Finer Steps in Online RL for Flow-based VLAs

Paper • 2603.02083 • Published Mar 2 • 9

Large Language Models

Universal Deep Research: Bring Your Own Model and Strategy

Paper • 2509.00244 • Published Aug 29, 2025 • 14
The Landscape of Agentic Reinforcement Learning for LLMs: A Survey

Paper • 2509.02547 • Published Sep 2, 2025 • 238
Efficient Multi-modal Large Language Models via Progressive Consistency Distillation

Paper • 2510.00515 • Published Oct 1, 2025 • 41
DeepSearch: Overcome the Bottleneck of Reinforcement Learning with Verifiable Rewards via Monte Carlo Tree Search

Paper • 2509.25454 • Published Sep 29, 2025 • 147

Company

TOS Privacy About Careers

Website

Models Datasets Spaces Pricing Docs