Steer, Don’t Rewrite: Annotate Agent Trajectories 2 Faster in Live Environments with onPanda
Dynamically connect to agent environments and annotate multi-turn SFT and preference data with tool_calls and reasoning online Existing agent annotation tools (such as Potato and Argilla ) mostly support assigning attributes or adding textual feedback to completed trajectories. However, editing trajectories to construct high-quality multi-turn agent SFT data presents two core challenges: Coupled…
onPanda is an open-source LLM alignment data annotation tool that simplifies the process of annotating multi-turn agent trajectories in live environments. Unlike existing agent annotation tools, onPanda enables annotators to edit reasoning, content, and tool_calls in real-time, rather than rewriting outputs after the fact. This approach offers several advantages, including faster annotation, high-quality preference data, and fine-grained token-level supervision.
Written by urgent.news from Dev.to's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
