Skip to content

Agentic RL: Credit Assignment and CLI Agents

by hoyant-su-agentic-rl.hf.space · remote · no sign-in to list tools · v1.1.0 · published by space.hf.hoyant-su-agentic-rl

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

Changes · 1
CompareRegistry entry

8 tools: 1 change things and 7 only read.

Scanned Oct 21, 2026

No check matched anything in the tool definitions. No finding is not a safety guarantee. How the checks work.

claude mcp add --transport http agentic-rl https://hoyant-su-agentic-rl.hf.space/gradio_api/mcp/

Tools

Open a tool for its reasons and full description. Descriptions are the publisher's own words, shown as they are.

8 tools

Changes things 1Claude Code: ask
  • Agentic_RL_filter_methodsFilter agent RL credit-assignment methods by research conditions and return original section evidence and BibTeX.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    Description, as the server wrote it
    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 order without a relevance or quality ranking.
Only reads 7Claude Code: allow
  • Agentic_RL_dataset_overviewInspect ShellOps and ShellOps-Pro task counts, train/test splits, task types, published schemas, source files, license and citation.No findings

    Why it is in this group

    • The description's first verb is "inspect": a word for reading.
    Description, as the server wrote it
    Inspect ShellOps and ShellOps-Pro task counts, train/test splits, task types, published schemas, source files, license and citation.
  • 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.No findings

    Why it is in this group

    • The name "Agentic_RL_fetch_evidence" says "fetch": a word for reading.
    Description, as the server wrote it
    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_get_taskInspect one published ShellOps or ShellOps-Pro task by its exact task_id and partition ('shellops' or 'shellops_pro').No findings

    Why it is in this group

    • The name "Agentic_RL_get_task" says "get": a word for reading.
    Description, as the server wrote it
    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 is available at the source links. No shell execution or solution verification is performed.
  • Agentic_RL_list_method_facetsList exact filter values for agent RL credit granularity, supervision, value critics and evaluation settings.No findings

    Why it is in this group

    • The name "Agentic_RL_list_method_facets" says "list": a word for reading.
    Description, as the server wrote it
    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_list_sourcesList original papers and retrieval coverage.No findings

    Why it is in this group

    • The name "Agentic_RL_list_sources" says "list": a word for reading.
    Description, as the server wrote it
    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_evidenceSearch original papers on agentic reinforcement learning, credit assignment and CLI agents.No findings

    Why it is in this group

    • The name "Agentic_RL_search_evidence" says "search": a word for reading.
    Description, as the server wrote it
    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_search_tasksFind real ShellOps CLI benchmark tasks by case-insensitive literal substring in the complete instruction, task ID or published task type.No findings

    Why it is in this group

    • The name "Agentic_RL_search_tasks" says "search": a word for reading.
    Description, as the server wrote it
    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 ordered by partition then task ID, with explicit pagination and no relevance scoring. The train subset is not double-counted.

This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.

Install

Pinned to version 1.1.0. Values in angle brackets are yours to fill in.

claude mcp add --transport http agentic-rl https://hoyant-su-agentic-rl.hf.space/gradio_api/mcp/

Run in a terminal.

Claude Code permissions

Allow the reads, ask before a change, deny the deletes. Paste into .claude/settings.json.

.claude/settings.json
{
  "permissions": {
    "allow": [
      "mcp__agentic-rl__Agentic_RL_list_sources",
      "mcp__agentic-rl__Agentic_RL_search_evidence",
      "mcp__agentic-rl__Agentic_RL_fetch_evidence",
      "mcp__agentic-rl__Agentic_RL_dataset_overview",
      "mcp__agentic-rl__Agentic_RL_search_tasks",
      "mcp__agentic-rl__Agentic_RL_get_task",
      "mcp__agentic-rl__Agentic_RL_list_method_facets"
    ],
    "ask": [
      "mcp__agentic-rl__Agentic_RL_filter_methods"
    ],
    "deny": []
  }
}

Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. It assumes the server is installed as agentic-rl. Review it before you use it.