Oracle-Budgeted Molecular Optimization with Short-Term Graph Memory

• URL: http://arxiv.org/abs/2607.28437v1
• Date: Thu, 30 Jul 2026 16:13:02 GMT
• Title: Oracle-Budgeted Molecular Optimization with Short-Term Graph Memory
• Abstract summary: We introduce short-term graph memory, a plug-in module that preserves the generator architecture and native update rule.<n>The module maintains an online graph neural surrogate that pre-screens each round's candidate pool.<n>It improves the mean top-10 score at no extra oracle cost and never falls behind the base on any oracle.
• Score: 13.101703587509641
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Molecular optimization is commonly performed under a limited oracle budget, which makes deciding what to evaluate as important as deciding what to generate. We introduce short-term graph memory, a plug-in module that preserves the generator architecture and native update rule while learning from previously evaluated molecules to prioritize subsequent oracle queries. The module maintains an online graph neural surrogate that pre-screens each round's candidate pool, so the fixed oracle budget is spent on molecules with higher predicted utility. Applied to a fragment-based generator on a standard molecular optimization benchmark, it improves the mean top-10 score at no extra oracle cost and never falls behind the base on any oracle; the gain extends to all four generators we tested at a tight budget of one thousand calls. We then analyze how surrogate-guided selection interacts with the exploration and exploitation behavior of different generators. Its benefit at larger budgets is consistent with two properties of the backbone: how broadly it searches, and how effectively its native search already exploits oracle feedback. We provide a simple way to spend a fixed oracle budget more selectively, and evidence on which generators benefit from it.

Related papers

• SkillLift: Learning Dense Rubrics from Sparse Oracles for Efficient Skill Evolution [2.429897021787139]
  LLM-based agents increasingly rely on persistent skills, i.e., reusable procedural prompts, to adapt without weight updates.<n>Existing skill self-evolution methods directly revise skill text based on execution feedback, but each oracle evaluation requires a full agent rollout.<n>We propose SkillLift, which decouples skill search from oracle cost by learning an oracle-aligned rubric as a structured evaluation space.<n> Experiments on complex agent task benchmarks show that our method outperforms existing auto-skill methods with 40--70% less token cost compared to frontier evolving methods.
  arXiv  Detail & Related papers  (2026-09-14T11:30:23Z)
• The Optimizer Is the Agent: Reasoning-Driven Search across Prompts, Programs, and ML Workflows [72.9051182568928]
  We present ReASearch, a unified framework for reasoning-driven optimization.<n>With a shared agent loop and domain-specific tools, ReASearch instantiates the exact same scaffold to optimize prompts, programs, and ML.<n>We observe that complex search behaviors emerge naturally from the agent's reasoning process.
  arXiv  Detail & Related papers  (2026-08-07T02:15:39Z)
• CADAQUES: A Cost-Aware Dual Architecture for Query-Efficient Autonomous Discovery [0.0]
  CADAQUES is a first-class primitive of the discovery loop built on one architectural principle.<n>It charges both evaluations and decisions against a common vector-valued budget spanning wall time, CPU hours, monetary cost, and language model tokens.<n>We evaluate the architecture by locating the critical temperature of the two-dimensional Ising model from noisy finite-size estimates.
  arXiv  Detail & Related papers  (2026-07-17T17:04:20Z)
• On the Design Space of Discrete Diffusion Online Adaptation for Molecular Optimization [55.27368653669229]
  Molecular optimization often starts from a pretrained generative model that captures a broad prior over valid molecular structures.<n>We study this adaptation problem for discrete diffusion models.<n>We find that acquisition, reward shaping, and model debiasing provide complementary routes to higher reward, especially for small molecules.
  arXiv  Detail & Related papers  (2026-07-03T00:06:31Z)
• Surrogate-Gated Generation and Foundation-Model Embeddings for Bayesian Materials Design [0.7500610196128554]
  We show that a cheap probabilistic surrogate can triage the generator's output, and what such a surrogate must do well.<n>A cross-factorial benchmark of surrogate performance spanning mechanical, electronic, and vibrational properties identifies pretrained ORB embeddings with a Gaussian process as the most reliable combination.<n>The complete pipeline is released as open-source software.
  arXiv  Detail & Related papers  (2026-06-26T20:10:01Z)
• MolMem: Memory-Augmented Agentic Reinforcement Learning for Sample-Efficient Molecular Optimization [30.982324843158057]
  MolMem is a multi-turn agentic reinforcement learning framework with a dual-memory system.<n>Uses Static Exemplar Memory to retrieve relevant exemplars for cold-start grounding, and Evolving Skill Memory to distill successful trajectories into reusable strategies.
  arXiv  Detail & Related papers  (2026-04-14T03:24:26Z)
• Neural Nonmyopic Bayesian Optimization in Dynamic Cost Settings [73.44599934855067]
  LookaHES is a nonmyopic BO framework designed for dynamic, history-dependent cost environments.<n>LookaHES combines a multi-step variant of $H$-Entropy Search with pathwise sampling and neural policy optimization.<n>Our innovation is the integration of neural policies, including large language models, to effectively navigate structured, domain-specific action spaces.
  arXiv  Detail & Related papers  (2026-01-10T09:49:45Z)
• Oracle-Efficient Combinatorial Semi-Bandits [38.838934613131535]
  We study the semi-bandit problem where an agent selects a subset of base arms and receives individual feedback.<n>We propose oracle-efficient frameworks that significantly reduce oracle calls while maintaining tight regret guarantees.
  arXiv  Detail & Related papers  (2025-10-24T13:07:08Z)
• CryptOracle: A Modular Framework to Characterize Fully Homomorphic Encryption [3.5348336893819554]
  This paper presents a detailed characterization of OpenFHE, a comprehensive open-source library for FHE.<n>We introduce CryptOracle, a modular evaluation framework comprising (1) a benchmark suite, (2) a hardware profiler, and (3) a predictive performance model.
  arXiv  Detail & Related papers  (2025-10-03T23:30:29Z)
• ALGO: Synthesizing Algorithmic Programs with LLM-Generated Oracle Verifiers [60.6418431624873]
  Large language models (LLMs) excel at implementing code from functionality descriptions but struggle with algorithmic problems. We propose ALGO, a framework that synthesizes Algorithmic programs with LLM-Generated Oracles to guide the generation and verify their correctness. Experiments show that when equipped with ALGO, we achieve an 8x better one-submission pass rate over the Codex model and a 2.6x better one-submission pass rate over CodeT.
  arXiv  Detail & Related papers  (2023-05-24T00:10:15Z)
• Controllable Text Generation with Neurally-Decomposed Oracle [91.18959622763055]
  We propose a framework to control auto-regressive generation models with NeurAlly-Decomposed Oracle (NADO) We present a closed-form optimal solution to incorporate the token-level guidance into the base model for controllable generation.
  arXiv  Detail & Related papers  (2022-05-27T20:17:53Z)
• Adapting to Misspecification in Contextual Bandits [82.55565343668246]
  We introduce a new family of oracle-efficient algorithms for $varepsilon$-misspecified contextual bandits. We obtain the first algorithm that achieves the optimal $O(dsqrtT + varepsilonsqrtdT)$ regret bound for unknown misspecification level.
  arXiv  Detail & Related papers  (2021-07-12T21:30:41Z)

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.