AgentSentry: Defending Against Indirect Prompt Injection in Tool-Using Agents

Shared entity: AgentSentry / Same source / Shared topic / What happened next / Tension

AgentSentry — Temporal Causal Defense Against Prompt Injection

Both cover AgentSentry; cite the same source (arXiv 2602.22724); overlapping topics (against, agent, agentsentry, causal, indirect).

Shared entity: Directly / Same source domain / Shared topic / What happened next / Tension

SplitAgent: Privacy-Preserving Enterprise Agents

Both cover Directly; reported by the same outlet (arxiv.org); overlapping topics (agent, directly, execution).

Shared entity: Directly / Same source domain / Shared topic / What happened next

BAVT: Budget-Aware Value Tree Cuts Wasted Tool Calls.

Both cover Directly; reported by the same outlet (arxiv.org); overlapping topics (agent, applicable, call, directly).

New RL framework trains CLI agents under partial observability.

Both cover Directly; reported by the same outlet (arxiv.org); overlapping topics (agent, applicable, directly).

Cross-Agent Attack Detection via Semantic Flow Reconstruction

Both cover Directly; reported by the same outlet (arxiv.org); overlapping topics (anyone, directly, indirect).

Memory-R1: RL-Based Agent Memory Management

Both cover Directly; reported by the same outlet (arxiv.org); overlapping topics (agent, applicable, directly).

Codified Context: Infrastructure for AI Agents in Complex Codebases

Both cover Directly; reported by the same outlet (arxiv.org); overlapping topics (agent, context, directly).

PCAS: Compiler-Based Policy Enforcement for Agents (48% → 93% Compliance)

Both cover Directly; reported by the same outlet (arxiv.org); overlapping topics (agent, directly, execution).