2 papers
cs.AI2026
CoEM: Empowering Long-Context Reasoning with Commit-on-Evidence Memory
Jingguang Li, Yebo Wu, Zuyi Guo +7
Long-context reasoning is essential for complex and long-horizon tasks, yet the performance of large language models (LLMs) degrades as context length increases. Recent approaches…
cs.CV2026
SafeVantage: Vantage-Aware Memory for Reliable Embodied Decisions
Sean Hardesty Lewis, Zuyi Guo, Benwang Chen +4
Reliable embodied decisions under partial observability require informative observations and sufficient supporting evidence. However, semantic scores alone do not reveal which view…