Agentic RL: Credit Assignment and CLI Agents
Filter agent RL methods by supervision, critic and task setting; retrieve source links and BibTeX.
我該用這個嗎
品質與安全性
發現項目（8）
- LOWTool 'Agentic_RL_list_sources' doesn't follow camelCase/snake_case在 Agentic_RL_list_sources 中
- LOWTool 'Agentic_RL_search_evidence' doesn't follow camelCase/snake_case在 Agentic_RL_search_evidence 中
- LOWTool 'Agentic_RL_fetch_evidence' doesn't follow camelCase/snake_case在 Agentic_RL_fetch_evidence 中
- LOWTool 'Agentic_RL_dataset_overview' doesn't follow camelCase/snake_case在 Agentic_RL_dataset_overview 中
- LOWTool 'Agentic_RL_search_tasks' doesn't follow camelCase/snake_case在 Agentic_RL_search_tasks 中
- LOWTool 'Agentic_RL_get_task' doesn't follow camelCase/snake_case在 Agentic_RL_get_task 中
- LOWTool 'Agentic_RL_list_method_facets' doesn't follow camelCase/snake_case在 Agentic_RL_list_method_facets 中
- LOWTool 'Agentic_RL_filter_methods' doesn't follow camelCase/snake_case在 Agentic_RL_filter_methods 中
根據工具定義與協定合規性的自動化分析。
上下文成本
這是每次將伺服器的工具載入模型上下文時所消耗的約略 token 數量。數量越高，可用於其他工作的注意力就越少。
安裝
一鍵安裝
將以下內容加入你的 `claude_desktop_config.json` 檔案：
{
"mcpServers": {
"agentic-rl": {
"url": "https://hoyant-su-agentic-rl.hf.space/gradio_api/mcp/"
}
}
}遠端端點
https://hoyant-su-agentic-rl.hf.space/gradio_api/mcp/streamable-http它能做什麼
工具清單
工具（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.
輸入結構描述
{
"type": "object",
"properties": {}
}🟢Agentic_RL_search_evidence(query, limit)
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.
輸入結構描述
{
"type": "object",
"properties": {
"query": {
"type": "string",
"description": ""
},
"limit": {
"type": "integer",
"description": "",
"default": 5
}
},
"required": [
"query"
]
}🟢Agentic_RL_fetch_evidence(evidence_id)
Fetch a complete original evidence block by the evidence_id returned from search_evidence, including section anchor, version, equations, table cells, links, and attribution.
輸入結構描述
{
"type": "object",
"properties": {
"evidence_id": {
"type": "string",
"description": ""
}
},
"required": [
"evidence_id"
]
}🟢Agentic_RL_dataset_overview
Inspect ShellOps and ShellOps-Pro task counts, train/test splits, task types, published schemas, source files, license and citation.
輸入結構描述
{
"type": "object",
"properties": {}
}🟢Agentic_RL_search_tasks(query, partition, split, limit, offset)
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.
輸入結構描述
{
"type": "object",
"properties": {
"query": {
"type": "string",
"description": ""
},
"partition": {
"type": "string",
"description": "",
"default": "all"
},
"split": {
"type": "string",
"description": "",
"default": "all"
},
"limit": {
"type": "integer",
"description": "",
"default": 10
},
"offset": {
"type": "integer",
"description": ""
}
},
"required": [
"query"
]
}🟢Agentic_RL_get_task(task_id, partition)
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.
輸入結構描述
{
"type": "object",
"properties": {
"task_id": {
"type": "string",
"description": ""
},
"partition": {
"type": "string",
"description": ""
}
},
"required": [
"task_id",
"partition"
]
}🟢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.
輸入結構描述
{
"type": "object",
"properties": {}
}🟢Agentic_RL_filter_methods(credit_granularity, required_supervision, learned_value_critic, evaluation_setting)
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.
輸入結構描述
{
"type": "object",
"properties": {
"credit_granularity": {
"type": "string",
"description": ""
},
"required_supervision": {
"type": "string",
"description": ""
},
"learned_value_critic": {
"type": "string",
"description": ""
},
"evaluation_setting": {
"type": "string",
"description": ""
}
}
}社群
證據