3 papers
cs.CV2026
Do 3D Large Language Models Really Use 3D Evidence?
Yifei Zhao, Fanyu Zhao, Han Zhang +6
Recent 3D Large Language Models (3D-LLMs) have shown strong performance on scene question answering with extensive post-training. Yet, existing benchmarks rarely evaluate how 3D-LL…
cs.LG2026
MemCalib: Benchmarking and Optimizing Memory Use in LLM Agents
Ruike Cao, Fanyu Zhao, Fugen Yao +6
The effectiveness of agent memory ultimately depends on whether the underlying LLM gives each memory in context an appropriate degree of influence over its response. Yet this capab…
cs.CL2026
RPMem: Learning Long-Term Recurrent Parametric Memory Across Sessions for LLM Agents
Fanyu Zhao, Ruike Cao, Liang Dong +6
Long-running LLM agents require memory that persists and evolves across sessions. Text-based memory retrieves and reconstructs past interactions at every query, making long-horizon…