Google agrees to buy 100% of the initial output from the Steel River Energy Center's 1.6GW solar project in Arkansas when it becomes operational in 2029 (Martha Muir/Financial Times) news:techmeme
Mistral AI Releases Robostral Navigate: An 8B Model Enabling Robots to Navigate Complex Environments Using a Single RGB Camera aiml:marktechpost
Show HN: ZenStack – access control at the ORM layer, built for coding agents news:hacker-news-(show-hn)
Show HN: Themis – Self-hosted AI code reviews with your own keys and models news:hacker-news-(show-hn)
Researchers detail "context bombing", where defenders use prompt injections to trigger guardrails of attackers' LLMs, cutting AI hacking success rates by ~90% (Dan Goodin/Ars Technica) news:techmeme
Microsoft Maps Year-Long ShinyHunters-Linked Salesforce Data Theft Across Three Paths news:the-hacker-news
Show HN: Rqshc – A C++/x64 assembly image compressor with its own RQI format news:hacker-news-(show-hn)
OpenAI's Ad Business Is on Pace to Miss Its Own Forecast by 90%, Analyst Says news:hacker-news-(front-page)
Sources: Nvidia intensified due diligence and cut its authorized AI chip customers in Singapore, Malaysia, and Japan by 50%+ to prevent China diversions (Zijing Wu/Financial Times) news:techmeme
QwenPaw-Data: Bridging Facts, Methodology, and Execution for Autonomous Enterprise Data Analytics academia:arxiv-cs.ai
SPARK: Susceptibility-Guided Profiling and Steering of Latent Reasoning States in Large Language Models academia:arxiv-cs.ai
Toward Contemplative LLM: A Modular Framework for Evaluating and Enhancing LLM Alignment in Mental Health academia:arxiv-cs.ai
A Formal Hierarchical Architecture for Agentic Orchestration with Stack-Based Execution and Lazy Discovery academia:arxiv-cs.ai
SCALECUA: Scaling Computer Use Agents with Verifiable Task Synthesis and Efficient Online RL academia:arxiv-cs.ai
The Verifier is the Curriculum: Execution-Gated Self-Distillation for Cross-Family Game Generation academia:arxiv-cs.ai
PHITSBench: an execution-scored benchmark for AI-assisted PHITS radiation-transport input generation using natural language academia:arxiv-cs.ai
Agents Don't Just Agree, They Remember: Benchmarking Persistent Sycophancy in Stateful Personal Agents academia:arxiv-cs.ai
Agentic-DPO: From Imitation to Agentic Policy Optimization on Expert Trajectories academia:arxiv-cs.ai
MAG: A Web-Agent Benchmark and Harness for Multimodal Action and Guide Generation academia:arxiv-cs.ai
From ambiguous utterances to governed reuse classes: canonicalization, quotient invariance, and conditional decidability academia:arxiv-cs.ai
YUKTI: From Natural-Language Situations to Robust, Verifiable Decisions An Uncertainty-Typed Proposition IR, Assumption-Robust Pareto Frontiers, and a Regret Certificate academia:arxiv-cs.ai
Dynamic Agent Skills: A Lifecycle Survey and Taxonomy of Evolving Skill Libraries academia:arxiv-cs.ai
First-Order Modal Logic in HOL: Deep and Shallow Embeddings with Automated Faithfulness (Extended Preprint) academia:arxiv-cs.ai
Cross-Layer Misalignment Detection in Agent Skills: A Progressive Loading-Aware Contrastive Learning Approach academia:arxiv-cs.ai
Route, Communicate, and Reason: Gated Routing and Adaptive Depth for Efficient Multi-Agent Reasoning academia:arxiv-cs.ai
Verifier-Guided Twelve-Tone Composition: A Generate-Verify-Repair Harness for Symbolic Music Generation academia:arxiv-cs.ai
Reverse Engineering Compliance: A Dual-Graph Verification Framework for Auditing Legacy IT Security Concepts academia:arxiv-cs.ai
LegalFarePlan: A Label-Setting Framework for Fare-Transparent Urban Rail Route Planning under Non-Additive Fare Rules academia:arxiv-cs.ai
Incremental Transformer for Surrogate-Based Inverse Design of Geopolymer Mixtures academia:arxiv-cs.ai
Opti-Agent-Bench: Benchmarking End-to-End Optimization R&D Agents on Real-World Business Problems academia:arxiv-cs.ai
NVAITC AI Scientist: A Governed End-to-End Research System -- A Hypertension GWAS Case Study academia:arxiv-cs.ai
The Hidden Footprint: Making Storage a First-Class Metric for LLM Agent Evaluation academia:arxiv-cs.ai
Scaffolding the Strategist: Architecture-Dependent Reasoning Interventions in Hotelling Spatial Markets academia:arxiv-cs.ai
Semantic Drift and the Stability of Operator Control in Reasoning-Class Decision Support Systems academia:arxiv-cs.ai
Comparing Socio-technical Design Principles with Guidelines for Human-centered AI academia:arxiv-cs.ai
How Much Does Correctness Cost? Budgeted Placement of Strong Correctors in a Weak Multi-Agent Swarm academia:arxiv-cs.ai
Embark Now: User Demand Oriented Framework for Multi-day Urban Travel Itinerary Planning academia:arxiv-cs.ai
Measure the Sim-to-Real Gap: Designing an Affordable Real-World Benchmark Platform for Reinforcement Learning in AIoT Systems academia:arxiv-cs.ai
CRiT-QA: Evaluating Multi-hop Reasoning with Counterfactual Chains and Distractor Traps academia:arxiv-cs.ai
GRATE: Temporal Extensions for Inductive KG Foundation Models via Gated Rotary Attention academia:arxiv-cs.ai
Personalized Emotional Intelligence in Generative AI through Symbolic Affective Reasoning academia:arxiv-cs.ai
Faithful, Not Corrective: Message-Format Effects in Multi-Hop Agent Relays Are Tier-Dependent academia:arxiv-cs.ai
Norm Enforcement for AI Agents: Robustly Shaping Behavior in Multi-Agent Systems academia:arxiv-cs.ai
MRUF: Multi-granularity Routing with Uncertainty-Aware Fusion for Robust Multimodal Sentiment Analysis academia:arxiv-cs.ai
Constraint-Aware Hierarchical Search for Regulation-Driven Fine-Grained Classification academia:arxiv-cs.ai