András Lukács

activity

20062025

most citedImpact of non-Poisson activity patterns on spreading processes

340 citations · 482 across the 9 of their papers we have counts for

collaborators

Showing 2025Show all

2 papers · 1 filter

cs.CR2025

Improving LLM Agents with Reinforcement Learning on Cryptographic CTF Challenges

Lajos Muzsai, David Imolai, András Lukács

We present 'Random-Crypto', a procedurally generated cryptographic Capture The Flag (CTF) dataset designed to unlock the potential of Reinforcement Learning (RL) for LLM-based agen…

stat.CO2025

$w hi ttl e h u r s t$ : A Python package implementing Whittle's likelihood estimation of the Hurst exponent

Bálint Csanády, Lóránt Nagy, András Lukács

This paper presents $w hi ttl e h u r s t$ , a Python package implementing Whittle's likelihood method for estimating the Hurst exponent in fractional Brownian motion (fBm). While the theor…

Improving LLM Agents with Reinforcement Learning on Cryptographic CTF Challenges

whittlehurst: A Python package implementing Whittle's likelihood estimation of the Hurst exponent

$w hi ttl e h u r s t$ : A Python package implementing Whittle's likelihood estimation of the Hurst exponent