R103 · Agent principles and patterns › Harness building blocks

EvoTrias: separation of powers for agentic program evolution

Read the original

self-improvementcoding-agentsevaluationcostagent-architecture

Source: Zhengyang Ai, Tong Liu, Jingxian Tang, Xiaobing Du, Tao Xiao, Fengshi Zhang, Zishuo Li, Xiaodong Ai, Pinyan Lu, "Where Autonomy Belongs: A Separation of Powers for Agentic Program Evolution", arXiv:2611.15309, submitted 2026-11-11 (58 pages), arXiv. Surfaced on LinkedIn by Pascal Biese, 2026-11-16.

The problem

LLM-driven program evolution (the AlphaEvolve family) loops: produce a candidate program, score it, build on the best. The paper names three decisions every such system makes:

Existing systems split into two camps. Controller-centric systems keep govern in a fixed algorithm and use a model call only to propose, which caps how ambitious each candidate can be. Agent-centric systems hand a coding agent (such as Claude Code) both govern and propose, which is costly and lets the agent see, and drift toward, how it is graded. Neither protects the judge.

Architecture

Each decision gets exactly one owner, and owners talk only through typed contracts, with runtime hooks enforcing the boundaries:

  1. Structured Governance spans rounds: a controller picks parents and directions from accumulated scores.

  2. Open Proposal works inside a round: a full coding agent writes and repairs the next version, with freedom to edit a real repository.

  3. Protected Judgment sits behind a private evaluator the agent cannot open or modify.

Because the split is clean, EvoTrias ships as a plug-in that turns an existing coding agent (Claude Code or OpenCode, per the post) into an evolution system.

Results (as reported)

Why it matters beyond program evolution

The lesson generalises to any agent loop with a metric: give the agent autonomy where creativity pays (writing code), keep search strategy in cheap deterministic code, and make the evaluator unreadable and unwritable by the agent. The best agent here was the one trusted with the fewest decisions.

Tradeoffs

Failure modes to watch

Review checklist for an optimise-against-a-metric agent loop

Connections

See R103 on the knowledge map

Part of the Research notes on nowucca.com. Figures and claims are the source's own unless the summary says otherwise.