-
rStar2-Agent: Agentic Reasoning Technical Report
Paper • 2508.20722 • Published • 120 -
AgentFly: Fine-tuning LLM Agents without Fine-tuning LLMs
Paper • 2508.16153 • Published • 162 -
Beyond Pass@1: Self-Play with Variational Problem Synthesis Sustains RLVR
Paper • 2508.14029 • Published • 119 -
InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency
Paper • 2508.18265 • Published • 225
peterlee6706
peterlee6706
·
AI & ML interests
None yet
Organizations
None yet
WeekDaily
-
rStar2-Agent: Agentic Reasoning Technical Report
Paper • 2508.20722 • Published • 120 -
AgentFly: Fine-tuning LLM Agents without Fine-tuning LLMs
Paper • 2508.16153 • Published • 162 -
Beyond Pass@1: Self-Play with Variational Problem Synthesis Sustains RLVR
Paper • 2508.14029 • Published • 119 -
InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency
Paper • 2508.18265 • Published • 225