arXiv subjects

Gonca Gürsun

Publications and source records attributed to Gonca Gürsun.

3 recordsLinked to original sources

arXiv2025

Towards Trustworthy Multi-Turn LLM Agents via Behavioral Guidance

Large Language Models demonstrate strong reasoning and generation abilities, yet their behavior in multi-turn tasks often lacks reliability and verifiability. We present a task completion framework that enables LLM-based agents to act under explicit behavioral guidance in environments described by reinforcement learning formalisms with defined observation, action, and reward signals. The framework integrates three components: a lightweight task profiler that selects reasoning and generation strategies, a reasoning module that learns verifiable observation - action mappings, and a generation module that enforces constraint-compliant outputs through validation or deterministic synthesis. We show that as the agent interacts with the environment, these components co-evolve, yielding trustworthy behavior.

cs.AI↗

arXiv2023

Can you text what is happening? Integrating pre-trained language encoders into trajectory prediction models for autonomous driving

In autonomous driving tasks, scene understanding is the first step towards predicting the future behavior of the surrounding traffic participants. Yet, how to represent a given scene and extract its features are still open research questions. In this study, we propose a novel text-based representation of traffic scenes and process it with a pre-trained language encoder. First, we show that text-based representations, combined with classical rasterized image representations, lead to descriptive scene embeddings. Second, we benchmark our predictions on the nuScenes dataset and show significant improvements compared to baselines. Third, we show in an ablation study that a joint encoder of text and rasterized images outperforms the individual encoders confirming that both representations have their complementary strengths.

cs.CV↗

arXiv2017

On Spectral Analysis of the Internet Delay Space and Detecting Anomalous Routing Paths

Latency is one of the most critical performance metrics for a wide range of applications. Therefore, it is important to understand the underlying mechanisms that give rise to the observed latency values and diagnose the ones that are unexpectedly high. In this paper, we study the Internet delay space via robust principal component analysis (RPCA). Using RPCA, we show that the delay space, i.e. the matrix of measured round trip times between end hosts, can be decomposed into two components - the expected latency between end hosts with respect to the current state of the Internet and the inflation on the paths between the end hosts. Using this decomposition, first we study the well-known low-dimensionality phenomena of the delay space and ask what properties of the end hosts define the dimensions. Second, using the decomposition, we develop a filtering method to detect the paths which experience unexpected latencies and identify routing anomalies. We show that our filter successfully identifies an anomalous route even when its observed latency is not obviously high in magnitude.

cs.NI↗