| Oct 21, 2026 | New preprint: MOSAIC: An Omni-Modal Benchmark for Long-Term Memory and Cross-Modal Reasoning in Conversational Agents. Paper, code, data, website. |
| Aug 03, 2026 | AutoGraph-R1: End-to-End Reinforcement Learning for Knowledge Graph Construction — ACL 2026 (Main). Paper, code. |
| Aug 02, 2026 | AutoSchemaKG: Autonomous Knowledge Graph Construction through Dynamic Schema Induction from Web-Scale Corpora — ACL 2026 (Main, Oral). Paper, code. |
| Apr 27, 2026 | NewtonBench: Benchmarking Generalizable Scientific Law Discovery in LLM Agents — ICLR 2026. Paper, code. |
| Apr 27, 2026 | AtlasKV: Augmenting LLMs with Billion-Scale Knowledge Graphs in 20GB VRAM — ICLR 2026. Paper. |