AI news this week: 31 source-linked stories
A dated list of 31 AI stories with links to their original sources.
Stories published this week, linked to their original sources. The underlying claims have not been independently verified.
Plan-and-Patch: Diffusion Language Models for Agentic Planning
Plan-and-
Agent-Controlled Forgetting for Tool-Using Agents: Reversible Context Curation in Practice
Tool-using agents repeatedly carry observations whose useful content can be much smaller than their original payload.
An Explainable Header-Centric Framework for Large-Scale Semantic Table Interpretation and Data Quality Assessment
Knowledge Graph (KG) quality depends not only on downstream graph validation, but also on the quality of tabular metadata used before integration.
The Harness as the Only Mutable Surface: Compliance-Bounded Self-Evolution of LLM Agents in Credit Pipelines, with a Measured Admission Gate
Self-improving LLM agents can adapt a credit pipeline to a changed rule, but an agent that rewrites itself destroys the artefact a supervisor reviews: a named change, a recorded test, an approval.
Speaking the Navigator’s Language: Trajectory-Grounded Instruction Translation for Frozen Aerial VLN Agents
Aerial vision-and-language navigation (VLN) agents are typically trained on detail-rich, trajectory-aligned commands, whereas users issue short, intent-driven instructions; on a frozen OpenFly navigator, this \emph{instruction gap} drops success rate (SR) from $31.03\%$ to $11.33\%$.
Whose Ground Truth? Embracing Ambiguity in Human-Centered AI
As AI systems increasingly interact with people and make decisions about them, understanding human interpretations becomes an important part of developing human-centered AI.
Synthesis Through Simulation: Generating Coherent Enterprise Data via Scalable Agent-System Interaction
Tool-calling agents have become central to enterprise AI, yet training and evaluating them at scale remains severely constrained due to business and legal restrictions on enterprise systems, data, and database schemas.
Verification and Self-Improvement in Agentic AI: Foundations and Limits
Agentic
EPOCH: Reliable Discovery through Evidence-Governed Search
AI research agents are increasingly used to search over programs, mathematical constructions, and proofs.
Into the Omniverse: How Developers Turn Ideas Into Simulations With Frontier AI Agents
Turning a simulation idea into a working application means assembling assets, connecting physics and rendering, and checking that the scene behaves as intended.
Offline AI Modules: Voice-First Offline Architecture, Hardware Reference Stack, Quantization and Benchmarking
The Offline AI Modules workstream enables practical, low-power, and community-accessible deployment of voice-first AI systems that operate fully offline.
Topology-Consistent Task Planning over Cellular Workflow Complexes for LLM-based Agents
Task planning for LLM agents requires workflows that satisfy both user intent and complex sub-task dependencies.
When to Rethink: Learning Multi-Perspective Self-Verification for Vision-Language Models
Vision-language models (
Smart Content Ingestion for Generative AI Workloads
The evolution of machine learning has progressively changed where intelligence resides in an AI system.
Beyond Refusal Patterns: Safe-Role Internalization for Robust and Generalizable LLM Safety Alignment
Large Language Models (LLMs) have achieved remarkable capabilities but remain vulnerable to jailbreak attacks that elicit harmful or unsafe outputs.
CuratorMAS: Automating Dataset Curation via Multi-Agent Orchestration
CuratorMAS
Principles that Guide, Actions that Inform: Agent Evolution via Knowledge Abstraction
Large language model
Introducing Claude Haiku 5.5
Our fastest, cheapest, and most capable small model yet.
GAMEGO: Training Game-Dev Agents with Synthetic Trajectories Anchored in Real-World Assets
Recent advances in Large Language Models (LLMs) have demonstrated remarkable capabilities in web front-end execution, with browser-based game generation emerging as a particularly prominent frontier.
AegisFlow: A Multi-Agent Agentic AI Framework for Autonomous Remediation and Self-Healing in Fragile Data Ecosystems
Traditional data pipelines are notoriously brittle, often failing due to upstream schema drift, API contract changes, or website DOM modifications.
RadOnc-Agent: An LLM-Orchestrated Framework for AI Workflows Across the Radiotherapy Care Pathway
Artificial intelligence has advanced individual radiotherapy tasks, yet these capabilities remain separated across clinical stages, software environments and data modalities.
Metonymic Circuits for Abstract Concept Grounding in Vision Transformers
We study how Vision Transformers ground abstract concepts (e.g., angry) when training data provide limited direct referential evidence.
NVIDIA, Microsoft Kick Off a New Beginning for Windows PCs With RTX Spark and AI Agents
At a
FluidPD: In-Place Elasticity for SLO-Aware Prefill-Decode Disaggregated LLM Serving
Prefill-decode disaggregation is becoming a common architecture for LLM serving because it separates two phases with distinct execution patterns and SLO objectives.
Why Telecom Operators Are Building Their AI Strategy on Open Models
Telecom operators are
Choosing Before Acting: Comparative Value Estimation for Long-Horizon Tool-Use Agents
Large language models (
From Scan to Treatment Plan, AI Helps Close Breast Cancer’s Deadliest Gaps
Breast cancer is the most
The AI Risk Observatory: What Can We Learn from AI Disclosures in Annual Reports About Societal Resilience?
Societal resilience research relies on access to useful and actionable data, which motivates our main research question: Can annual reports, processed at scale with LLMs, provide a useful signal about how companies disclose their response to AI?
DeReAct: Decomposed Reasoning and Acting for Reliable AI Agents
DeRe
World Editing: Intervening on Executable Worlds at Increasing Depth
Interactive world models are increasingly capable of generating environments and acting within them, yet deliberately editing an existing executable world remains underexplored.
Fast Models, Slow Evidence: A Paired and Self-Audited Evaluation of System-1 Decision Models for LLM Agent Harnesses
Agent harnesses make many small, typed decisions per task: which model to call, which tool to use, whether retrieved text is relevant, whether an input carries an injection.