Coding agents require a three-level proactivity taxonomy (Reactive, Scheduled, Situation Aware) evaluated by insight policy quality using Insight Decision Quality, Context Grounding Score, and Learning Lift.
Intent detection in the age of LLMs
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 1
other 1
citation-polarity summary
representative citing papers
A hybrid deterministic-plus-semantic interception layer for continuous task-based authorization of multi-turn LLM agent tool invocations, with new multi-turn datasets and initial experiments.
LLMs fail to detect hidden harmful intent, allowing systematic bypass of safety mechanisms through framing techniques, with reasoning modes often worsening the issue.
citing papers explorer
-
Agentic Coding Needs Proactivity, Not Just Autonomy
Coding agents require a three-level proactivity taxonomy (Reactive, Scheduled, Situation Aware) evaluated by insight policy quality using Insight Decision Quality, Context Grounding Score, and Learning Lift.
-
Hybrid Inspection and Task-Based Access Control in Zero-Trust Agentic AI
A hybrid deterministic-plus-semantic interception layer for continuous task-based authorization of multi-turn LLM agent tool invocations, with new multi-turn datasets and initial experiments.
-
Beyond Context: Large Language Models' Failure to Grasp Users' Intent
LLMs fail to detect hidden harmful intent, allowing systematic bypass of safety mechanisms through framing techniques, with reasoning modes often worsening the issue.