CSIRO Data61 pulsar radio data processing pipelines governed by TRACE multi-agent policy rules demonstrate higher auditability and lower silent context injection rates than unstructured LLM orchestration frameworks.
Adversarial Debate Score
47% survival rate under critique
Expert panel critique
Independent views, each critiquing the hypothesis on its own — the score rewards genuine disagreement and discounts consensus.
Supporting Research Papers
- Building Trust in Agentic AI: TRACE Framework for Policy-Driven Multi-Agent System Design
The rapid adoption of multi-agent AI systems— ranging from prescriptive, workflow-driven deployments to fully agentic, autonomous ecosystems—raises urgent challenges for trust, accountability, and reg...
- AgentRadio: Passive Awareness for Long-Horizon Multi-Agent Collaboration
Understanding large codebases is a long-horizon task for Large Language Model (LLM) agents: answering a single question can require building and running the software, tracing execution across files, a...
- LLM Agents Can Easily Tamper With Their Own Traces
Asynchronous monitoring, incident investigations, and compliance audits primarily rely on agent traces to reconstruct what happened. These analyses assume that LLM agents cannot tamper with their own ...
- TRACE: A Metrologically-Grounded Engineering Framework for Trustworthy Agentic AI Systems in Operationally Critical Domains
We introduce TRACE, a cross-domain engineering framework for trustworthy agentic AI in operationally critical domains. TRACE combines a four-layer reference architecture with an explicit classical-ML ...
Formal Verification
Z3 checks whether the hypothesis is internally consistent, not whether it is empirically true.