Structured communication improves auditability in agent alpha discovery
VST: Verifiable Structured Transport for Auditable Agent-to-Agent Alpha Discovery
Artificial Intelligence
Summary
Finding valuable patterns between software agents can be slow because their communication is usually unstructured and hard to verify or replay. The authors designed a system where these agents talk using well-defined, typed messages that can be checked for correctness and repeated exactly as before. This structured approach doesn't necessarily make predictions more accurate, but it ensures the process is transparent and auditable, reducing errors and cheating. Their method performed well compared to others in testing, though all methods struggled to beat the benchmark. They emphasize that more work is needed to isolate the unique benefits of their system.
agent-to-agent communicationstructured protocoltyped messagescausal trajectorypredictor modeltransactional controlauditabilityalpha discoverySharpe ratioreplayability
Authors
Yuqi Li, Siyuan Liu, Bingjun Liu
Abstract
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.