MoA Reference Models Are Not Told They Are References

Bug tracker — July 7, 2026. Hermes bug #60272 exposes a basic design omission in Mixture of Agents: reference models get the full conversation context, but they are never explicitly told they are plaintext-only reference models. As a result, they try to use tools, those tool calls fail, and the aggregate model inherits polluted context from the failure.

The Design Gap in One Sentence

Hermes asks reference models to help solve the task, but never tells them the rules of their role. The reference model behaves like a full agent, attempts tool calls, and then the aggregate model reasons over failure output that never should have existed.

Expected vs Actual Behavior

ModeExpectedActual
Reference modelProvide reasoning and plain-text input for the aggregate modelAttempts file edits or other tool calls because it is never told not to
Aggregate modelIssue the real tool calls after synthesizing referencesReceives contaminated context that assumes reference-side tool actions were meaningful

Why This Is More Than a Cosmetic Prompt Bug

Reporter's Proposed Role Prompt

You are operating as a reference model in a Mixture-of-Agents (MoA) configuration; you are able to reason about the conversation, but you cannot issue tool calls. Everything you output is handled as plaintext by the hermes-agent harness.

The elegance of this proposal is that it addresses the design gap at the prompt layer while keeping the reference output plain-text for downstream synthesis. The reporter also suggests filtering the instruction back out before feeding consolidated reference output to the aggregate model.

The MoA Subsystem Cluster Emerging on July 7

IssueFailure ModeWhy It Matters
#60272Reference models are unaware of their role and issue tool callsRole confusion pollutes aggregate context
#60345Reference models silently disappear on context overflowReference loss is hidden from the user
#60084Tool-loop guardrails missing for reference modelsReference-side control boundaries are under-specified

Together, these issues show that MoA shipped with multiple missing control surfaces: role-awareness, context protection, and reference-specific guardrails.

Why This Is Strong Review-Site Material

Flagship features matter most when they fail at the subsystem-design level. #60272 is not a superficial glitch. It suggests Hermes built MoA without clearly defining the contract for a reference model. When the architecture does not tell a component what it is allowed to do, failure is not accidental — it is structural. For a review site comparing managed and local agent stacks, that is exactly the kind of signal that belongs on record.

Case Summary

Source URL: https://github.com/NousResearch/hermes-agent/issues/60272