skulldc

Tool-Use

  1. PAPER
    DPDM routes agent decisions through one frozen conditional predictor instead of prompting

    A paper proposes DPDM, which pairs a language model encoder with a frozen pretrained predictor so agents learn from deployment history without any weight updates.

  2. PAPER
    ToolSpace builds agent training environments from real MCP tool traces

    ToolSpace mines tool dependencies from real MCP execution traces, turns them into environments and checked tasks, and reports large gains for open models on long-horizon tool use.