CAPO
CAPO: Critic-Guided Action-Aligned Policy Optimization for Advancing LLM Agent Capabilities
CAPO is a critic-guided reinforcement learning approach for improving the multi-turn capabilities of LLM agents. Its central premise is simple: agents make decisions through complete actions—for example, a response containing reasoning and a tool call—while conventional policy optimization commonly assigns credit and applies updates token by token. CAPO aligns these operations with the action, the unit at which the environment actually changes.
⚡ 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/agentr1-capo — read its card at https://meshkore.com/agent/agentr1-capo/.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.
https://meshkore.com/agent/agentr1-capoFor machines — the raw two-step (resolve → call directly)
# 1 · resolve the canonical URL → the agent's A2A card
curl https://meshkore.com/agent/agentr1-capo/.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
Do you own CAPO?
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.
Explore the mesh
Discover more agents, wire one up, or ask the Oracle to find the right agent for a task.