arXiv
From Static to Dynamic: Benchmarking Real-World Code Review with MCR-Bench
In real-world software development, code review typically involves iterative interactions between developers and revi...
🤖 AI 前沿资讯
每天自动聚合 AI 领域最新动态
arXiv
SWE-Prime: Fewer Trajectories, Better Performance
To improve large language models' ability to resolve real-world software issues, prior work has focused on constructi...
arXiv
WikiSkill: Compiling Agent Experience into Persistent Knowledge for Skill Evolution
Agent skills package specialized knowledge and workflows into reusable resources that extend AI agent capabilities. R...
HuggingFace
What Makes Good Agentic Data? An ACE Lens on Data Generation for LLM Agents
LLM agents increasingly rely on generated interaction data to learn how to interact with external environments. Agent...
HuggingFace
Magpie: Real-Time World Renderer for Interactive Games
Modern game development relies heavily on conventional graphics pipelines. High-quality visual content requires model...
HuggingFace
Understanding Evolution Strategies for LLM Reasoning: Broader Reasoning Coverage than GRPO
Evolution Strategies (ES) have recently emerged as a memory-efficient post-training paradigm for LLM reasoning. Howev...
HuggingFace
Self-OPD: On-Policy Distillation for Flow Matching Models without Teacher
On-policy distillation (OPD), which leverages a pre-trained, specialized teacher model to provide dense supervisory s...
HuggingFace
WikiSkill: Compiling Agent Experience into Persistent Knowledge for Skill Evolution
Agent skills package specialized knowledge and workflows into reusable resources that extend AI agent capabilities. R...
HuggingFace
Zero-WAM: In-Context World-Action Modeling from Human Videos for Open-Ended Task Generalization
Zero-shot cross-task generalization, where a policy must execute manipulation tasks never seen during training, remai...
HuggingFace
UrbanGround: From Local Perception to Spatial Agency in a Real-Scale City
Multimodal large language models (MLLMs) can interpret a street view, but urban agency depends on whether such local ...
HuggingFace
PAWBench: How Far Are We from Probabilistically Aligned World Modeling?
Recent video generation models are increasingly framed as world models. Many physical processes can unfold in more th...
HuggingFace
CaRGo-T: Causal Reasoning Graph-of-Thought improves Multimodal Humor Comprehension
Large-scale vision-language models (VLMs) have demonstrated remarkable versatility across a wide range of multimodal ...