AI
ASI-Bench: At the Dawn of Artificial Superintelligence
Researchers have introduced ASI-Bench, a new benchmark designed to evaluate the capabilities of artificial intelligence systems in exploring the unkno...
AI
AI
DeAR: Decentralized Agentic Reasoning via Capability Grounding and Collaborative Thought Navigation
A new AI framework called DeAR (Decentralized Agentic Reasoning) has been proposed to improve the accuracy of complex reasoning tasks. Unlike traditio...
AI
PlanPO: Group Planning-Aware Policy Optimization for Multi-Turn Agentic LLMs
Researchers have proposed a new method for training large language models (LLMs) called PlanPO. This approach aims to improve the performance of LLMs ...
AI
LiveHouse-TS: An Open-world Living Benchmark for Time Series Foundation Models
Researchers have introduced LiveHouse-TS, an open-world living benchmark for Time Series Foundation Models (TSFMs). Unlike traditional benchmarks that...
AI
SignalReasoner: Assessing the Upper Bound of 3B Models for Signal Mathematical Reasoning
Researchers have fine-tuned a large language model, called Qwen2.5-3B-Base, to improve its mathematical reasoning capabilities in signal processing pr...
AI
Wuying-Browser-Agent: Real-World Centric Fundamental Long-Horizon Browser Agents
Researchers from the AIMAE Team have introduced Wuying-Browser-Agent, a unified framework for building browser agents that can perform well in real-wo...
AI
LLMs for Medical Consultation Are Evaluated Too Late: The Preformulation Gap
Researchers evaluated three large language models for medical consultation and found that they often provide self-care advice before the patient's con...
AI
TileMix: Tile-Centric Mixed-Precision Attention for LLM Inference Acceleration
Researchers have developed TileMix, a method for accelerating large language model inference. It does this by allowing different levels of precision f...
AI
LLM-Only PDDL Domain Repair with Open-Weight Models
Researchers have evaluated the ability of large language models to automatically repair errors in planning domain definition languages (PDDL) using a ...
AI
Cognitive Graph Intelligence for Adaptive and Robust DDoS Attack Detection in Next Generation Networks
Researchers have proposed a system called GraphGAN to detect Distributed Denial-of-Service (DDoS) attacks in next-generation networks. The system uses...
AI
LEGO-RL: Harness-Native Reinforcement Learning for Coding Agents
Researchers have developed LEGO-RL, a framework that improves reinforcement learning for coding agents. Current methods rely on harnesses to manage to...
AI
Task-Aware Harness Provisioning for LLM Agents in Mission-Critical Infrastructure Operations
Researchers have developed a new method for optimizing the information and tools available to large language model (LLM) agents in mission-critical in...