5
A Self-Evolving Agent for Longitudinal Personal Health Management
HealthClaw is a proposed self-evolving agent architecture designed to provide longitudinal health management by maintaining private memory of user routines and medical history.
5
When Bots Join the Team: Bot Adoption and the Institutional Fabric of Open-Source Software Projects
Researchers analyzed nearly 3,000 GitHub projects to understand how the integration of automated bots as active participants influences the organizational structure of open-source software teams.
5
How Far Can Root Cause Analysis Go on Real-World Telemetry Data?
A study evaluating root cause analysis in microservice failures reveals that current AI and classical methods struggle to effectively process large-scale, multimodal telemetry data.
5
Set-shifting Behavioral Test for Harnessed Agents
A new benchmark based on cognitive psychology tests has been developed to evaluate how AI agents adapt when the reliability of their tools changes during operation.
5
IMMNet: Hybrid Fusion of Model-based and Data-driven Approaches for Maneuvering Target Tracking
IMMNet integrates traditional model-based tracking algorithms with neural components to improve the accuracy and interpretability of maneuvering target tracking in 3D environments.
5
The SIGReg Objective as Variational Free Energy: A Theoretical Active-Inference Account of JEPA World Models
The paper provides a theoretical framework linking Joint-Embedding Predictive Architectures to active inference principles through variational free energy.
5
Experience Memory Graph: One-Shot Error Correction for Agents
A new error-correction method called Experience Memory Graph aims to help LLM agents recover from failures in long-horizon tasks more efficiently than traditional reflection techniques.
5
STOCKTAKE: Measuring the Gap Between Perception and Action in LLM Agents with a Fair Oracle
A new evaluation framework called STOCKTAKE aims to distinguish between perception errors and execution failures in LLM agents during long-term decision-making tasks.
5
Federated Explainable Artificial Intelligence: Roles, Architectures, Evaluation, and Open Challenges
This review examines the integration of explainable AI techniques within federated learning architectures to improve transparency in privacy-preserving distributed model training.
5
Interaction Protocol Shapes Moral Judgment in Multi-Agent Debate
A study demonstrates that the interaction protocols used in multi-agent debates significantly influence the moral reasoning and judgment outcomes of large language models.
5
Interventional Grounding Audits: Black-Box Premise-Dependency Tests for LLM Chain-of-Thought via Predicate Substitution
A new auditing method uses predicate substitution to test whether large language models genuinely rely on stated premises during chain-of-thought reasoning.
5
DIVE: Embedding Compression via Self-Limiting Gradient Updates
DIVE is a new dimensionality reduction technique for language model embeddings that uses self-limiting gradient updates to improve compression efficiency.
5
Infineon, LS Electric partner on DC power infrastructure for AI data centers
Infineon and LS Electric have signed a non-binding memorandum of understanding to jointly develop next-generation direct current power systems for AI data centers.
5
中信证券与光谷金控签署框架合作协议
CITIC Securities and Optics Valley Financial Holdings have entered a partnership to provide capital market services and investment support for emerging technology companies.
5
SpaceX in your index fund, explained
This article discusses the potential financial risks and market implications of including SpaceX in major index funds.
5
Building an agentic AI solution at Bluesight with Amazon Bedrock
Healthcare compliance company Bluesight has utilized Amazon Bedrock AgentCore to develop and deploy Prism, a unified agentic AI assistant.
5
Developer withdraws plan to replace hotel with data center in El Segundo, California
Developer Eight Form has withdrawn its proposal to replace a hotel with a data center in El Segundo, California, following public opposition during a planning meeting.
5
SPARK: Susceptibility-Guided Profiling and Steering of Latent Reasoning States in Large Language Models
The SPARK framework profiles and steers the latent reasoning states of large language models to diagnose and correct reasoning failures before final outputs are generated.
5
Partial Contracts Suffice: Sound, LLM-Inferred Regression Verification
Researchers have developed a contract-based regression verification tool that uses large language models to infer partial contracts, ensuring sound software patch verification without requiring manual specifications.
5
一汽解放J6E大客户定制版批量交付，挚途L2++智驾系统成“快递神车”技术杀手锏
FAW Jiefang has delivered customized trucks equipped with Zhitu Technology's L2++ autonomous driving system for logistics operations.
5
Why APEC 2026 Spotlight Turns to Chengdu: A Western Chinese City Digital Economy Transformation
Chengdu will host the APEC Digital and AI Ministerial Meeting in July 2026, showcasing its digital economy infrastructure and computing capacity.
5
中国稀土集团等在甘肃成立新公司
China Rare Earth Group has partnered with Gansu Guangsheng Rare Earth to establish a new joint venture focused on rare earth smelting and new material research.
5
高盛：AI或引爆美国通胀，存储暴涨是核心推手
Goldman Sachs reports that the AI boom could trigger a wave of inflation in the US, driven primarily by supply constraints and rising prices for memory chips and semiconductors.
5
NTT breaks ground on campus in Chonburi, Thailand
NTT has commenced construction on its new Bangkok 4 data center campus in Chonburi, Thailand, with operations expected to begin in 2027.