6 citations · 14 across the 8 of their papers we have counts for
10 papers
Cortex: A Fixed-Point Theory of Governed Coding Agents - Technical Report
Marius-Constantin Dinu, Florian Zeba
A coding agent combines a large language model (LLM) with a harness that plans, edits, and executes code. We study Cortex, a supervisory layer for pre-execution governance, require…
HyDRA: A Hybrid-Driven Reasoning Architecture for Verifiable Knowledge Graphs
Adrian Kaiser, Claudiu Leoveanu-Condrei, Ryan Gold +2
The synergy between symbolic knowledge, often represented by Knowledge Graphs (KGs), and the generative capabilities of neural networks is central to advancing neurosymbolic AI. A…
Primality Testing via Circulant Matrix Eigenvalue Structure: A Novel Approach Using Cyclotomic Field Theory
Marius-Constantin Dinu
This paper presents a novel primality test based on the eigenvalue structure of circulant matrices constructed from roots of unity. We prove that an integer is prime if and…
Parameter Choice and Neuro-Symbolic Approaches for Deep Domain-Invariant Learning
Marius-Constantin Dinu
As artificial intelligence (AI) systems advance, we move towards broad AI: systems capable of performing well on diverse tasks, understanding context, and adapting rapidly to new s…
Large Language Models Can Self-Improve At Web Agent Tasks
Ajay Patel, Markus Hofmarcher, Claudiu Leoveanu-Condrei +3
Training models to act as agents that can effectively navigate and perform actions in a complex environment, such as a web browser, has typically been challenging due to lack of tr…
SymbolicAI: A framework for logic-based approaches combining generative models and solvers
Marius-Constantin Dinu, Claudiu Leoveanu-Condrei, Markus Holzleitner +2
We introduce SymbolicAI, a versatile and modular framework employing a logic-based approach to concept learning and flow management in generative processes. SymbolicAI enables the…
Addressing Parameter Choice Issues in Unsupervised Domain Adaptation by Aggregation
Marius-Constantin Dinu, Markus Holzleitner, Maximilian Beck +7
We study the problem of choosing algorithm hyper-parameters in unsupervised domain adaptation, i.e., with labeled data in a source domain and unlabeled data in a target domain, dra…
Reactive Exploration to Cope with Non-Stationarity in Lifelong Reinforcement Learning
Christian Steinparz, Thomas Schmied, Fabian Paischer +5
In lifelong learning, an agent learns throughout its entire life without resets, in a constantly changing environment, as we humans do. Consequently, lifelong learning comes with a…
A Dataset Perspective on Offline Reinforcement Learning
Kajetan Schweighofer, Andreas Radler, Marius-Constantin Dinu +5
The application of Reinforcement Learning (RL) in real world environments can be expensive or risky due to sub-optimal policies during training. In Offline RL, this problem is avoi…
Align-RUDDER: Learning From Few Demonstrations by Reward Redistribution
Vihang P. Patil, Markus Hofmarcher, Marius-Constantin Dinu +5
Reinforcement learning algorithms require many samples when solving complex hierarchical tasks with sparse and delayed rewards. For such complex tasks, the recently proposed RUDDER…