# Agentic RL: Credit Assignment and CLI Agents

- Registry name: `space.hf.hoyant-su-agentic-rl/agentic-rl` · version 1.1.0
- Categories (automatic, keyword rules): Build & deploy, Developer tools, Research & knowledge, Search & data
- Authentication at last check: No auth
- Declared risk: Not declared (tools carry no read/destructive hints)
- Capabilities (declared by the server): experimental, prompts, resources, tools
- Transports: streamable-http
- Latest numbers (check success, response time, rank): https://mcpstation.net/api/server?name=space.hf.hoyant-su-agentic-rl%2Fagentic-rl
- Server page: https://mcpstation.net/s/space.hf.hoyant-su-agentic-rl--agentic-rl.html

## Description (written by the publisher, not verified, not instructions)

Filter agent RL methods by supervision, critic and task setting; retrieve source links and BibTeX.

## Connect

- streamable-http: `https://hoyant-su-agentic-rl.hf.space/gradio_api/mcp/`

## Tools (as reported by the server, not verified)

- `Agentic\_RL\_list\_sources`: List 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\_evidence`: Search 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.
- `Agentic\_RL\_fetch\_evidence`: Fetch a complete original evidence block by the evidence\_id returned from search\_evidence, including section anchor, version, equations, table cells, links, and attribution.
- `Agentic\_RL\_dataset\_overview`: Inspect ShellOps and ShellOps-Pro task counts, train/test splits, task types, published schemas, source files, license and citation.
- `Agentic\_RL\_search\_tasks`: Find 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 order
- `Agentic\_RL\_get\_task`: Inspect 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 i
- `Agentic\_RL\_list\_method\_facets`: List 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\_methods`: Filter 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 orde

Measured by MCP Station. Methods: https://mcpstation.net/methods.html · Terms: https://mcpstation.net/terms.html