most citedLight-IF: Endowing LLMs with Generalizable Reasoning via Preview and Self-Checking for Complex Instruction Following

1 citations · 1 across the 2 of their papers we have counts for

collaborators
Showing cs.AIShow all

1 paper · 1 filter

cs.AI2026

LexiHorizon: Stabilizing Reinforcement Learning for Long-Horizon Deep Search

Zhiqing Nong, Liang Wen, Chao-Hsuan Liu

Deep search agents tackle complex knowledge tasks through iterative retrieval, multi-hop reasoning, and evidence synthesis across multiple sources. Existing approaches typically as…