space.hf.hoyant-su-agentic-rl/agentic-rl
Agentic RL: Credit Assignment and CLI Agents
space.hf.hoyant-su-agentic-rl/agentic-rl costs 754 tokens of context per session. It has 8 tool definitions. That is 0.4 % of a 200k window. Measured 2026-10-03.
Filter agent RL methods by supervision, critic and task setting; retrieve source links and BibTeX.
alive probed 2026-10-03 · HTTP 200
8tools
754tokens for the tool definitions
0.4 %of a 200k context window
1.4 sto initialize
90 msto list tools
- Endpoint
- https://hoyant-su-agentic-rl.hf.space/gradio_api/mcp/ (streamable-http)
- Host
- hoyant-su-agentic-rl.hf.space
- Protocol
- 2025-11-25
- Reports itself as
- Gradio 1.30.0
- Capabilities
- experimental, prompts, resources, tools
- Instructions
- none
- Website
- https://huggingface.co/spaces/Hoyant-Su/Agentic-RL
- Registry
- active, updated 2026-09-08 · registry entry
- Reachable
- 2 of the last 2 probes
Most expensive tools
| Tool | Tokens | Share of this server |
|---|---|---|
| Agentic_RL_search_tasks | 174 | 23 % |
| Agentic_RL_filter_methods | 131 | 17 % |
| Agentic_RL_get_task | 123 | 16 % |
| Agentic_RL_search_evidence | 88 | 12 % |
| Agentic_RL_fetch_evidence | 74 | 10 % |
History
We add a row when the result changes. A server with no change keeps its last row.
| Probed | Result | Init | Tools | Tokens |
|---|---|---|---|---|
| 2026-10-03 20:43 | alive | 1.4 s | 8 | 754 |
| 2026-10-03 17:57 | alive | 1.9 s | 8 | 754 |
Badge
[](https://mcp-pulse.ulehla.dev/s/space.hf.hoyant-su-agentic-rl/agentic-rl)