arXiv AI July 14, 2026 By Parastou Fahim, Constantino Lagoa, R\^omulo Meira-G'oes

Learning Linear Temporal Specifications from Demonstrations with Uncertainty

arXiv:2607. 10918v1 Announce Type: new Abstract: Learning temporal logic specifications from system demonstrations is essential for tasks such as formal verification and controller synthesis, especially in safety-critical domains.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

arXiv AI

Sep 2

On Synthesis of Metric Interval Temporal Logics

arXiv:2609.01032v1 Announce Type: cross Abstract: Automated mining of formal specifications is vital for verifying real-time systems. However, existing passive learning approaches remain restricted t...

By Hsi-Ming Ho, Shankaranarayanan Krishna, Khushraj Madnani

benchmarks

arXiv Machine Learning

Aug 17

hint$^2$: Hierarchical World Models for Inference-Time Temporal Logic Guidance

arXiv:2608. 13678v1 Announce Type: cross Abstract: A central goal of robot learning is to enable robots to execute rich instructions specified at runtime.

By Moritz Zoellner, Anastasios Manganaris, Ahmed H. Qureshi, Rohan Paleja

diffusion robotics safety

arXiv Machine Learning

Jul 13

Learning-enabled Parameter Synthesis for Nonlinear Systems from Signal Temporal Logic

arXiv:2607. 08899v1 Announce Type: cross Abstract: Signal Temporal Logic (STL) is increasingly used to describe interpretable objectives and constraints for optimal control and learning methods, especially when no target time series data is available.

By Alex Beaudin, Hanna Krasowski, Eric Palanques-Tost, Calin Belta, Murat Arack

arXiv AI

Aug 17

Reward Machines for Signal Temporal Logic

arXiv:2608. 13625v1 Announce Type: new Abstract: Signal temporal logic (STL) provides a formal language for specifying real-time properties of real-valued observations, along with a quantitative robustness score for monitoring satisfaction.

By Alper Kamil Bozkurt, Shangtong Zhang, Yuichi Motai

agents reinforcement-learning

arXiv AI

Aug 17

Semantically Labelled Automata for Multi-Task Reinforcement Learning with LTL Instructions

arXiv:2602. 06746v2 Announce Type: replace Abstract: We study multi-task reinforcement learning (RL), a setting in which an agent learns a single, universal policy capable of generalising to arbitrary, possibly unseen tasks.

By Alessandro Abate, Giuseppe De Giacomo, Mathias Jackermeier, Jan Kret\'insk\'y, Maximilian Prokop, Christoph Weinhuber

rag agents reinforcement-learning benchmarks

arXiv AI

Aug 18

Zero-Shot Instruction Following in RL via Structured LTL Representations

arXiv:2602. 14344v2 Announce Type: replace-cross Abstract: We study instruction following in multi-task reinforcement learning, where an agent must zero-shot execute novel tasks not seen during training.

By Mathias Jackermeier, Mattia Giuri, Jacques Cloete, Alessandro Abate

agents reinforcement-learning

One email a morning, machine-written

Related stories

On Synthesis of Metric Interval Temporal Logics

hint$^2$: Hierarchical World Models for Inference-Time Temporal Logic Guidance

Learning-enabled Parameter Synthesis for Nonlinear Systems from Signal Temporal Logic

Reward Machines for Signal Temporal Logic

Semantically Labelled Automata for Multi-Task Reinforcement Learning with LTL Instructions

Zero-Shot Instruction Following in RL via Structured LTL Representations