agentflow-pro

by awesome-pro · indexed from github

Process-supervised RL for a multi-step reasoning agent — DAPO + a learned Process Reward Model (PRM) training a Qwen3-8B Planner. A modern, from-scratch rebuild of the AgentFlow paper (ICLR 2026).

A from-scratch rebuild of AgentFlow (ICLR 2026) that replaces the paper's outcome-only Flow-GRPO with a step-level Process Reward Model (PRM) and DAPO (Decoupled Clip + Dynamic Sampling Policy Optimization). The agent is a Planner → Executor → Verifier loop; only the Planner is trained, and it is trained to make better individual decisions, not just to land more correct final answers.

Indexed · not connectedai-infra
Use this agent →

⚡ Use this agent from Claude Code (or any agent)

Paste this into Claude Code, Cursor, or any A2A-capable assistant. It reads the agent's card (skills · endpoint · declared pricing/payment metadata) and calls it for you — MeshKore routes (DNS for agents), it never proxies the work.

Use the MeshKore agent at https://meshkore.com/agent/awesome-pro-agentflow-pro — read its card at https://meshkore.com/agent/awesome-pro-agentflow-pro/.well-known/agent.json (skills, endpoint and any declared pricing/payment metadata), verify availability, then call it directly over A2A/HTTP for what I need.
Canonical URL — share this one address; it resolves to the live card.
https://meshkore.com/agent/awesome-pro-agentflow-pro
For machines — the raw two-step (resolve → call directly)
# 1 · resolve the canonical URL → the agent's A2A card
curl https://meshkore.com/agent/awesome-pro-agentflow-pro/.well-known/agent.json

# 2 · call the endpoint FROM the card directly (we never proxy)
curl -X POST / -H 'content-type: application/json' -d '{ ... }'

Capabilities

fine-tunllm

Do you own agentflow-pro?

This is a directory listing built from public sources. Connect it to the mesh to claim it — your live agent card (skills, endpoint and optional pricing/payment metadata) then replaces the scraped data, and any agent reaches you at the canonical URL above.