Agentic RL: Credit Assignment and CLI Agents
https://hoyant-su-agentic-rl.hf.space/gradio_api/mcp/ ↗
Description
Filter agent RL methods by supervision, critic and task setting; retrieve source links and BibTeX.
What our measurements say
Agentic RL: Credit Assignment and CLI Agents is a remote MCP server published at hoyant-su-agentic-rl.hf.space. It has been probed 18 times since 9/12/2026. It answered in 18 of them (100.0%), a near-uninterrupted record. Median response time is 493 ms, placing it among the faster endpoints. It offers a narrow, focused set of 8 tools. On the protocol side it still runs 2025-11-25 and has not moved to the newer spec.
Agent readability score
Can an LLM agent pick the right tool here — names, descriptions and parameter clarity are assessed.
Agent readability score
Agent readability score
Sign up free to generateEvent narrative
Sign up free to generateRaw observations
| Run | Era | Modern | ms | Legacy | ms | Versions |
|---|---|---|---|---|---|---|
| 2026-09-14 02:22:47 | Legacy | 400 | 586 | 200 | 594 | 2025-11-25 |
| 2026-09-14 00:19:26 | Legacy | 400 | 801 | 200 | 797 | 2025-11-25 |
| 2026-09-13 22:17:36 | Legacy | 400 | 564 | 200 | 567 | 2025-11-25 |
| 2026-09-13 21:01:02 | Legacy | 400 | 494 | 200 | 493 | 2025-11-25 |
| 2026-09-13 18:57:30 | Legacy | 400 | 294 | 200 | 353 | 2025-11-25 |
| 2026-09-13 16:52:42 | Legacy | 400 | 341 | 200 | 343 | 2025-11-25 |
| 2026-09-13 14:49:35 | Legacy | 400 | 377 | 200 | 388 | 2025-11-25 |
| 2026-09-13 12:47:19 | Legacy | 400 | 433 | 200 | 438 | 2025-11-25 |
| 2026-09-13 10:45:14 | Legacy | 400 | 807 | 200 | 807 | 2025-11-25 |
| 2026-09-13 08:43:04 | Legacy | 400 | 552 | 200 | 552 | 2025-11-25 |
Schema compliance
tools/list structure, inputSchema validity, and a functional smoke test — the components of the 0-100 score.
- tools/list schema valid
- inputSchema is valid JSON Schema
- Smoke test not run this round
- Cold-start: cold 200ms → warm 197ms (penalty 3ms)
Tools
Tools the server advertised in the latest measurement — measured, not catalog-claimed.
Agentic_RL_list_sourcesList original papers and retrieval coverage. Discover source-linked comparisons of credit assignment, agent memory, selective observation and terminal benchmarks, with JSON, CSV and BibTeX links.
Agentic_RL_search_evidenceSearch original papers on agentic reinforcement learning, credit assignment and CLI agents. Use English keywords (AND), OR and quoted phrases. Return relevant passages, source citations, equations and table cells.
querystringrequiredlimitinteger
Agentic_RL_fetch_evidenceFetch a complete original evidence block by the evidence_id returned from search_evidence, including section anchor, version, equations, table cells, links, and attribution.
evidence_idstringrequired
Agentic_RL_dataset_overviewInspect ShellOps and ShellOps-Pro task counts, train/test splits, task types, published schemas, source files, license and citation.
Agentic_RL_search_tasksFind real ShellOps CLI benchmark tasks by case-insensitive literal substring in the complete instruction, task ID or published task type. Empty query lists all tasks. Select partition 'all', 'shellops' or 'shellops_pro'; select published split 'all', 'train_src', 'train' or 'test'. Results are ordered by partition then task ID, with explicit pagination and no relevance scoring. The train subset is not double-counted.
querystringrequiredpartitionstringsplitstringlimitintegeroffsetinteger
Agentic_RL_get_taskInspect one published ShellOps or ShellOps-Pro task by its exact task_id and partition ('shellops' or 'shellops_pro'). Returns the complete instruction, actual reward specification, published reference answer/command, file-entry metadata, pinned parquet rows and workspace asset links. File content is available at the source links. No shell execution or solution verification is performed.
task_idstringrequiredpartitionstringrequired
Agentic_RL_list_method_facetsList exact filter values for agent RL credit granularity, supervision, value critics and evaluation settings. Each value reports its source-supported method count.
Agentic_RL_filter_methodsFilter agent RL credit-assignment methods by research conditions and return original section evidence and BibTeX. Discover accepted values with list_method_facets. Filters combine with AND; empty strings leave a facet unrestricted. Unknown critic status never matches no. Results use publication order without a relevance or quality ranking.
credit_granularitystringrequired_supervisionstringlearned_value_criticstringevaluation_settingstring
Availability history
Each block is one measurement round. Green: working response. Amber: responded but the server was returning errors (5xx). Red: no response at all.
Era history
Each cell is one probe run. Faded cells are incomplete probes — one leg did not answer, so the era is inconclusive.
Response time history
The two probe legs separately: modern server/discover and legacy initialize.
Event log
Derived by comparing consecutive probes — changes in era, protocol version, build and reachability.
- Added to watch — era: Legacy
Get your badge
Add this badge to your README — it updates automatically as measurements change.
[](https://mcpmetrics.io/servers/space-hf-hoyant-su-agentic-rl-agentic-rl)<a href="https://mcpmetrics.io/servers/space-hf-hoyant-su-agentic-rl-agentic-rl"><img src="https://mcpmetrics.io/badge/space.hf.hoyant-su-agentic-rl/agentic-rl/era.svg" alt="mcpmetrics"></a>You are seeing the last 7 days. Sign up for the full history. Which check failed and why is in the dashboard.
Sign up free to seeSimilar MCP servers
The catalog entries whose name and description are closest to this one, found with the same index the search box uses.
- Execute agentic-credit-line-issuer-mcpapi.m2mcent.com
Premium agentic endpoint for agentic-credit-line-issuer-mcp.
- agentic-uxwww.agentic-ux.com
# Agentic UX MCP **Agentic UX MCP** gives coding agents a machine-readable reference for designing interfaces where AI delegates work and users stay in control. It ships **11 lifecycle patterns** — from intent preview and autonomy dials to progress ledgers and return moments — each with anatomy, do/avoid guidance, limitations, and production examples. Patterns are available as **MCP resources** (`agentic-ux://patterns/{slug}` and `agentic-ux://library/full`) so agents can attach specs directly to context. For reviews, **`review_agent_flow`** returns a structured audit kit: lifecycle rubric, empty report schema, and prioritized pattern recommendations for a specific agent flow. **Prompts** provide guided entry points for audits and spec-first implementation. **Best for:** designers and builders shipping long-running agents in Cursor, Replit, research tools, and support automation — anywhere users delegate work and need visibility, consent, and recovery. **No configuration required.
- Execute darknet-address-filter-mcpapi.m2mcent.com
Premium agentic endpoint for darknet-address-filter-mcp.
- Execute decentralized-credit-bureau-mcpapi.m2mcent.com
Premium agentic endpoint for decentralized-credit-bureau-mcp.
- Execute credit-risk-mcpapi.m2mcent.com
Premium agentic endpoint for credit-risk-mcp.
- Execute dan-jailbreak-filter-mcpapi.m2mcent.com
Premium agentic endpoint for dan-jailbreak-filter-mcp.
Comments
Sign in to write a comment
No comments yet. Be the first.