From Model Scaling to System Scaling: Scaling the Harness in Agentic AI
Paper • 2605.26112 • Published • 7
CyberGym-Pro
non-profit
AI & ML interests
None defined yet.
Shangding-Gu
submitted a
paper to Daily Papers 5 months ago
Shangding-Gu
authored 8
papers 5 months ago
A Review of Safe Reinforcement Learning: Methods, Theory and Applications
Paper • 2205.10330 • Published
TeaMs-RL: Teaching LLMs to Generate Better Instruction Datasets via Reinforcement Learning
Paper • 2403.08694 • Published
Agentic Web: Weaving the Next Web with AI Agents
Paper • 2507.21206 • Published
AccidentBench: Benchmarking Multimodal Understanding and Reasoning in Vehicle Accidents and Beyond
Paper • 2509.26636 • Published • 1
AgenticPay: A Multi-Agent LLM Negotiation System for Buyer-Seller Transactions
Paper • 2602.06008 • Published • 5
Understanding Agent Scaling in LLM-Based Multi-Agent Systems via Diversity
Paper • 2602.03794 • Published
Long Context, Less Focus: A Scaling Gap in LLMs Revealed through Privacy and Personalization
Paper • 2602.15028 • Published • 1
LLMs Should Express Uncertainty Explicitly
Paper • 2604.05306 • Published • 1