ManyIH and ManyIH-Bench address instruction conflicts in LLM agents with up to 12 privilege levels across 853 tasks, revealing frontier models achieve only ~40% accuracy.
Jailbreak distillation: Renewable safety benchmarking
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
GraphRAG-IRL fuses graph-grounded MaxEnt IRL pre-ranking with persona-guided LLM re-ranking to deliver up to 16.8% NDCG@10 gains over IRL-only baselines on MovieLens and consistent 4-6% gains on KuaiRand.
citing papers explorer
-
Many-Tier Instruction Hierarchy in LLM Agents
ManyIH and ManyIH-Bench address instruction conflicts in LLM agents with up to 12 privilege levels across 853 tasks, revealing frontier models achieve only ~40% accuracy.
-
GraphRAG-IRL: Personalized Recommendation with Graph-Grounded Inverse Reinforcement Learning and LLM Re-ranking
GraphRAG-IRL fuses graph-grounded MaxEnt IRL pre-ranking with persona-guided LLM re-ranking to deliver up to 16.8% NDCG@10 gains over IRL-only baselines on MovieLens and consistent 4-6% gains on KuaiRand.