Pith. sign in

AgentPoison : Red-teaming LLM agents via poisoning memory or knowledge bases

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it

fields

cs.LG 1

years

2026 1

verdicts

CONDITIONAL 1

representative citing papers

Persistent Semantic Entities in Tool-Augmented LLM Systems

cs.LG · 2026-08-08 · conditional · novelty 5.0

Tool-augmented LLM agents retain injected preferences and instructions across many turns, while factual falsehoods are often corrected, and a name-binding registry is the main entry point.

citing papers explorer

Showing 1 of 1 citing paper.

  • Persistent Semantic Entities in Tool-Augmented LLM Systems cs.LG · 2026-08-08 · conditional · none · ref 4

    Tool-augmented LLM agents retain injected preferences and instructions across many turns, while factual falsehoods are often corrected, and a name-binding registry is the main entry point.