Tech Business/VC TechCrunch

Cyera agrees to acquire Oasis Security for $1B to safeguard proliferating AI agents

Cyera is acquiring Oasis Security for $1B to enhance security for AI agents.

AI/ML arXiv cs.AI

MINT-V2X: A Mobility-Integrated Network Trajectory Dataset for Predictive Resource Management

Introduction of MINT-V2X, a dataset combining vehicle trajectories and wireless network parameters for predictive resource management in V2X systems.

AI/ML arXiv cs.AI

EventOD: Event-Aware OD Flow Generation via LLM-Guided Semantic Modulation

EventOD is an event-adaptive framework that uses LLMs to generate origin-destination flows during disruptive events for better urban resilience.

AI/ML arXiv cs.AI

StanceBench: A Benchmark for Audio LLM-Based Interpersonal Stance Evaluation from Speech

StanceBench is a new benchmark for evaluating interpersonal stance in conversational speech using audio-capable LLMs.

AI/ML arXiv cs.AI

TRE: Training-Free Hallucination Detection for Diffusion Language Models

TRE is a training-free metric that detects hallucinations in Diffusion Language Models by analyzing entropy signals during decoding.

Software Engineering Hacker News

Teach Yourself Programming in Ten Years (1998)

An archival look at the long-term process of learning programming, emphasizing that mastery takes years rather than weeks.

AI/ML arXiv cs.AI

CRAFT: Learn the Schema, Execute the Plan

CRAFT is a two-stage post-training recipe that improves coding agents by learning schema knowledge and tool-use behavior, reducing token overhead.

AI/ML arXiv cs.AI

Reason Before You Retrieve: Agentic Planning for Multi-modal RAG

MM-R2 is a multimodal agentic retrieval framework that reasons about what and where to search before performing retrieval in RAG systems.

AI/ML arXiv cs.AI

DocHRL: A Hierarchical Reinforcement Learning Framework for Cost-Optimised Document Classification

DocHRL uses hierarchical reinforcement learning to dynamically select the most cost-effective classification policy for documents based on complexity.

AI/ML arXiv cs.AI

Extracting Algorithms in Pre-trained LLMs: A Case on Hidden Markov Models

Research utilizing the Principal Activations Probe (PAP) to understand how pre-trained LLMs perform in-context learning on Hidden Markov Models.

AI/ML arXiv cs.AI

PTStore (Prefix Tensor Store): Distributed Prefix Caching and Replication for High Throughput Inference Serving

PTStore introduces distributed prefix caching and replication for KV caches to increase inference throughput and reduce latency for long-context LLMs.

AI/ML arXiv cs.AI

STAIF: A Stage-wise Optimization for Complex Instruction Following

STAIF is a stage-wise optimization framework that decouples soft constraint alignment from hard constraint verification for complex instruction following.

AI/ML arXiv cs.AI

ARdena: Scenario-driven control of real-time LLM agents

ARDena provides a framework for real-time control of multimodal LLM agents using scenario-driven structured prompting to modify behavior at runtime.

AI/ML arXiv cs.AI

KG2Code: Bridging Knowledge Graphs and Large Language Models via Executable Code for Question Answering

KG2Code transforms knowledge graphs into executable code representations to reduce hallucinations and improve question answering in LLMs.

AI/ML arXiv cs.AI

Do Language Models Converge to Themselves? Recursive Self-Refinement as Textual Relaxation

A study on recursive self-refinement in LLMs, finding that text converges to a model-preferred fixed-point rather than improving indefinitely.

AI/ML Hacker News

Banning AI will not make it go away

A discussion on why banning AI is an ineffective strategy for controlling its development and proliferation.

Other Hacker News

Leeaky Catches hidden fees draining your travel budget

An exploration of hidden fees in travel budgeting and how they can drain consumer funds.

Software Engineering Hacker News

Type checker may be wrong – Lean and the Curry-Howard correspondence

A technical discussion regarding the Lean theorem prover and the implications of the Curry-Howard correspondence on type checking.

Other Ars Technica

Reaction wheel failures leave Swift rescue mission spinning in orbit

A rescue mission is experiencing orbital instability due to the failure of two of its three reaction wheels.

Other Ars Technica

College lab class ends with 32 people on antibiotics for deadly germ exposure

A college lab class resulted in widespread antibiotic treatment for students after they were exposed to a deadly pathogen.