arXiv
An Empirical Study of Harness Design for Coding Agents
Coding harnesses shape how autonomous coding agents translate model capabilities into long-horizon software-engineeri...
🤖 AI 前沿资讯
每天自动聚合 AI 领域最新动态
arXiv
Quantifying Overclaiming Propensity in Frontier LLM Agents
Frontier coding agents are increasingly trusted to work autonomously for long periods, yet an agent's final response ...
arXiv
ERCPMP-Gx: Endoscopic Image and Video Dataset for Morphological, Histopathological, and Genomic Characterization of Colorectal Polyposis
Hereditary polyposis syndromes can be precursor lesions to colorectal cancer and are associated with a broad spectrum...
arXiv
Paint-Anything: Unified Any-Color Control for Image Generation and Editing
Professional design requires any-color control: the ability to specify an object's target color with any 24-bit hex v...
arXiv
FAMOS: Feed-Forward 3D Articulation Modeling from Sparse Observations
Modeling articulated objects from sparse monocular views is challenging because each observation reveals only partial...
arXiv
Workspace Models: Lightweight Robotic Memory via Saliency-Driven Supervision
Complex robotic manipulation tasks frequently require a long-term memory of past events and actions. As conditioning ...
arXiv
Coding Agents with an Obstacle-Aware Harness for Safe Robot Manipulation
Coding agents have emerged as a promising paradigm for robot manipulation: a language model writes the robot controll...
HuggingFace
An Empirical Study of Harness Design for Coding Agents
Coding harnesses shape how autonomous coding agents translate model capabilities into long-horizon software-engineeri...
HuggingFace
SoL-Pi: Recursively Scaling Auto-Research Loops for Efficient Agent Harness
As coding agents move from supervised code completion to unattended, around-the-clock exploration, their work expands...
HuggingFace
Region-Level Policy Optimization for Fine-grained MLLM Perception
Fine-grained visual perception in MLLMs is commonly improved by raising the resolution, but the added visual tokens i...
HuggingFace
VABench: Measuring Embodied Spatial Intelligence through Visual Demonstrations, Active Perception, and Metric Control
Spatial intelligence requires more than describing object locations. Under incomplete observation, models must identi...
HuggingFace
RiskChainBench: A Benchmark for Obfuscated Platform Message Restoration and Evidence-Grounded Web Investigation
Platform abuse campaigns conceal redirection instructions with emojis, homophones, character decomposition, and redun...