EvoUndo: Recoverability-Constrained Self-Evolution for LLM Agent Harnesses

• URL: http://arxiv.org/abs/2608.28363v1
• Date: Fri, 28 Aug 2026 14:15:36 GMT
• Title: EvoUndo: Recoverability-Constrained Self-Evolution for LLM Agent Harnesses
• Abstract summary: We introduce EvoUndo, a framework for representing, synthesizing, diagnosing, and independently verifying recoverability of model-generated self-modifications.<n>Across 600 unseen one-shot self-evolution tasks, we identify 197 capability-improving mutations that fail recoverability verification.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• TTSD-FAR: Test-Time Self-Distillation with Fisher-Anchored Restoration for Missing-Modality Emotion Recognition in LVLMs [83.78708832901194]
  Large video-language models (LVLMs) have shown remarkable performance on multimodal tasks like multimodal emotion recognition (ER) in the wild.<n>However, real-world deployment remains challenging: modalities may be missing or noisy at test time.<n>We propose a solution in which a frozen teacher guides an adaptive low-rank student via self-distillation.<n>Experiments on MELD, DFEW, and BAH under 0%-50% missing modalities show that this unified adaptation-restoration design consistently outperforms entropy-based adaptation, RAG, and perplexity-based generation.
  arXiv  Detail & Related papers  (2026-08-18T23:40:28Z)
• One Recipe, Many Harnesses: What Self-Evolution Encodes Across Languages and Models [46.83445434865936]
  Self-evolving harnesses are closed-loop systems in which an agent inspects its own rollouts and edits its prompts, tools, and memory.<n>It remains unclear whether they encode benchmark-specific adaptations, language-specific engineering knowledge, or compensation for limitations of the underlying model.
  arXiv  Detail & Related papers  (2026-08-10T19:45:45Z)
• From Failing to Passing: Evolving Natural Language Prompt Optimization Rules for LLM Code Generation [11.454560846406698]
  We introduce a search-based approach that identifies and evolves a set of natural language transformation rules.<n>We then proposeFIX, a staged repair pipeline that combines the evolved transformation rules with execution-feedback repair.<n>Our results show that DualFix recovers up to 30% of baseline failures and fixes 3-5 times more failing cases than Self-Fix.
  arXiv  Detail & Related papers  (2026-07-06T14:10:56Z)
• Conditional Co-Ablation: Recovering Self-Repair Backups in Transformer Circuits [47.668752416295185]
  Conditional Co-Ablation asks how much each remaining unit's ablation effect grows once a primary set has been removed.<n>On the GPT-2-small IOI circuit, CoAx raises backup-head recovery from 0.33 to 0.91 ROC-AUC.
  arXiv  Detail & Related papers  (2026-07-02T09:32:57Z)
• One Reflection Is Not Enough: Self-Correcting Autonomous Research via Multi-Hypothesis Failure Attribution [85.65263343588026]
  We propose SAGE, a Self-correcting, Autonomous, Grounded Experimenter.<n>Its core mechanism, Multi-Hypothesis Failure Attribution (MHFA), treats recovery as a structured causal diagnosis.<n>On a 12-topic, 5-domain benchmark, SAGE increases metrics-bearing outputs from 42% to 92% over a baseline reflection.
  arXiv  Detail & Related papers  (2026-06-30T10:54:16Z)
• ANNEAL: Adapting LLM Agents via Governed Symbolic Patch Learning [12.44509691077682]
  We introduce ANNEAL, a neuro-symbolic agent that converts recurring failures into governed symbolic edits of a process knowledge graph.<n>Its core mechanism, Failure-Driven Knowledge Acquisition (FDKA), localizes the responsible operator, synthesizes a typed patch through constrained LLM generation, and validates the proposal.<n>Across four domains and 27 multi-seed runs, ANNEAL is the only evaluated system that commits persistent structural repairs.
  arXiv  Detail & Related papers  (2026-05-04T05:24:03Z)
• Negation is Not Semantic: Diagnosing Dense Retrieval Failure Modes for Trade-offs in Contradiction-Aware Biomedical QA [1.0330395403064265]
  Large Language Models (LLMs) have demonstrated strong capabilities in question answering, yet their tendency to generate plausible but unverified claims poses serious risks in clinical settings.<n>To mitigate these risks, the TREC 2025 BioGen track mandates grounded answers that explicitly surface contradictory evidence.<n>We present a proxy-based development framework using the SciFact dataset to systematically optimize retrieval architectures.
  arXiv  Detail & Related papers  (2026-03-18T10:35:44Z)
• ReLoop: Structured Modeling and Behavioral Verification for Reliable LLM-Based Optimization [6.572539312871392]
  Large language models (LLMs) can translate natural language into optimization code, but silent failures pose a critical risk.<n>We introduce ReLoop, addressing silent failures from two complementary directions.
  arXiv  Detail & Related papers  (2026-02-17T20:20:33Z)
• ReForm: Reflective Autoformalization with Prospective Bounded Sequence Optimization [73.0780809974414]
  We propose a Reflective Autoformalization method that integrates semantic consistency evaluation into the autoformalization process.<n>This enables the model to iteratively generate formal statements, assess its semantic fidelity, and self-correct identified errors.<n>Experiments show that ReForm achieves an average improvement of 22.6 percentage points over the strongest baselines.
  arXiv  Detail & Related papers  (2025-10-28T16:22:54Z)
• Evolving LLMs' Self-Refinement Capability via Synergistic Training-Inference Optimization [53.93621974137829]
  Self-Refinement refers to a model's ability to revise its own responses to produce improved outputs.<n>EVOLVE is a framework for eliciting and tracking the evolution of Self-Refinement through iterative training.<n>We demonstrate the potential of leveraging Self-Refinement to achieve broader Self-Improvement of intrinsic model abilities.
  arXiv  Detail & Related papers  (2025-02-08T15:21:55Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.