Publications
ArcMemo: Abstract Reasoning Composition with Lifelong LLM Memory
Matthew Ho, Chen Si, Zhaoxiang Feng, Fangxu Yu, Yichi Yang, Zhijian Liu, Zhiting Hu, Lianhui Qin.
Under review at ICLR 2026.
Concept-level memory for test-time continual learning on ARC-AGI abstract reasoning puzzles. Achieved 59.33% official score (+7.5% relative gain over no-memory baseline).
LabMemo: Concept-Level Memory for Autonomous Scientific Discovery
Zhaoxiang Feng, David Scott Lewis, Enrique Zueco.
Accepted at IEEE IROS 2025 Workshop on Embodied AI and Robotics for Future Scientific Discovery (AIR4S).
Extends concept-level memory to autonomous scientific agents with a Planner–Selector–Verifier architecture. Achieved 4.01% parameter identification error from 50 samples and 87% task retention.