Online Surrogate Repair: Decoupling High-Fidelity Feedback from Search Length in Closed-Loop Discovery

• URL: http://arxiv.org/abs/2609.07655v1
• Date: Mon, 07 Sep 2026 15:42:45 GMT
• Title: Online Surrogate Repair: Decoupling High-Fidelity Feedback from Search Length in Closed-Loop Discovery
• Abstract summary: We propose emphonline surrogate repair (OSR), a closed-loop algorithm that uses sparse high-fidelity evaluations to update the surrogate throughout a longer agent search.<n>An acquisition rule selects which designs from the agent's accumulated proposals receive high-fidelity evaluation, and the resulting labels update the surrogate used in subsequent episodes.
• Score: 24.4458458394035
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: Closed-loop AI scientists can generate candidate designs at low marginal computational cost, whereas reliable feedback may require wet-lab synthesis, characterization, or high-fidelity computation. Addressing this imbalance through custom laboratory automation remains infrastructure-intensive and costly, while replacing new experiments with a fixed surrogate leaves persistent model errors that can be amplified by optimization. We propose \emph{online surrogate repair} (OSR), a closed-loop algorithm that uses sparse high-fidelity evaluations to update the surrogate throughout a longer agent search conducted primarily with inexpensive surrogate feedback. An acquisition rule selects which designs from the agent's accumulated proposals receive high-fidelity evaluation, and the resulting labels update the surrogate used in subsequent episodes. Across controlled synthetic environments, we demonstrate that improving global surrogate fit does not necessarily reduce maximum regret, whereas Q90-UCB and expected improvement (EI) substantially reduce regret by directing evaluations toward regions that determine the optimizer's decisions. On MADE, controls receiving high-fidelity feedback after every episode require $6.36$--$7.23\times$ more oracle queries to match Online EI under two LLM orchestrators and $10.27\times$ more under the non-LLM Chemeleon+MLIP workflow. Online surrogate repair introduces a novel third feedback regime between fixed-surrogate operation and high-fidelity feedback after every episode, separating the frequency of high-fidelity evaluation from the duration of the agent's search.

