{"slug": "onpanda-efficient-annotation-of-on-policy-alignment-data-for-llms-and-agents-via", "title": "onPanda: Efficient Annotation of On-Policy Alignment Data for LLMs and Agents via Token-Level Correction", "summary": "Researchers introduced onPanda, an interactive tool for annotating LLM alignment data and agent trajectories that uses token-level correction as its core interaction, letting annotators locate the first inappropriate token in a model response and pick a substitute. The tool targets efficient annotation of on-policy alignment data for LLMs and agents.", "body_md": "We present onPanda, an interactive tool for efficiently annotating LLM alignment data and agent trajectories. onPanda adopts token-level correction as its core interaction: while reading a model response, the annotator locates the first inappropriate token and either picks a substitute from the mode", "url": "https://wpnews.pro/news/onpanda-efficient-annotation-of-on-policy-alignment-data-for-llms-and-agents-via", "canonical_source": "https://aiflash.com/news/124144/", "published_at": "2026-09-22 05:00:00+00:00", "updated_at": "2026-09-22 05:25:53.118608+00:00", "lang": "en", "topics": ["ai-safety", "large-language-models", "ai-agents", "ai-research", "ai-tools"], "entities": ["onPanda"], "alternates": {"html": "https://wpnews.pro/news/onpanda-efficient-annotation-of-on-policy-alignment-data-for-llms-and-agents-via", "markdown": "https://wpnews.pro/news/onpanda-efficient-annotation-of-on-policy-alignment-data-for-llms-and-agents-via.md", "text": "https://wpnews.pro/news/onpanda-efficient-annotation-of-on-policy-alignment-data-for-llms-and-agents-via.txt", "jsonld": "https://wpnews.pro/news/onpanda-efficient-annotation-of-on-policy-alignment-data-for-llms-and-agents-via.jsonld"}}