Agentic RL: Credit Assignment and CLI Agents

space.hf.hoyant-su-agentic-rlPublished by hoyant-su-agentic-rl.hf.spaceOfficial publisherv1.1.0Updated Oct 24, 2026

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

The publisher's own server: agentic.no

VerifiedStreamable HTTPWeb executableKnowledge & MemoryAI & ML

Overview

AI-generated overview

Lets an assistant filter agentic reinforcement-learning methods by supervision, critic and task setting, and retrieve source links and BibTeX.

What you can do
This remote MCP server exposes a catalogue of agentic reinforcement-learning methods. An assistant can filter entries by attributes such as supervision type, critic usage and task setting, then retrieve the associated source links and BibTeX citations. It is a reference and lookup service rather than a training or execution tool.
When to use it
Useful when writing or reviewing research on agent RL and you need to compare methods or pull citations quickly. It suits literature and survey work rather than running experiments.
Requirements
A remote streamable HTTP endpoint; no package installation, account, API key or environment variable is declared. Network access to the hosted endpoint is required.
Before you install
No credentials are requested and no write actions are described. The catalogue content comes from a third-party hosted service, so verify citations and links against the original sources before relying on them.

Installation

In SourceWeft

  1. Open Agentic RL: Credit Assignment and CLI Agents in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Use with an agent

Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.

Read https://sourceweft.com/mcp/space.hf.hoyant-su-agentic-rl%2Fagentic-rl/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.

Read the install guide the agent follows

Other MCP clients

Add this to your client's mcpServers config.

{
  "mcpServers": {
    "agentic-rl-credit-assignment-and-cli-age": {
      "type": "http",
      "url": "https://hoyant-su-agentic-rl.hf.space/gradio_api/mcp/"
    }
  }
}

Tools

8

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.

Takes no parameters.

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.

Parameterslimitqueryrequired

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.

Parametersevidence_idrequired

Agentic_RL_dataset_overview

Inspect ShellOps and ShellOps-Pro task counts, train/test splits, task types, published schemas, source files, license and citation.

Takes no parameters.

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 ordered by partition then task ID, with explicit pagination and no relevance scoring. The train subset is not double-counted.

Parameterslimitqueryrequiredsplitoffsetpartition

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 is available at the source links. No shell execution or solution verification is performed.

Parameterstask_idrequiredpartitionrequired

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.

Takes no parameters.

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 order without a relevance or quality ranking.

Parameterscredit_granularityevaluation_settinglearned_value_criticrequired_supervision

Version history

1
  1. v1.1.0LatestSep 16, 2026

Score

72% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 daysRequired25 pts
  • Auth declaredRequired10 pts
  • Tools listedRequired15 pts
  • DescriptionRequired15 pts
  • Logo10 pts

    Publish an icon in the registry entry.

  • Documentation15 pts

    Declare a GitHub repository with a README, or serve resource_documentation in the OAuth protected-resource metadata.

  • LicenseNot applicable

    A hosted service is used under its provider's terms, so no license is expected here. This check is left out of the percentage.

Other Agentic integrations

agentic.no

no.agenticOfficial publisher

A remote MCP endpoint that helps an assistant find GPU sellers for AI inference by model, ordered cheapest first, with per-call payment via x402.

Streamable HTTPWeb executable
AI & MLNot indexed yetOct 24, 2026

Agentic Engineering Periodic System

academy.aseOfficial publisher

Agentic Engineering Periodic System's hosted MCP server, published by ase.academy; no sign-in required; Streamable HTTP; 4 tools.

Streamable HTTPWeb executable
Developer Tools4 toolsOct 24, 2026

Agentic Video

Published by GitHub account tlq5l

Local stdio MCP server that lets a text-and-image assistant inspect video files: contact sheets, transcripts, cuts, loudness and sync checks.

STDIODesktop only
Data & Analytics25 toolsNov 1, 2026

Agentic Os

Published by GitHub account kinnister

Read-only MCP server that exposes the agentic-os governance, SDLC and quality-engineering methodology to an assistant, without executing anything.

STDIODesktop only
Developer ToolsNot validated yetOct 29, 2026

Agentic-Ops Control Plane

Published by GitHub account nolll77

Governed SRE and MLOps control plane that lets an assistant query a failure-mode taxonomy, scenario blueprints and read-only production telemetry.

Streamable HTTPWeb executableAuth
Cloud & InfrastructureCredential requiredNov 7, 2026