单卡 24GB 上研究长链路多工具 Agent 的 RL 训练稳定性 —— 以及工具使用行为本身的退化。Qwen2.5-1.5B + LoRA / τ-bench airline / 四臂消融。RL training stability for long-horizon multi-tool agents on a single RTX 4090D.
Cross-referenced across 55 tracked directories
#3145
Popularity Rank
1 / 55
Listed In
Emerging
Adoption Stage
9/20/2026
Created
1
GitHub Stars
9/20/2026
Last Commit
Recently added to the ecosystem
Score: 100/100
0 dependency vulnerabilities found
bytedance
The Open-Source Multimodal AI Agent Stack: Connecting Cutting-Edge AI Models and Agent Infra
klim.paskov
One-time non-executable namespace claim for OIDC trusted-publisher setup.
ildargiv
Windows app for printing photos on Epson, Canon, HP, Brother and other inkjet printers: smart crop, ICC colour profiles, printer colour correction, borderless print, AI-agent/MCP mode
...more