EviGate: Evidence-Gated Inheritance for Self-Evolving Program-Repair Agents

Large language model agents can generate patches, execute tests, and reuse repair trajectories, making program repair a natural setting for studying agents that adapt from their own interaction histories. Yet passing the evidence available on one task does not establish a reliable improvement: additional rollouts help only when their outcomes can be selected correctly, while local lessons may overfit visible tests and cause regressions when inherited through memory or parameters. We introduce EviGate, an evidence-gated inheritance framework that treats self-evolution as a sequence of separately authorized state transitions. EviGate combines execution-grounded candidate selection, staged experience consolidation, and parameter adaptation whose proposed children are retained only after promotion, regression, and safety checks, with append-only lineage connecting every decision. On 100 seeds and 17 fixed EvoCodeGym tasks, uninformed three-candidate sampling adds only $+0.39/75$ private cases, whereas executable selection gains $+11.05$ (seed$\times$task 95% CI $[7.22,15.22]$). Memory, parameter, fresh-task, and repository-level evaluations further expose negative transfer and weak proposal coverage, establishing EviGate as an auditable inheritance protocol and empirical boundary map rather than a demonstration of repeated capability growth.