The Last Mile to the Real World: Agent-Native Primitives as Reusable Building Blocks for Solving Real-World Tasks Paper • 2611.07461 • Published 16 days ago • 31
The Last Mile to the Real World: Agent-Native Primitives as Reusable Building Blocks for Solving Real-World Tasks Paper • 2611.07461 • Published 16 days ago • 31
Harness Engineering in LLM Tool Use via Agent-Native Reusable Tool Primitives Paper • 2609.01736 • Published Sep 1
Harness Engineering for Software Engineering via Modular Executable Dev-Primitives Paper • 2610.07832 • Published Oct 6 • 9
TextReg: Mitigating Prompt Distributional Overfitting via Regularized Text-Space Optimization Paper • 2605.21318 • Published Oct 5 • 7
From Knowledge Access to Source Learning: Developing Source-Specific Competence Paper • 2610.02150 • Published Oct 1 • 9
The Last Mile to the Real World: Agent-Native Primitives as Reusable Building Blocks for Solving Real-World Tasks Paper • 2611.07461 • Published 16 days ago • 31
Harness Engineering for Software Engineering via Modular Executable Dev-Primitives Paper • 2610.07832 • Published Oct 6 • 9
Harness Engineering for Software Engineering via Modular Executable Dev-Primitives Paper • 2610.07832 • Published Oct 6 • 9
Breaking Babel: A Self-Evolving Multi-Agent System for Long-Form Subtitle Translation Paper • 2609.38660 • Published Sep 29 • 22
Breaking Babel: A Self-Evolving Multi-Agent System for Long-Form Subtitle Translation Paper • 2609.38660 • Published Sep 29 • 22
Breaking Babel: A Self-Evolving Multi-Agent System for Long-Form Subtitle Translation Paper • 2609.38660 • Published Sep 29 • 22
ANTMAN: Adaptive Need Tracking for Multi-Agent Navigation in Large Information Spaces Paper • 2609.33326 • Published Sep 27 • 18
Learning to Communicate: Toward End-to-End Optimization of Multi-Agent Language Systems Paper • 2604.21794 • Published Apr 23
Agent Primitives: Reusable Latent Building Blocks for Multi-Agent Systems Paper • 2602.03695 • Published Feb 3 • 3
Break Me If You Can: Self-Jailbreaking of Aligned LLMs via Lexical Insertion Prompting Paper • 2601.02670 • Published Apr 8
Crafting Adversarial Inputs for Large Vision-Language Models Using Black-Box Optimization Paper • 2601.01747 • Published Jan 5
GUARD: Role-playing to Generate Natural-language Jailbreakings to Test Guideline Adherence of Large Language Models Paper • 2402.03299 • Published Feb 5, 2024 • 1