arxiv:2605.24202
Yaolun Zhang
Mercury7353
AI & ML interests
Code LLM, LLM Agent, Multi-Agent System
Recent Activity
authored a paper about 6 hours ago
When Does Multi-Agent RL Improve LLM Workflows? Workflow, Scale, and Policy-Sharing Tradeoffs upvoted a paper about 14 hours ago
When Does Multi-Agent RL Improve LLM Workflows? Workflow, Scale, and Policy-Sharing Tradeoffs upvoted a paper about 17 hours ago
Speculative Pipeline Decoding: Higher-Accruacy and Zero-Bubble Speculation via Pipeline ParallelismOrganizations
models 9
Mercury7353/MetaAgent-X
Reinforcement Learning • 8B • Updated • 61 • 4
Mercury7353/masrl_coldstart_4b
4B • Updated • 1 • 1
Mercury7353/masrl_0228_mix_coldstart
8B • Updated • 58
Mercury7353/masrl_coldstart_0228_mix_codemath
Updated
Mercury7353/masrl0206_notool
8B • Updated • 26
Mercury7353/masrlnothink0128
8B • Updated • 1
Mercury7353/masrl-1227
8B • Updated • 1
Mercury7353/mas_rl_coldstart_1220
8B • Updated • 1
Mercury7353/PyLlama3
Text Generation • Updated • 9 • 5