A privacy model for agentic negotiation
Barkha Rani · hf · 2026-07-21
This paper studies a subtler privacy problem in negotiation agents: even if private constraints are never explicitly revealed, an adversary can infer them from concession timing, trajectories, and convergence patterns. The authors formalize this as behavioral privacy leakage and propose an adaptive stochastic negotiation policy that aims to guarantee $(\varepsilon, \delta)$-differential privacy, almost-sure convergence when agreement is possible, and strong utility. On 3,000 synthetic bilateral negotiations, the mechanism cuts adversarial inference accuracy by 43–50% while keeping success rate and utility above 90%.
More from Research
- Draft paper uses Markov-chain eigenfunctions to build partitions and speed up sampling — michaelchchoi · 2026-07-21
- Autoresearch proposes packaging ML runs as studies with questions, analysis, and code diffs — morgymcg · 2026-07-21
- GitHub repo adds lightweight ternary QAT for Prism-ML Bonsai models — terminoid_ · 2026-07-21
- Qdrant co-hosts a Munich meetup on search, retrieval, and agentic RAG on July 23 — qdrant_engine · 2026-07-21
- GigaChat Audio targets long-form audio grounding with timestamps across 120-minute inputs — ai-sage · 2026-07-21
- Paper models Transformer components as stochastic geometry and tests five architectures — Zhihua Liang · 2026-07-21