Cover Image

Natural Synthesis: Outperforming Reactive Synthesis Tools with Large Reasoning Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Schmitt, Frederik, Cosler, Matthias, Metzger, Niklas, Siber, Julian, Krsmanovic, Vladimir, Ghanem, Mohamed, Finkbeiner, Bernd
Format:	Preprint
Published:	2026
Subjects:	Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Learning Representations Through Contrastive Neural Model Checking
by: Krsmanovic, Vladimir, et al.
Published: (2025)

Learning Better Representations From Less Data For Propositional Satisfiability
by: Ghanem, Mohamed, et al.
Published: (2024)

Less Effort, Shorter Proofs: Reinforcement Learning for Security Protocol Analysis in Tamarin
by: Cosler, Matthias, et al.
Published: (2026)

NeuroSynt: A Neuro-symbolic Portfolio Solver for Reactive Synthesis
by: Cosler, Matthias, et al.
Published: (2024)

Synthesis of Temporal Causality
by: Finkbeiner, Bernd, et al.
Published: (2024)

Stream-Based Monitoring of Algorithmic Fairness
by: Baumeister, Jan, et al.
Published: (2025)

Explainability Requirements as Hyperproperties
by: Finkbeiner, Bernd, et al.
Published: (2025)

Information Flow Guided Synthesis with Unbounded Communication
by: Finkbeiner, Bernd, et al.
Published: (2024)

Closure and Complexity of Temporal Causality
by: Carelli, Mishel, et al.
Published: (2025)

Counterfactual Explanations for MITL Violations
by: Finkbeiner, Bernd, et al.
Published: (2024)

An Information-Flow Perspective on Explainability Requirements: Specification and Verification
by: Finkbeiner, Bernd, et al.
Published: (2025)

Synthesis of Universal Safety Controllers
by: Finkbeiner, Bernd, et al.
Published: (2025)

When Independent Sampling Outperforms Agentic Reasoning
by: Dong, Yihe, et al.
Published: (2026)

Heavy-Tailed Class Imbalance and Why Adam Outperforms Gradient Descent on Language Models
by: Kunstner, Frederik, et al.
Published: (2024)

GenDFIR: Advancing Cyber Incident Timeline Analysis Through Retrieval Augmented Generation and Large Language Models
by: Loumachi, Fatma Yasmine, et al.
Published: (2024)

Agentic Proposing: Enhancing Large Language Model Reasoning via Compositional Skill Synthesis
by: Jiao, Zhengbo, et al.
Published: (2026)

PromptCoT 2.0: Scaling Prompt Synthesis for Large Language Model Reasoning
by: Zhao, Xueliang, et al.
Published: (2025)

A Scientific Reasoning Model for Organic Synthesis Procedure Generation
by: Liu, Guoqing, et al.
Published: (2025)

Model Comparisons: XNet Outperforms KAN
by: Li, Xin, et al.
Published: (2024)

Scaling Transformers for Time Series Forecasting: Do Pretrained Large Models Outperform Small-Scale Alternatives?
by: Chakraborty, Sanjay, et al.
Published: (2025)

Task-Specific Efficiency Analysis: When Small Language Models Outperform Large Language Models
by: Cao, Jinghan, et al.
Published: (2026)

SPARF: Large-Scale Learning of 3D Sparse Radiance Fields from Few Input Images
by: Hamdi, Abdullah, et al.
Published: (2022)

SFT-then-RL Outperforms Mixed-Policy Methods for LLM Reasoning
by: Limozin, Alexis, et al.
Published: (2026)

Motor Imagery EEG Signal Classification Using Minimally Random Convolutional Kernel Transform and Hybrid Deep Learning
by: Hwaidi, Jamal, et al.
Published: (2025)

Monitoring Second-Order Hyperproperties
by: Beutner, Raven, et al.
Published: (2024)

LLMSynthor: Macro-Aligned Micro-Records Synthesis with Large Language Models
by: Tang, Yihong, et al.
Published: (2025)

Temporal Reasoning with Large Language Models Augmented by Evolving Knowledge Graphs
by: Lin, Junhong, et al.
Published: (2025)

LiveOIBench: Can Large Language Models Outperform Human Contestants in Informatics Olympiads?
by: Zou, Kaijian, et al.
Published: (2025)

Differentially Private Runtime Monitoring
by: Finkbeiner, Bernd, et al.
Published: (2026)

Verifying Asynchronous Hyperproperties in Reactive Systems
by: Beutner, Raven, et al.
Published: (2025)

Reasoning of Large Language Models over Knowledge Graphs with Super-Relations
by: Wang, Song, et al.
Published: (2025)

HAD: Hybrid Architecture Distillation Outperforms Teacher in Genomic Sequence Modeling
by: Yang, Hexiong, et al.
Published: (2025)

Transcendence: Generative Models Can Outperform The Experts That Train Them
by: Zhang, Edwin, et al.
Published: (2024)

Model Reprogramming Outperforms Fine-tuning on Out-of-distribution Data in Text-Image Encoders
by: Geng, Andrew, et al.
Published: (2024)

Combining LLM Code Generation with Formal Specifications and Reactive Program Synthesis
by: Murphy, William, et al.
Published: (2024)

A Large Language Model for Feasible and Diverse Population Synthesis
by: Lim, Sung Yoo, et al.
Published: (2025)

Scaling Embeddings Outperforms Scaling Experts in Language Models
by: Liu, Hong, et al.
Published: (2026)

Training Multimodal Large Reasoning Models Needs Better Thoughts: A Three-Stage Framework for Long Chain-of-Thought Synthesis and Selection
by: Wang, Yizhi, et al.
Published: (2025)

Large Language Model-Guided Prediction Toward Quantum Materials Synthesis
by: Okabe, Ryotaro, et al.
Published: (2024)

Confidence-Credibility Aware Weighted Ensembles of Small LLMs Outperform Large LLMs in Emotion Detection
by: Elgabry, Menna, et al.
Published: (2025)