An embodied agent that keeps expanding its behavior repertoire through ongoing human–robot interaction — new skills, new object concepts, and new language grounding are acquired online rather than baked in at training time.
Inspired by Karpathy's *autoresearch* direction, AURA is a sample-efficient prompt optimizer for compound AI systems: after every rollout it hands the full trace back to the LLM and asks for one named edit to its own prompt. Across multi-hop QA, instruction following, and AIME-style math, AURA matches GRPO with up to 35× fewer rollouts and beats MIPROv2 by ~10 points on aggregate.
Industrial vision QA system for a live hazardous-powder-explosive packaging line. ≥ 99% accuracy over a 30-day production run on the customer's RTX 4060; operator-level alarms via a fixed-protocol online-monitoring API.
A legal-service LLM built with Southwest University of Political Science and Law (SWUPL) and Beijing Chaoxing Tianxia: RoPE-extended long-context backbone, legal knowledge graph + vector DB, tool-calling and form-filling agent, and a small intent/NER model that rewrites user questions into formal logical symbols for reasoning.
Formulated aerospace-part electroplating scheduling as a large-scale MILP and trained a GNN on historical schedules to provide warm-start solutions and variable priorities. FENNEL graph partitioning + high-confidence variable fixing reduced the effective search space by ≈ 10×; average solve time ≳ 10× faster.