Related papers

• CAFE: Self-Improving Search Agents Need Co-Evolving Feedback [64.5257526832476]
  Outcome-supervised search agents learn when and how to retrieve evidence, but terminal rewards neither localize intermediate errors nor redirect an ongoing trajectory before those errors compound.<n>Treating corrective feedback as a learned in-trajectory intervention couples the two roles: the agent must decide when to request and use feedback, while the critic must infer useful corrections from outcome-confounded rollouts whose failure patterns shift as the agent improves.
  arXiv  Detail & Related papers  (2026-08-25T16:39:00Z)
• LLM-as-a-Verifier: A General-Purpose Verification Framework [74.40111651545979]
  We introduce LLM-as-a-Verifier, a general-purpose verification framework.<n>It provides fine-grained feedback for agentic tasks without requiring additional training.<n>It achieves state-of-the-art performance on several benchmarks.
  arXiv  Detail & Related papers  (2026-07-06T17:59:35Z)
• Closing the Reflection Gap: A Free Calibration Bonus for Agentic RL [12.234169944475537]
  RefGRPO is a simple yet effective fix that augments standard RL algorithms with two key ingredients.<n>A free calibration bonus computed by contrasting the agent's own reflection with the actual outcome.<n>The resulting reflection turns the agent into its own verifier grounded in environment feedback.
  arXiv  Detail & Related papers  (2026-06-12T07:47:15Z)
• Reinforced Agent: Inference-Time Feedback for Tool-Calling Agents [6.158612515104146]
  We introduce Helpfulness-Harmfulness metrics to measure the tradeoff between agent feedback and reviewer feedback.<n>We evaluate our approach on BFCL and Tau2-Bench (multi-turn stateful scenarios), achieving +5.5% on irrelevance detection and +7.1% on multi-turn tasks.<n>Our metrics reveal that reviewer model choice is critical: the reasoning model o3-mini achieves a 3:1 benefit-to-risk ratio versus 2.1:1 for GPT-4o.
  arXiv  Detail & Related papers  (2026-04-29T22:09:47Z)
• Frontier-Eng: Benchmarking Self-Evolving Agents on Real-World Engineering Tasks with Generative Optimization [16.92885982726064]
  We introduce Frontier-Eng, a human-verified benchmark for generative optimization.<n>Unlike previous suites, Frontier-Eng tasks are grounded in industrial-grade simulators and verifiers.<n>We evaluate eight frontier language models using representative search frameworks.
  arXiv  Detail & Related papers  (2026-04-14T05:02:06Z)
• Optimization-Embedded Active Multi-Fidelity Surrogate Learning for Multi-Condition Airfoil Shape Optimization [0.0]
  Active multi-fidelity surrogate modeling is developed for multi-condition airfoil shape optimization.<n>The framework couples a low-fidelity-informed Gaussian process regression transfer model with uncertainty-triggered sampling and a synchronized elitism rule.<n>The optimized design improves cruise efficiency by 41.05% and take-off lift by 20.75% relative to the best first-generation individual.
  arXiv  Detail & Related papers  (2026-03-17T18:43:11Z)
• RetroAgent: From Solving to Evolving via Retrospective Dual Intrinsic Feedback [54.39884046754265]
  RetroAgent is an online RL framework that enables agents to master complex interactive environments.<n>Our experiments show that RetroAgent achieves state-of-the-art (SOTA) performance.
  arXiv  Detail & Related papers  (2026-03-09T16:23:33Z)
• OPV: Outcome-based Process Verifier for Efficient Long Chain-of-Thought Verification [91.15649744496834]
  We propose the Outcome-based Process Verifier (OPV), which verifies the rationale process of summarized outcomes from long chains of thought.<n>OPV achieves new state-of-the-art results on our held-out OPV-Bench, outperforming much larger open-source models such as Qwen3-Max-Preview with an F1 score of 83.1 compared to 76.3.
  arXiv  Detail & Related papers  (2025-12-11T15:47:38Z)
• Long-horizon Reasoning Agent for Olympiad-Level Mathematical Problem Solving [65.02106674311908]
  This paper introduces Intern-S1-MO, a long-horizon math agent that conducts multi-round hierarchical reasoning.<n>By maintaining a compact memory in the form of lemmas, Intern-S1-MO can more freely explore the lemma-rich reasoning spaces.<n> Experiments show that Intern-S1-MO can obtain 26 out of 35 points on the non-geometry problems of IMO2025, matching the performance of silver medalists.
  arXiv  Detail & Related papers  (2025-12-11T15:26:28Z)
• A Survey of LLM-based Automated Program Repair: Taxonomies, Design Paradigms, and Applications [12.409034344742768]
  Large language models (LLMs) are reshaping automated program repair (APR)<n>We categorize the recent 63 LLM-based APR systems published from January 2022 to June 2025 into four paradigms.<n>This taxonomy clarifies key trade-offs: fine-tuning delivers strong task alignment at high training cost; prompting enables rapid deployment but is limited by prompt design and context windows.<n>We outline research directions that combine lightweight human feedback, repository-aware retrieval, code analysis, and cost-aware planning to advance reliable and efficient LLM-based APR.
  arXiv  Detail & Related papers  (2025-06-30T11:46:01Z)
• Supervised Optimism Correction: Be Confident When LLMs Are Sure [91.7459076316849]
  We establish a novel theoretical connection between supervised fine-tuning and offline reinforcement learning.<n>We show that the widely used beam search method suffers from unacceptable over-optimism.<n>We propose Supervised Optimism Correction, which introduces a simple yet effective auxiliary loss for token-level $Q$-value estimations.
  arXiv  Detail & Related papers  (2025-04-10T07:50:03Z)
• On the Role of Feedback in Test-Time Scaling of Agentic AI Workflows [71.92083784393418]
  Agentic AI (systems that autonomously plan and act) are becoming widespread, yet their task success rate on complex tasks remains low.<n>Inference-time alignment relies on three components: sampling, evaluation, and feedback.<n>We introduce Iterative Agent Decoding (IAD), a procedure that repeatedly inserts feedback extracted from different forms of critiques.
  arXiv  Detail & Related papers  (2025-04-02T17:40:47Z)

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.