Multi agent federations improve identity and governance with new secure system
PRIMUS: Identity, Governance, and Verification for Multi-Agent Federations
Artificial Intelligence
Summary
When groups of agents or computers work together, it can be hard to know who joined, whether they followed the rules, and who is in charge. The authors introduce PRIMUS, a system that uses special codes and signatures to identify participants securely and reduce false punishments. They also explore how to judge the quality of group decisions more fairly, using signals beyond simple yes or no answers. Their tests show this approach works well on some puzzles and real AI outputs, though challenges remain. Overall, the work improves trust and decision-making in cooperative systems under difficult conditions.
multi agent federationprime power identityBLS aggregate signatureByzantine quorumverifiable random function (VRF)partial synchronyartifact fidelitybinary covering codesfault tolerancegovernance
Authors
Sasank Annapureddy, Anjaneya Prasad Thamatani
Abstract
Multi-agent federations need governance that answers three questions under adversarial conditions: who participated (identity), did they conform (enforcement), and who decides (authority). A separate question is whether the verification machinery that polices a federation's outputs can also steer a generate-and-test loop toward better answers. Part I. PRIMA introduced prime-power agent identity and a consensus token whose factorization indexes participation, but assumed honest agents. We present PRIMUS, which couples prime-power identity with BLS aggregate signatures (PIAC), derives a safe-kill threshold that reduces false-positive agent termination from 80% to 0.00% under 10% channel noise, gives the closed-form economic boundary where singleton governance outperforms Byzantine quorum ($γ^* \approx 9f$, verified flat across n = 50 to 10,000), and specifies VRF succession with lease and fencing that makes safety unconditional under partial synchrony. Five problems are identified as provably unfixable within the model and stated as scope boundaries. Part II. A verifier is not a solver. We ask whether PRIMA's binary artifact-fidelity verdict can be converted into a graded fitness signal, and measure the conversion on binary covering codes. Calibration against injected fault burden is strong ($ρ$ = 0.676 deterministic, 0.819 full); against real LLM-generated candidates the same scores fall to 0.158 and 0.406, roughly a quarter of the calibration value (the same-designer confound, measured). As a pre-filter it beats a random-score control convincingly and a binary gate narrowly. Under 400 iterations of explicit optimization it was not gamed, but only because the objective saturated after one honest answer. A cross-family judge preserves the burden-ordering signal while destroying individual judgments. No covering-code record resulted. Measured program cost: USD 164.78.