2 papers
cs.AI2026
Learning What to Skip: Counterfactual Credit Assignment for Efficient Multi-Agent LLM Workflows
Jinfeng Xu, Zheyu Chen, Ziyue Peng +6
Multi-agent LLM workflows use planning, execution, verification, and summarization to improve task performance, yet the value of each component depends on the state already produce…
cs.IR2026
Recommendation World Models for Future-State Control
Jinfeng Xu, Zheyu Chen, Ziyue Peng +6
Sequential recommendation optimizes which items to rank, while each displayed slate also shapes subsequent feedback and user state. We study how a trained ranker can support decisi…