EvoUndo：面向LLM Agent框架的可恢復性約束自我演化

摘要

LLM 智能體日益在執行期間自我修改提示詞、工具、中介軟體、資源與執行框架。此類自我演化雖可提升能力，但成功的變異可能留下持久效應，而這些效應在與其創建時不同的狀態下無法安全復原。我們提出 EvoUndo，一個用於表示、合成、診斷並獨立驗證模型生成之自我修改在跨反事實狀態下可恢復性的框架。在 600 項未見過的單次自我演化任務中，我們識別出 197 個提升能力但未能通過可恢復性驗證的變異。在原始恢復表示下，傳統修復策略對這 197 個自然失敗案例的恢復數為 0/197。確定性預言機分析在原始恢復語言 L0 下恢復 48/197，而擴展恢復演算將經驗預言機恢復提升至 191/197。隨後，一項協議鎖定的 2×2 接地×表達力干預區分出兩個瓶頸：在原始語言足夠時，精確狀態位址接地將成功恢復從 0/48 提升至 38/48（79.2%），而擴展恢復語言使預言機定義之 S1 層級中的 142/143（99.3%）失敗案例得以恢復。在主要 gpt-oss-120b 主幹模型上，向更豐富語言加入精確位址診斷會使恢復率降至 133/143（93.0%）；Qwen3.8-27B 重現實驗保留了接地與表達力效應，但未保留此負面交互作用，表明後者具有模型依賴性。這些結果表明，可靠的智能體自我演化需要共同設計驗證、狀態接地、見證語意與恢復語言表達力，而非僅依賴迭代提示。

English

LLM agents increasingly modify their own prompts, tools, middleware, resources, and execution harnesses at runtime. Such self-evolution can improve capability, but a successful mutation may leave persistent effects that cannot be safely reversed in states different from the one in which it was created. We introduce EvoUndo, a framework for representing, synthesizing, diagnosing, and independently verifying recoverability of model-generated self-modifications across counterfactual states. Across 600 unseen one-shot self-evolution tasks, we identify 197 capability-improving mutations that fail recoverability verification. Under the original recovery representation, conventional repair strategies recover 0/197 of these natural failures. Deterministic oracle analysis recovers 48/197 under the original recovery language L0, while the extended recovery calculus increases empirical oracle recovery to 191/197. A protocol-locked 2x2 grounding-by-expressivity intervention then separates two bottlenecks: exact state-address grounding increases successful recovery from 0/48 to 38/48 (79.2%) when the original language is sufficient, while extending the recovery language enables recovery on 142/143 (99.3%) failures in the oracle-defined S1 stratum. On the primary gpt-oss-120b backbone, adding exact-address diagnostics to the richer language reduces recovery to 133/143 (93.0%); a Qwen3.8-27B replication preserves the grounding and expressivity effects but not this negative interaction, indicating that the latter is model-dependent. These results indicate that reliable agent self-evolution requires co-designing verification, state grounding, witness semantics, and recovery-language expressivity rather than relying on iterative prompting alone.