AI/ML arXiv cs.AI

Supporting Autonomous Process Execution within a Multi-Perspective Constraint Frame via Numeric Planning

Research introducing a tool for what-if analysis in AI-augmented Business Process Management Systems using multi-perspective constraint frames.

AI/ML arXiv cs.AI

RELIC: Revealed Principles for Learning Interpretable Composable Skills in Multi-Agent Planning

Introduces RELIC, a framework for privacy-preserving multi-agent planning that uses 'revealed principles' instead of sharing executable policies.

AI/ML arXiv cs.AI

FUSAR-R1: A Large-Scale Reasoning Model for Intelligent Interpretation of SAR Images

Presents FUSAR-R1, a large-scale reasoning model utilizing chain-of-thought and reinforcement learning for intelligent SAR image interpretation.

AI/ML arXiv cs.AI

From Overload to Insights: How AI Agents Can Support Scientists in Analyzing Complex Data

Explores the design and evaluation of AI agents to assist scientists at European XFEL in analyzing complex, large-scale datasets.

AI/ML arXiv cs.AI

AgentBrew: Lifelong Knowledge Brewing from Strong Teachers to Weak LLM Agents

Introduces AgentBrew, a training-free knowledge distillation method that converts teacher LLM experiences into external memory for weaker student agents.

AI/ML arXiv cs.AI

Beyond Semantic Equivalence: Logical Graphs for LLM Uncertainty Quantification

Proposes Logical Graph Uncertainty (LGU), a framework for better LLM uncertainty quantification by modeling logical entailment and incompatibility.

AI/ML arXiv cs.AI

Environment-free Synthetic Data Generation for API-Calling Agents

A method for generating synthetic training data for API-calling agents using LLMs as world models, removing the need for live executable environments.

AI/ML arXiv cs.AI

Lomekwi: Resource-Bounded Tool Discovery in LLM Agents

Analyzes tool discovery in LLM agents, distinguishing between curiosity, recognition, and efficiency, and identifying an inverse scaling law for recognition.

AI/ML arXiv cs.AI

Training Continuous Chain of Thought Models: A Tale of Two Regimes

Introduces C-MTP, a fast direct supervision approach for Continuous Chain-of-Thought models, while highlighting performance drops in long-trace reasoning.

Software Engineering Hacker News

A PHP server that can handle 10x as many concurrent requests as Nginx+PHP-fpm

A discussion about a new PHP server claiming to handle 10x more concurrent requests than the traditional Nginx and PHP-fpm stack.

Other Hacker News

Zoom is now Chrome only

Zoom has reportedly shifted its compatibility to be Chrome-only, potentially limiting user access on other browsers.

AI/ML arXiv cs.AI

Just A Rather Very Intelligent Spoken Agent

Researchers introduce JarvisBench and a modular prototype for always-on, spoken AI mediators that facilitate better long-horizon agent-user interaction.

AI/ML arXiv cs.AI

A Research Prototype for Closed-Loop Generative Design of Customized Foot Orthoses via Semantic-Physics Alignment

TANS-FO is a research prototype for automating the design of customized foot orthoses using a Text-Aligned Neural Surrogate and GNNs for real-time stress prediction.

AI/ML arXiv cs.AI

TopoTuner: Topological Finetuning of Large Language Models

TopoTuner is a new framework for selective fine-tuning of LLMs using topological persistence diagrams to identify which weights to freeze, reducing parameters and training time.

AI/ML arXiv cs.AI

Diversity-Oriented Fine-Tuning for Uncertainty-Based Hallucination Detection

This paper proposes diversity-oriented fine-tuning using SFT and DPO to make LLM hallucinations more detectable via semantic entropy.

AI/ML arXiv cs.AI

DS@GT ARC at eRisk 2026: Hybrid Multi-Agent LLM System with Structured Algorithmic Guidance for Conversational Depression Screening

A hybrid multi-agent system combining Gemma 27B with algorithmic guidance for depression screening outperformed a paid GPT-5-nano baseline at lower cost.

AI/ML arXiv cs.AI

Tractable Query Answering under Epistemic Confidentiality Policies in DL Ontologies (extended version)

The paper presents a new semantics based on minimal policy violation (MPV) for tractable query answering in DL ontologies under confidentiality policies.

AI/ML arXiv cs.AI

RECON: Benchmarking Agent Memory for Compositional Reasoning over Long Contexts

RECON is a new benchmark evaluating compositional reasoning over long contexts (50k-100k tokens) to test agent memory and reliability.

AI/ML arXiv cs.AI

Constraint-Anchored Reasoning Traces

CART is a neuro-symbolic framework that interleaves natural language reasoning with symbolic constraints to prevent 'error snowballing' in multimodal LLMs.

Software Engineering Hacker News

Reverse-engineering is cheap now

A discussion on the increasing accessibility and reduced cost of reverse-engineering tools and techniques.