The narration step in LLM-solver loops is vulnerable to prompt injection that inverts verified solver conclusions, and hardened prompts reduce but do not eliminate the risk under adaptive attacks.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
Finite trace observations induce the Cantor topology on infinite traces while simulation observations generate a finer topology, with a general theorem equating open sets to finitely verifiable properties.
citing papers explorer
-
Analyzing the Narration Gap in LLM-Solver Loops
The narration step in LLM-solver loops is vulnerable to prompt injection that inverts verified solver conclusions, and hardened prompts reduce but do not eliminate the risk under adaptive attacks.
-
A Topological Framework for Finite Behavioural Observations and Verification
Finite trace observations induce the Cantor topology on infinite traces while simulation observations generate a finer topology, with a general theorem equating open sets to finitely verifiable properties.