activity
20242026
collaborators

8 papers

cs.AI2026

Solver-Aware Decompositions for Programming-by-Example: When Dividing Requires Knowing how to Conquer

Janis Zenkner, Tobias Sesterhenn, Tim Grams +1

Decomposition-based Programming-by-example (PBE) scales performance by splitting tasks into subtasks that a learned synthesizer solves: a decomposer predicts intermediate subgoals,…

cs.LG2026

Revisiting Predictive Process Monitoring in the Age of Foundation Models: A Comparative Study of Sequence, Tabular, and LLM Approaches

Lennart Fertig, Lukas Kirchdorfer, Tobias Sesterhenn

Predictive process monitoring (PPM) leverages event logs to forecast the future of running process instances, for instance, predicting the next activity, the remaining time until c…

cs.AI2026

BIM-Edit: Benchmarking Large Language Models for IFC-Based Building Information Modeling

Bharathi Kannan Nithyanantham, Clemens Kujat, Tobias Sesterhenn +5

Large language models (LLMs) are increasingly applied to computer-aided design (CAD) to generate design artifacts from textual instructions. In engineering practice, this requires…

cs.CL2025

MCP4IFC: IFC-Based Building Design Using Large Language Models

Bharathi Kannan Nithyanantham, Tobias Sesterhenn, Ashwin Nedungadi +4

Bringing generative AI into the architecture, engineering and construction (AEC) field requires systems that can translate natural language instructions into actions on standardize…

cs.PL2025

A Compute-Matched Re-Evaluation of TroVE on MATH

Tobias Sesterhenn, Ian Berlot-Attwell, Janis Zenkner +1

Reusing established theorems and formulas is central to mathematical problem solving, serving as essential building blocks for tackling increasingly complex challenges. Recent work…

cs.PL2025

Beyond Either-Or Reasoning: Transduction and Induction as Cooperative Problem-Solving Paradigms

Janis Zenkner, Tobias Sesterhenn, Christian Bartelt

Traditionally, in Programming-by-example (PBE) the goal is to synthesize a program from a small set of input-output examples. Lately, PBE has gained traction as a few-shot reasonin…

cs.SE2025

Shedding Light in Task Decomposition in Program Synthesis: The Driving Force of the Synthesizer Model

Janis Zenkner, Tobias Sesterhenn, Christian Bartelt

Task decomposition is a fundamental mechanism in program synthesis, enabling complex problems to be broken down into manageable subtasks. ExeDec, a state-of-the-art program synthes…

cs.SE2024

AbstractBeam: Enhancing Bottom-Up Program Synthesis using Library Learning

Janis Zenkner, Lukas Dierkes, Tobias Sesterhenn +1

LambdaBeam is a state-of-the-art, execution-guided algorithm for program synthesis that utilizes higher-order functions, lambda functions, and iterative loops within a Domain-Speci…