|
| 1 | + |
| 2 | +# Compare AgentJet with Other Platforms with Agentic RL |
| 3 | + |
| 4 | + |
| 5 | +- Multi OSS Training Backbone: Support switching between multiple open-source training backbones quickly. |
| 6 | +- Multi OSS Infer Backbone: Support both vLLM and SGLang. |
| 7 | +- Low Code Change: Do not require too many edits to convert a user‑defined (multi) agent workflow into trainable workflows. |
| 8 | +- Without-GPU (Cloud-Computing): Rollout and power RL training in a laptop without GPU, using Tinker (AgentLightning) or without Tinker (AgentJet-TinkerScript, comming soon) |
| 9 | +- Timeline Optimization: Automatically merge shared-history context generated by the same agents to promote training speed. |
| 10 | +- Open Bench Platform: Trace baseline environment's performance across git history in different training backbones. |
| 11 | +- Multi-Agent Optimization: Deal with sophisticated multi-agent interaction efficiently, automatically clustering and merging samples generated by the same agents. |
| 12 | +- High-res Rollout Logging: Integrated with token level rollout trajectory, highlighting token logprob and loss mask for deep‑level research. |
| 13 | +- Agentic Framework Compatible: Easy to convert AgentScope and Langchain workflows into trainable workflows. |
| 14 | + |
| 15 | + |
| 16 | +| Feature | AgentJet (Beta) | AgentLightning | rLLM | VeRL 0.7.0 | |
| 17 | +|--------- |--------- |---------------- |------|------------ | |
| 18 | +| Multi OSS Training Backbone | ✅ | ❌ | ❌ | ➖ | |
| 19 | +| Multi OSS Infer Backbone | ✅ | ✅ | ✅ | ✅ | |
| 20 | +| Low Code Change | ✅ | ✅ | ✅ | ➖ | |
| 21 | +| Without-GPU (Cloud-Computing) | (Testing) | ✅ | ❌ | ➖ | |
| 22 | +| Timeline Optimization | ✅ | ❌ | ❌ | ➖ | |
| 23 | +| Open Bench Platform | ✅ | ❌ | ❌ | ✅ | |
| 24 | +| Multiagent Optimization | ✅ | ❌ | ❌ | ✅ | |
| 25 | +| High-res Rollout Logging | ✅ | ❌ | ❌ | ❌ | |
| 26 | +| AgentScope Compatible | ✅ | ✅ | ✅ | ➖ | |
| 27 | +| Langchain Compatible | ✅ | ✅ | ✅ | ➖ | |
| 28 | + |
| 29 | + |
| 30 | +!!! Note "" |
| 31 | + - ✅ = "supported"; ❌ = "not supported"; ➖ = "not applicable" or "not investigated" |
| 32 | + - All projects are quickly evolving. We expect features not supported today will catch up sooner or later. |
0 commit comments