arXiv
PAIChecker: Uncovering and Checking PR-Issue Misalignment in SWE-Bench-Like Benchmarks
SWE-bench-like benchmarks are widely used for evaluating LLM's issue resolution capability. They typically follow a c...
🤖 AI 前沿资讯
每天自动聚合 AI 领域最新动态
arXiv
OSReward: Instituting Standardized Evaluation for Cross-Platform Computer-Use Reward Models
Computer-using agents (CUAs) are advancing rapidly across the digital world. A CUA trajectory records the agent's act...
arXiv
AISPA: User-Centric System Prompt Auditing for Large Language Model Applications
System prompts are instructions configured by developers to govern the behaviors of foundation models in AI applicati...
arXiv
AskChem: Claim-Centered Infrastructure for Chemistry Literature Synthesis
Chemistry literature synthesis often requires assembling specific findings scattered across many publications, yet ex...
arXiv
PAC-MAN: Perception-Aware CBF-RL for Whole-Body Safety in Humanoid Dodgeball
We present PAC-MAN, a perception-aware CBF-RL framework that couples control-barrier safety with deployment-realistic...
arXiv
ReToken: One Token to Improve Vision-Language Models for Visual Retrieval
Long visual context poses a challenge for vision-language models: performance degrades as the number of distractors g...
arXiv
Learning to Trace Seiberg Dualities
Dualities play an important role in establishing both microscopic and emergent phenomena in a wide range of physical ...
HuggingFace
Beacon: Knowing When and How to Perform Agentic Visual Reasoning
The fundamental goal of agentic visual reasoning is to improve the success rate of multimodal large language models (...
HuggingFace
RefCaptioner: Multi-Reference Image-Grounded Video Captioning
Existing video captioning models generate natural descriptions of video content but cannot explicitly ground local vi...
HuggingFace
Qwen-UI-Agent Technical Report: Toward Next-Generation Real-World Centric Foundation GUI Agents
GUI agents have the potential to become a general purpose executor over existing digital devices. To advance them tow...
HuggingFace
Memory Decoder at Scale: A Pretrained, Parametric Long-Term Memory
Decoder-only language models entangle long-term memory and reasoning in a single parameter set, making it difficult t...
HuggingFace
Can Large Language Models Execute Parent Orders?
Parent-order execution is a core problem in algorithmic trading, where the goal is to split a large order into smalle...