information-flow-control

Tag

Cards List
#information-flow-control

AgentGFM: A Graph Foundation Model with Node-Agent Information-Flow Control

arXiv cs.LG · 2026-07-30 Cached

AgentGFM proposes a graph foundation model where each node acts as an agent with a shared trainable policy, enabling adaptive information-flow control through a predict–act–observe–correct process. It achieves strong performance across node-level, graph-level, and large-scale transfer tasks.

0 favorites 0 likes
#information-flow-control

@yunwei37: Several recent papers, including https://arxiv.org/html/2606.25189v1…, give the feeling that I am no longer designing and writing a system or paper, but rather "training" a system: empirical research collects a large amount of real-world scenario data as a training set, and based on this data, let AI analyze what properties the system should have and how to design and implement it; then I write a set of test cases to verify whether it works...

X AI KOLs Timeline · 2026-06-27 Cached

This paper presents ActPlane, a policy engine that enforces safety and effectiveness policies for AI agents at the OS kernel level using eBPF, bridging the semantic gap between natural language policy intent and concrete system actions.

0 favorites 0 likes
#information-flow-control

The Misattribution Gap: When Memory Poisoning Looks Like Model Failure in Agentic AI Systems

arXiv cs.AI · 2026-05-25 Cached

This paper identifies a structural failure in multi-agent AI pipelines where memory-layer attacks can be misattributed as model misalignment, formalizing Semantic Norm Drift (SND) and proposing Counterfactual Composition Testing and Memory-Persistent Information-Flow Control as defenses.

0 favorites 0 likes
← Back to home

Submit Feedback