pith. sign in

Hipo: Instruction hierarchy via constrained reinforcement learning

2 Pith papers cite this work. Polarity classification is still indexing.

2 Pith papers citing it

fields

cs.CR 1 cs.LG 1

years

2026 2

verdicts

UNVERDICTED 2

representative citing papers

Security Considerations for Multi-agent Systems

cs.CR · 2026-03-09 · unverdicted · novelty 6.0

No existing AI security framework covers a majority of the 193 identified multi-agent system threats in any category, with OWASP Agentic Security Initiative achieving the highest overall coverage at 65.3%.

citing papers explorer

Showing 2 of 2 citing papers.

  • Detector-Evasive LLM Paraphrasing via Constrained Policy Optimization cs.LG · 2026-05-29 · unverdicted · none · ref 34

    DEPO formulates detector-evasive paraphrasing as a constrained MDP and solves it via Lagrangian primal-dual RL with GRPO-style updates to achieve evasion while satisfying a semantic-preservation constraint.

  • Security Considerations for Multi-agent Systems cs.CR · 2026-03-09 · unverdicted · none · ref 152

    No existing AI security framework covers a majority of the 193 identified multi-agent system threats in any category, with OWASP Agentic Security Initiative achieving the highest overall coverage at 65.3%.