Categories › AI & Agents › Thinking, planning & prompt tools
Filter agent RL methods by supervision, critic and task setting; retrieve source links and BibTeX.
Remote server: your requests and data go to hoyant-su-agentic-rl.hf.space. Claude Code: claude mcp add --transport http agentic-rl-credit-assignment-and-cli-age https://hoyant-su-agentic-rl.hf.space/gradio_api/mcp/ · Claude app: Settings → Connectors → Add custom connector.
The tools this server listed when we connected to it, in its own words.
Agentic_RL_list_sources — List original papers and retrieval coverage. Discover source-linked comparisons of credit assignment, agent memory, selective observation anAgentic_RL_search_evidence — Search original papers on agentic reinforcement learning, credit assignment and CLI agents. Use English keywords (AND), OR and quoted phraseAgentic_RL_fetch_evidence — Fetch a complete original evidence block by the evidence_id returned from search_evidence, including section anchor, version, equations, tabAgentic_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. EmAgentic_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 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-Agentic_RL_filter_methods — Filter agent RL credit-assignment methods by research conditions and return original section evidence and BibTeX. Discover accepted values wNot tested by KitScout yet. When our harness runs it, pros, cons and the tasks we tried appear here, with the date and evidence.