Command Palette
Search for a command to run...
Papers
Daily updated cutting-edge AI research papers to help you keep up with the latest AI trends
3,251 papers

SCALING VERIFIABLE ENVIRONMENTS FOR LONG-HORIZON WORK AGENTS

Harness Scaling for Generalizable Agentic Reinforcement Learning

Automating ML for Science: Can Frontier Agents Climb Scientific Hills in the Wild?

AGENT WORLD MODEL IN THE WILD: COMPUTER-USE AGENT ENVIRONMENT SYNTHESIS

LOOKING AHEAD: MODELING FUTURE EVOLUTION IN AUTOREGRESSIVE VIDEO GENERATION

StreamEval: Evaluating Interactive Streaming Video Generation Models

CACHE ENGINEERING FOR AGENTS

Generalist Dexterous Bimanual Tracking Control from Human Demonstrations

SpatialScout: Can VLM Agents Actively Explore and Map 3D Scenes?

Épi: Towards a Persistent, Self-Improving Agent for Autonomous Research

Fish Audio Drama 3 Technical Report

Sage-A1.5: From Long-Horizon Execution to Scientific Exploration with Capability Composition

Spatial Reasoning with a General Coding Agent

Ropedia W0: Scaling Loco-Manipulation World Models across Embodiments with Human Experience

Focused Omni-Modal GUI Agents

PAR: Progress-Aligned Recurrence for Length Generalization in State Tracking

Matrix-Game 4.0: Harnessing Video Models for Real-Time Playable Game Worlds

SpecMRL: Redesign Matryoshka Representation Learning within Parametric Spectrum

EgoXperience: Learning World-Grounded Egocentric Representations from Human Experience

Holi-World: Building Holistic World Intelligence from Human-Ego Experience

Learning from Fleet Experience: A Collective Learning Paradigm for Robots

Scaling Parameter-Efficient Fine-Tuning for Brain Encoding

MemT-1.0: Towards Memory-Native Evolution

DiscoveryRSI: Recursively Learning to Discover Valuable Hypotheses

CAN VISUAL GENERATION EXPAND WHAT UNIFIED MULTIMODAL MODELS KNOW?

Into the Unknown: Benchmarking AI agents on open scientific research problems

PACK LIGHT, CARRYON: BUILDING OBJECT-ORIENTED CONTEXT FOR LONG-HORIZON AGENTS

HexaShell: A Thin Harness for Exploring the Limits of VLM Agents as Robot Coding Agents

LEARNING TO THINK AND EXPLORE IN 3D WORLD

BizAgentBench: Unveiling Hidden Challenges in Deploying Long-Horizon Agents for Real-World Business

Has GPT-6-Astra Achieved Embodied Intelligence?

TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents