AI/ML arXiv cs.AI

Euclid-MCP: A Model Context Protocol Server for Deterministic Logical Reasoning via Prolog

Euclid-MCP is an open-source MCP server that integrates LLMs with SWI-Prolog for deterministic logical reasoning in safety-critical domains.

AI/ML arXiv cs.AI

Logical Regression for Planning with Axioms

A new methodology for approximating logical regression in automated planning domains that include axioms, significantly reducing variable counts for execution monitoring.

AI/ML arXiv cs.AI

PATS: Policy-Aware Training Scaffolding for Agentic Reinforcement Learning

PATS is a policy-centric training paradigm for agentic RL that uses dynamic training scaffolds to improve the performance of weak policies in long-horizon tasks.

AI/ML arXiv cs.AI

Bridging the Gap Between Plausibility and Admissibility: Constraint-Aware Flow Maps for Dynamic Graph Systems

Research on using symbolic constraints to improve the structural feasibility of generative trajectory modeling in dynamic graph systems.

AI/ML arXiv cs.AI

Agent-Guided Relational Concept Discovery: Toward Interpretable Surgical Margin Assessment

A framework for Agent-Guided Concept Discovery to improve interpretable surgical margin assessment using mass spectrometry data.

AI/ML arXiv cs.AI

Detecting LLM-Generated Tokens in Human--LLM Coauthored Text

A token-level detection method for identifying LLM-generated content within human-AI coauthored texts using an adaptive smoothing rule.

Other Hacker News

The Ever-Receding Pocket

A Hacker News discussion thread regarding the concept of the 'ever-receding pocket'.

AI/ML arXiv cs.AI

Logic Programming Semantics for Causal Processes

Research investigating the relationship between logic programming semantics and the eventual states of causal processes, particularly for life sciences modeling.

AI/ML arXiv cs.AI

BasketEvent: Understanding Who Did What and When in Basketball Videos

Introduction of BasketEvent, a player-centric basketball event understanding dataset and PlayNet, a reasoning framework for fine-grained sports video analysis.

AI/ML arXiv cs.AI

An LLM-Driven Workflow for Automated Process Control Strategy Generation and Tuning from Dynamic Process Models

A structured LLM-driven workflow for automated process control strategy generation and tuning using dynamic process models and Bayesian optimization.

AI/ML arXiv cs.AI

Expert Behavior Prior Reinforcement Learning

Proposed Expert Behavior Prior (EBP) algorithm to improve online reinforcement learning sample efficiency using a Q-guided conditional variational autoencoder.

Other arXiv cs.AI

Regulating autonomous and agentic AI

A study on the challenges of regulating autonomous and agentic AI, proposing a shift from reactive to active regulatory systems.

AI/ML arXiv cs.AI

SPORD: A Simulation-Propose-then-OR-Dispose Approach for Supply Chain Planning

The SPORD method and NetSim platform by JD.com for decoupled supply chain planning using simulation and integer programming.

AI/ML arXiv cs.AI

Towards Faithful Graph Explanations with Synergistic Edge Effects via Granular Balls

Introduction of SeeExplainer, a parameter-free explainer for Graph Neural Networks that captures synergistic edge effects via granular balls.

AI/ML arXiv cs.AI

Multimodal Pretraining for Generalizable EEG Representation Learning

A multimodal EEG foundation model utilizing Mamba architecture and Vision Transformers for generalizable seizure detection.

AI/ML arXiv cs.AI

MSBraM: A Multi-scale Self-supervised Brain Foundation Model for Hierarchical EEG Dynamics Learning

MSBraM, a multi-scale self-supervised brain foundation model designed to learn hierarchical EEG representations through a two-stage pretraining framework.

AI/ML Hacker News

Flux 3 X Mimic: The Next Generation of Video-Action Models

Discusses Flux 3 X Mimic, a new generation of video-action models.

Other Hacker News

Nothing works and everyone is euphoric

A reflective or critical piece on the current state of technology or society where 'nothing works' despite general euphoria.

Other Hacker News

It's getting harder to focus every day

An exploration or discussion regarding the increasing difficulty of maintaining focus in the modern era.

Software Engineering Hacker News

Show HN: A static, client-side tarot calculator for Brazilian Portuguese

A showcase of a static, client-side tarot calculator specifically for Brazilian Portuguese users.