critique-aware-training

Tag

Cards List
#critique-aware-training

CAST: Critique-Aware Supervision for Training Reliable Long-Horizon Tool-Calling Agents

Hugging Face Daily Papers · yesterday Cached

CAST is a critique-aware training framework that improves LLM agent reliability by generating structured action-level rationales from sparse outcomes, outperforming GPT-OSS-120B on tool-calling benchmarks.

0 favorites 0 likes
← Back to home

Submit Feedback