Tag
Introduces AgenticCANN, a knowledge-augmented agentic evolution framework for automated Ascend C operator generation on Huawei NPUs, achieving significant speedups and improved feasibility across multiple operator patterns.
AEvo is a meta-editing framework that improves iterative agentic search by separating proposal and evaluation into two roles and using accumulated memory to guide future search. It achieves a 26% relative gain over baselines and state-of-the-art results on open-ended optimization tasks.
Solvita is an agentic evolution framework that enables continuous learning in code generation through reinforcement learning updates to graph-structured knowledge networks, achieving state-of-the-art performance on competitive programming benchmarks.