4 papers
Atropos: Improving Cost-Benefit Trade-off of LLM-based Agents under Self-Consistency with Early Termination and Model Hotswap
Naryeong Kim, Shin Yoo
Open-weight Small Language Models(SLMs) can provide faster local inference at lower financial cost, but may not achieve the same performance level as commercial Large Language Mode…
Capturing Semantic Flow of ML-based Systems
Shin Yoo, Robert Feldt, Somin Kim +1
ML-based systems are software systems that incorporates machine learning components such as Deep Neural Networks (DNNs) or Large Language Models (LLMs). While such systems enable a…
Identifying Bug Inducing Commits by Combining Fault Localisation and Code Change Histories
Gabin An, Jinsu Choi, Jingun Hong +2
A Bug Inducing Commit (BIC) is a code change that introduces a bug into the codebase. Although the abnormal or unexpected behavior caused by the bug may not manifest immediately, i…
Lachesis: Predicting LLM Inference Accuracy using Structural Properties of Reasoning Paths
Naryeong Kim, Sungmin Kang, Gabin An +1
Large Language Models are increasingly used to build agents to perform more complex tasks. As LLMs perform more complicated reasoning through longer interactions, self-consistency,…