#agent-ai News & Analysis

7 articles tagged with #agent-ai. AI-curated summaries with sentiment analysis and key takeaways from 50+ sources.

7 articles

AINeutralarXiv – CS AI · 4d ago7/10

🧠

AgentRiskBOM: A Risk-Scoping Security Bill of Materials for Agentic AI Systems

Researchers introduce AgentRiskBOM, a security framework that documents the capabilities and risk exposure of autonomous AI agents by tracking their access to tools, data, credentials, and external services. The framework significantly outperforms existing bill-of-materials standards (SBOM, AIBOM, MLBOM) in identifying agentic security risks, exposing 100% of risk-category visibility compared to 10.5% for traditional approaches.

AIBullisharXiv – CS AI · Jun 57/10

🧠

Unsupervised Skill Discovery for Agentic Data Analysis

Researchers introduce DataCOPE, an unsupervised framework that enables AI agents to discover and refine data-analysis skills without labeled training data. By using verification signals from exploration trajectories, the system improves agent performance by 9.71% on report-style tasks and 32.30% on reasoning-style tasks, offering a practical approach to enhance analytical AI without costly manual supervision.

AI × CryptoBullishcrypto.news · May 277/10

🤖

Robinhood opens door for AI agents as crypto trading plans loom

Robinhood has launched Agentic Trading and Agentic Credit Card services that enable users to connect AI agents directly to their trading and spending accounts on the platform. This move represents a significant expansion of AI integration in retail finance and signals growing institutional acceptance of autonomous agents managing financial assets.

AIBullisharXiv – CS AI · May 117/10

🧠

SOD: Step-wise On-policy Distillation for Small Language Model Agents

Researchers introduce SOD (Step-wise On-policy Distillation), a framework that improves small language models' ability to use tools and reason through complex tasks by adaptively controlling how much they learn from larger teacher models at each step. The approach achieves up to 20.86% improvement over existing methods and demonstrates that a 0.6B parameter model can reach 26.13% accuracy on AIME 2025, a significant benchmark for mathematical reasoning.

AINeutralarXiv – CS AI · Jun 196/10

🧠

Execution-bound advisory automation for agentic AI: a reproducible AIBOM-driven CSAF-VEX framework

Researchers present a framework that combines software bill of materials (SBOM) and AI bill of materials (AIBOM) artifacts with runtime monitoring to generate cryptographically signed security advisories for AI systems. The approach evaluates vulnerability exploitability using static analysis and observed execution conditions across synthetic AI workloads, tested on approximately 10,000 component entries.

AIBullisharXiv – CS AI · Mar 36/103

🧠

Look Back to Reason Forward: Revisitable Memory for Long-Context LLM Agents

Researchers introduce ReMemR1, a new approach to improve large language models' ability to handle long-context question answering by integrating memory retrieval into the memory update process. The system enables non-linear reasoning through selective callback of historical memories and uses multi-level reward design to strengthen training.

AINeutralSimon Willison Blog · Jun 23/10

🧠

datasette-agent-micropython 0.1a0

datasette-agent-micropython 0.1a0 is an early-stage alpha release that integrates agent capabilities with MicroPython for embedded systems. This release enables AI-driven automation on resource-constrained devices, bridging datasette's data management with micropython's embedded computing ecosystem.