AI/ML arXiv cs.AI

The Easy Trap: Why LLMs Underestimate Misconception-Driven Difficulty

A study reveals that LLMs underestimate the difficulty of educational tasks driven by student misconceptions, a phenomenon termed the 'Easy Trap'.

AI/ML arXiv cs.AI

The Human Utility Factor: A Computable Welfare Metric That Reframes AI Governance as a Constrained Optimisation Problem

The Human Utility Factor (HUF) is proposed as a computable welfare metric to treat AI governance as a constrained optimization problem focused on socioeconomic stability.

Cybersecurity arXiv cs.AI

AI Security Priorities: A Field-Wide Agenda

A multi-sector expert agenda is presented to prioritize AI security efforts, focusing on technical assurance and the governance of agentic AI.

AI/ML arXiv cs.AI

SimpleWikiSearch: A Clean Offline Wikipedia Environment for Agentic Search

SimpleWikiSearch provides a controlled, offline environment for reproducible agentic-search evaluation using a cleaned Wikipedia dump.

AI/ML arXiv cs.AI

GuidedRAG: Semantic Steering of Retrieval-Augmented Generation

GuidedRAG introduces semantic steering and a selection stage to improve retrieval relevance and reduce overhead in Retrieval-Augmented Generation.

AI/ML arXiv cs.AI

IFCMemoryBench: Evaluating Long-Term Memory of LLM-Based Agents in BIM Information Retrieval

IFCMemoryBench is a new benchmark for evaluating long-term memory in LLM agents within the specialized domain of Building Information Modelling (BIM).

AI/ML arXiv cs.AI

IDP AutoOpt: Agent-Driven Optimization of Document Processing Pipeline Configurations

IDP AutoOpt is an autonomous LLM agent that optimizes configurations for intelligent document processing pipelines, reducing tuning time from weeks to hours.

AI/ML arXiv cs.AI

FinCacheServe: Dependency-Consistent Answer Reuse for Cost-Efficient RAG Serving over Mutable Enterprise Documents

FinCacheServe is a cost-efficient RAG serving system that uses dependency-consistent answer reuse to reduce LLM calls for mutable enterprise documents.

AI/ML Hacker News

DeepSeek-V4-Flash Update

DeepSeek-V4-Flash update discussed in Hacker News comments.

Software Engineering Hacker News

Simulating TCP loss and congestion in browser using Go/WASM

A project demonstrating how to simulate TCP loss and congestion within a web browser using Go and WebAssembly.

AI/ML arXiv cs.AI

Predict before you train: Scaling Laws for particle physics foundation models

Researchers develop scaling laws for particle physics foundation models, allowing performance prediction of large models based on small-model training compute.

AI/ML arXiv cs.AI

Forensic Reproducibility Audit of a Radiology Vision-Language Model Benchmark: From Intended Protocol to Released Artifact

A forensic audit reveals reproducibility issues in a radiology vision-language model benchmark, leading to the withdrawal of original performance claims.

AI/ML arXiv cs.AI

Emergent Sparsity in Frozen Random CNN Feature Extractors for Deep Reinforcement Learning

Study finds that deep reinforcement learning agents using frozen random CNN feature extractors spontaneously develop sparse representations of task-relevant information.

AI/ML arXiv cs.AI

Large-Scale ChatBot Validation Through Customer Digital Twin Simulations

A new framework for validating LLM chatbots in banking using synthetic customer digital twins to simulate diverse interaction styles.

AI/ML arXiv cs.AI

Sim2Win: A Team-Agnostic, Event-Based Pre-Match Outcome Prediction and Tactical Profiling System for Football

Sim2Win is a team-agnostic football outcome prediction system using tactical profiles and event data instead of team identities.

AI/ML arXiv cs.AI

Identifying Implicit Bias in LLM-based Chat AI Toward People with Intellectual Disabilities

Research identifies negative implicit biases toward people with intellectual disabilities in popular LLMs, including GPT-4o and Llama-3.

AI/ML arXiv cs.AI

Archetypes or ability? Clustering for modelling student mathematical competence

A study on student mathematical competence suggests overall ability is the dominant factor for performance, challenging assumptions about discrete skill sets.

AI/ML arXiv cs.AI

The Age of AI Agents Demands A New Scientific Paradigm To Sustain Trustworthy Science

An argument for a new scientific paradigm to maintain trust in science as AI agents begin to autonomously generate hypotheses and design experiments.

Software Engineering Hacker News

JEP 401: Value Objects (Preview) merged to OpenJDK master

JEP 401 introduces Value Objects to OpenJDK, providing a way to define classes that are treated as values rather than identities.

Cybersecurity Hacker News

Human Honeypot

An exploration or implementation of a 'Human Honeypot', likely focused on cybersecurity or social engineering detection.