Andrei C. Aioanei

Papers on Lattice

Total citations

Topics

h-index

Research focus

Eval Frameworks & Benchmarks (2)Tool Use & Agents (1)World Models & Planning (1)Natural Language Processing (1)Code Generation & Program Synthesis (1)

Frequent co-authors

Jens Lehmann (2)Sahar Vahdati (2)Andrei Aioanei (1)Hamed Babaei Giglou (1)

Papers (3)

Jul 30, 2026

Amazon ScienceJul 30, 2026·also TIB -Leibniz Information Centre for Science

Tycho: Active Abstraction with Programmatic World Models for ARC-AGI-3

Tycho's innovative approach to active abstraction allows agents to achieve perfect action efficiency while navigating complex game environments, outperforming human players significantly.

Jens Lehmann, Andrei C. Aioanei, Andrei Aioanei +1

Tool Use & Agents World Models & Planning

Jul 2, 2026

Hamed Babaei Giglou +4Jul 2, 2026·also TIB Leibniz Information Centre for Science and Technology

OntoLearner: A Modular Python Library for Ontology Learning with Large Language Models

The central challenge of ontology learning isn't model sophistication but rather how knowledge is structured and encoded, as revealed by a comprehensive evaluation using OntoLearner.

Hamed Babaei Giglou, Jennifer D’Souza, Andrei C. Aioanei +2

Eval Frameworks & Benchmarks Natural Language Processing

Mar 5, 2026

Mar 5, 2026·also TIB - Leibniz Information Centre

ARC-TGI: Human-Validated Task Generators with Reasoning Chain Templates for ARC-AGI

Forget static benchmarks: ARC-TGI offers a dynamic, human-validated approach to generating ARC-AGI tasks, enabling scalable dataset sampling and controlled benchmarking.

Jens Lehmann, S. Khushbakht, Syeda Khushbakht +6

Code Generation & Program Synthesis Eval Frameworks & Benchmarks Reasoning & Chain-of-Thought

Search

Andrei C. Aioanei

Research focus

Frequent co-authors

Papers (3)