VST：用于可审计的智能体间Alpha发现的可验证结构化传输

中文摘要 AI 辅助

智能体间（A2A）的Alpha发现过程因挖掘智能体与评估智能体之间反复的反馈循环而变得缓慢，在当代LLM多智能体系统中，这些交接是自由形式的自然语言消息，不携带稳定契约且无法重放。我们首先将这种通信重构为一种结构化的智能体间协议，采用类型化、因果可寻址、单播的记录形式，使得提交的流形成因果轨迹。在该轨迹上，一个具有四个类型化头的单一预测器预测两个挖掘智能体在几个周期后将收到的累积指导；随后，一个事务性的验证-跳跃控制器仅在通过四级门控时提交多周期推测性结果，否则回滚到精确的先前状态。结构是促成性贡献，其价值不在于准确性。受控消融实验表明，同等信息的自由文本通道达到相同的预测器命中率。类型化提供的是可进行模式检查、确定性重放并通过构造防止向评估者泄露预测的状态：通过构造实现可审计性，而非经验压力测试的保证。在CSI 1000样本外留存集上，我们的单次运行是八种方法（七个基线和我们的方法）中唯一在因子层面保持正的中位数年化收益率和夏普比率的方法，尽管所有方法（包括我们的）的中位数超额收益仍为负；其开发选择的前20投资组合在优化周期内的分割上选择，达到0.71的中位数留存夏普比率。我们描述性地报告这些单次运行结果，未扣除成本，并始终明确其局限性；特别是我们未将跳跃机制的效果与继承的搜索基底分离，这留待未来工作。

英文摘要

Agent-to-agent (A2A) alpha discovery is slowed by repeated feedback cycles between mining and evaluation agents, whose hand-offs, in contemporary LLM multi-agent systems, are free-form natural-language messages that carry no stable contract and cannot be replayed. We first restructure this communication as a structured agent-to-agent protocol of \emph{typed, causally addressable, unicast records}, so that the committed stream forms a causal trajectory. On that trajectory a single predictor with four typed heads forecasts the accumulated guidance the two miners would receive several cycles ahead; a transactional verify--leap controller then commits a multi-cycle speculative outcome only when it passes a four-level gate, and otherwise rolls back to the exact prior state. Structure is the enabling contribution, and its value is not accuracy. A controlled ablation shows an equal-information free-text channel reaches the same predictor hit rate. What typing provides is a state that can be schema-checked, replayed deterministically, and prevented by construction from leaking a forecast to an evaluator: auditability by construction, not an empirically stress-tested guarantee. On a CSI~1000 out-of-sample holdout, our single run is the only one among eight methods (seven baselines and ours) to hold a positive median annualized return and Sharpe at the factor level, though the median return \emph{in excess} of the benchmark stays negative for every method including ours; its development-selected top-20 portfolios reach a $0.71$ median holdout Sharpe, selected on a split inside the optimization horizon. We report these single-run results descriptively, gross of costs, and are explicit about their limits throughout; in particular we do not isolate the effect of the leap machinery from the inherited search substrate, which we leave to future work.

发表机构

• Panda AI（熊猫人工智能）

机构由 AI 辅助整理，请以论文原文为准。