arXiv AI July 20, 2026 By Eduardo C. Garrido-Merch\'an

From Black Box to Executable Logic: Explainable Reinforcement Learning through Prolog Expert Systems

arXiv:2607. 15459v1 Announce Type: new Abstract: A trained deep reinforcement learning policy is a black box, and we ask whether it can be made explainable by rewriting it as an executable logic program that reproduces its behaviour and that a person can read, a logic engine can run, and an optimizer can edit.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv AI.

reinforcement-learning

arXiv AI

Aug 6

Capability-Gated Planning: Cost-to-Goal Discovery and the Limits of Myopic Experiment Selection

arXiv:2608. 05085v1 Announce Type: cross Abstract: Systems that automate scientific discovery must repeatedly decide which experiment to run, which hypothesis to test, which tool to build, and when to stop.

By Ahmed Hassoon, Mark Dredze

arXiv Machine Learning

Aug 4

Near-Optimal Reinforcement Learning for Constrained Recurrence Objectives

arXiv:2511. 19849v2 Announce Type: replace-cross Abstract: Recurrence objectives, where a target region must be visited infinitely often, are a fundamental class of specifications for Markov decision processes (MDPs) and form the core of $\omega$-regular and linear temporal logic (LTL) objectives.

By Dominik Wagner, Leon Witzman, Luke Ong

reinforcement-learning safety

arXiv Machine Learning

Aug 11

Finite Constant Frontiers and Auditable Regret Certificates for Average-Reward Reinforcement Learning

arXiv:2608. 07725v1 Announce Type: new Abstract: Average-reward reinforcement-learning regret is known up to logarithmic factors, but the numerical content of published guarantees is difficult to compare because probability mode, structural parameter, logarithmic normalization, prior information, and planning assumptions differ.

By Ibne Farabi Shihab, Abu Sa-Adat Mohamed Moon-Im Al Ahsan, Md Najmus Swaqeeb

reinforcement-learning safety

arXiv AI

Jun 17

Shattering the Autoregressive Curse: Dynamic Epistemic Entropy Orchestrated Erasable Reinforcement Learning for LLMs

arXiv:2606. 17735v1 Announce Type: new Abstract: Although reinforcement learning (RL) has expanded the cognitive boundaries of large language models (LLMs), it often remains vulnerable to the autoregressive curse in long-horizon logical reasoning: small epistemic perturbations introduced early in generation can propagate irreversibly along the Markov decision process flow, triggering cascading failures that drive the reasoning trajectory toward collapse.

By Ziliang Wang, Kang An, Faqiang Qian, Jialu Cai, Cijun Ouyang, Yuhang Wang, Qibing Ren, Yichao Wu

llms reinforcement-learning benchmarks

arXiv Machine Learning

Aug 11

Information Routing across Batch Boundaries: Memory--Batch Tradeoffs in Lipschitz Bandits

arXiv:2608. 07922v1 Announce Type: new Abstract: Adaptive learning needs both a state that preserves what observations imply and opportunities to act on that state.

By Zicheng Lyu, Zengfeng Huang

arXiv Machine Learning

Jun 29

Learning to Reason with Curriculum II: Compositional Generalization

arXiv:2606. 27721v1 Announce Type: new Abstract: Compositional generalization, the ability to solve complex problems by combining solutions to simpler sub-problems, is a fundamental capability of both natural and artificial intelligence, and a key mechanism underlying chain-of-thought reasoning.

By Nived Rajaraman, Audrey Huang, Miroslav Dudik, Robert Schapire, Dylan Foster, Akshay Krishnamurthy

reinforcement-learning fine-tuning

Related stories

Capability-Gated Planning: Cost-to-Goal Discovery and the Limits of Myopic Experiment Selection

Near-Optimal Reinforcement Learning for Constrained Recurrence Objectives

Finite Constant Frontiers and Auditable Regret Certificates for Average-Reward Reinforcement Learning

Shattering the Autoregressive Curse: Dynamic Epistemic Entropy Orchestrated Erasable Reinforcement Learning for LLMs

Information Routing across Batch Boundaries: Memory--Batch Tradeoffs in Lipschitz Bandits

Learning to Reason with Curriculum II: Compositional Generalization