GAIA：一种面向 LLM-人类 B2B 谈判与筛选的通用代理交互架构
GAIA: A General Agency Interaction Architecture for LLM-Human B2B Negotiation & Screening
AI总结：
本文提出治理优先的 GAIA 框架，通过信息门控推进、双重反馈整合和授权边界三种机制，规范 LLM 智能体在 B2B 谈判与筛选中的委托行为，实现安全、高效且可问责的人机协作。
摘要：
各类组织正日益探索将筛选和谈判任务委托给 AI 系统，但在高风险的 B2B 场景中部署仍受到治理约束：防止未经授权的承诺、确保在议价前获得充分信息，以及维持有效的人类监督和可审计性。此前关于大语言模型谈判的研究主要强调智能体之间的自主议价，而忽略了分阶段信息收集、明确授权边界和系统性反馈整合等实际需求。我们提出 GAIA，一个面向 B2B 谈判与筛选中 LLM-人类代理关系的治理优先框架。GAIA 定义了三个基本角色——委托人（人类）、受托人（LLM 智能体）和交易对手——并设置可选的批评者（Critic）以提升性能，同时通过三种机制组织交互：将筛选与谈判分离的信息门控推进机制；将 AI 批评与轻量级人工纠正相结合的双重反馈整合机制；以及带有明确升级路径的授权边界机制。我们的贡献有四个方面：（1）一个正式治理框架，包含三种协同机制和四个安全不变量，用于在有限授权下进行委托；（2）通过任务完备性跟踪（TCI）和显式状态转换实现信息门控推进，将筛选与承诺分离；（3）双重反馈整合，通过并行学习通道将批评者建议与人类监督相融合；（4）一个混合验证蓝图，将自动化协议指标与人类对结果和安全性的判断相结合。通过连接理论与实践，GAIA 为安全、高效且可问责的 AI 委托提供了一种可复现的规范，可在采购、房地产和人员配置等工作流程中实例化。
英文摘要：
Organizations are increasingly exploring delegation of screening and negotiation tasks to AI systems, yet deployment in high-stakes B2B settings is constrained by governance: preventing unauthorized commitments, ensuring sufficient information before bargaining, and maintaining effective human oversight and auditability. Prior work on large language model negotiation largely emphasizes autonomous bargaining between agents and omits practical needs such as staged information gathering, explicit authorization boundaries, and systematic feedback integration. We propose GAIA, a governance-first framework for LLM-human agency in B2B negotiation and screening. GAIA defines three essential roles - Principal (human), Delegate (LLM agent), and Counterparty - with an optional Critic to enhance performance, and organizes interactions through three mechanisms: information-gated progression that separates screening from negotiation; dual feedback integration that combines AI critique with lightweight human corrections; and authorization boundaries with explicit escalation paths. Our contributions are fourfold: (1) a formal governance framework with three coordinated mechanisms and four safety invariants for delegation with bounded authorization; (2) information-gated progression via task-completeness tracking (TCI) and explicit state transitions that separate screening from commitment; (3) dual feedback integration that blends Critic suggestions with human oversight through parallel learning channels; and (4) a hybrid validation blueprint that combines automated protocol metrics with human judgment of outcomes and safety. By bridging theory and practice, GAIA offers a reproducible specification for safe, efficient, and accountable AI delegation that can be instantiated across procurement, real estate, and staffing workflows.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
