Self-Improvement Imitation with Biologically Guided Search for Protein Design Under Oracle Budgets

• URL: http://arxiv.org/abs/2605.26690v1
• Date: Tue, 26 May 2026 08:29:36 GMT
• Title: Self-Improvement Imitation with Biologically Guided Search for Protein Design Under Oracle Budgets
• Abstract summary: We introduce SILO, a trajectory-level self-improvement imitation framework for oracle-budgeted protein design.<n>SILO uses a hierarchical edit policy that decomposes each mutation into a position choice followed by a residue choice.<n>It achieves the highest maximum and top-100 mean fitness on 8 of 8 landscapes within our evaluations.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Protein sequence optimization under tight oracle budgets requires methods that explore vast combinatorial spaces while making each evaluation informative. Existing reinforcement learning and off-policy generative approaches often degrade under surrogate noise, and position-agnostic mutation proposals risk disrupting functionally critical residues. We introduce SILO, a trajectory-level self-improvement imitation framework for oracle-budgeted protein design. SILO uses a hierarchical edit policy that decomposes each mutation into a position choice followed by a residue choice. In each active-learning round, the policy samples candidate trajectories via incremental stochastic beam search without replacement (SBS), and a UCB-based proxy ensemble, combined with an alanine-scan fitness score (AFS), selects candidates with functionally relevant edits for in silico oracle evaluation. The policy is then updated by next-action cross-entropy imitation on the round's best oracle-labeled trajectories, avoiding value-function estimation. Across eight reproduced protein fitness landscapes and five strong baselines from prior work, SILO achieves the highest maximum and top-100 mean fitness on 8 of 8 landscapes within our evaluations, often exhibiting faster early-stage improvement. In low-data and noisy-proxy stress tests on two landscapes per setting, SILO remains competitive or best when several baselines degrade. Ablations show that SBS with AFS account for much of the gains, with iterative imitation providing additional improvement. Code is available at: https://github.com/grimmlab/SILO.git

Related papers

• SSPO: Structure-Aware Similarity-Weighted Preference Optimization for Neural Combinatorial Optimization [7.503926194234302]
  Preference-optimization methods anchor on the single best solution and discard fine-grained quality and structural signal from all other peers.<n>We propose SSPO (Structure-Aware Similarity-Weighted Preference Optimization), which scores all $B$ sampled solutions jointly through a dissimilarity-weighted leave-one-out baseline.
  arXiv  Detail & Related papers  (2026-08-12T16:04:54Z)
• Tail-Aware Adaptive-k: Query-Adaptive Context Selection for Retrieval-Augmented Generation [0.9786690381850356]
  We propose Tail-Aware Adaptive-k(TAA-k), a training-free framework that operationalizes Extreme Value Theory (EVT) through a localized validation strategy.<n>Under mild monotone likelihood ratio assumptions, TAA-k yields a stable, query-adaptive cutoff corresponding to the earliest noise-dominated position.<n>Experiments on WebQuestions, 2WikiMultiHopQA, and MuSiQue demonstrate that TAA-k achieves near-oracle retrieval quality (F1 within 2-3% of oracle) with orders-of-magnitude efficiency gains over global EVT methods.
  arXiv  Detail & Related papers  (2026-06-10T10:37:19Z)
• AgentPLM: Agentic Protein Language Models with Reasoning-Augmented Decoding for Protein Sequence Design [0.48342038441006796]
  Protein language models (PLMs) generate sequences in a single forward pass with no mechanism to consult external biophysical feedback or redirect generation.<n>We introduce AgentPLM, which addresses this by equipping a pre-trained PLM with i) Reasoning-Augmented Decoding (RAD), which interleaves autoregressive generation with tool calls.<n>We evaluate AgentPLM on benchmark tasks spanning de novo enzyme design, antibody optimisation, thermostability, PPI interface design, and zero-shot fitness prediction with standardised oracle APIs.
  arXiv  Detail & Related papers  (2026-06-01T15:35:02Z)
• Res$^2$CLIP: Few-Shot Generalist Anomaly Detection with Residual-to-Residual Alignment [21.61732087909472]
  Few-shot Generalist Anomaly Detection requires models to generalize to novel categories without retraining.<n>Existing CLIP-based methods face two major challenges: coarse-grained unified text prompts struggle to adapt to fine-grained foreground-background differences.<n>We propose to shift multimodal alignment entirely into a unified residual space, where residual representations naturally eliminate fine-grained normal feature differences.
  arXiv  Detail & Related papers  (2026-05-15T16:49:58Z)
• RASP-Tuner: Retrieval-Augmented Soft Prompts for Context-Aware Black-Box Optimization in Non-Stationary Environments [0.0]
  We present online tuning as context-conditioned regret minimization.<n>RASP-Tuner instantiates a decomposition motivated by first principles.<n>On nine synthetic non-stationary benchmarks, RASP-Tuner improves or matches cumulative regret relative to our GP-UCB and CMA-ES implementations.
  arXiv  Detail & Related papers  (2026-04-20T09:52:36Z)
• Label-Free Cross-Task LoRA Merging with Null-Space Compression [50.63908869296697]
  We introduce Null-Space Compression (NSC) Merging, a label-free, output-agnostic method that sets merge weights from adapter geometry.<n>NSC achieves state-of-the-art performance across twenty heterogeneous vision tasks with balanced gains where prior methods overfit subsets of tasks.
  arXiv  Detail & Related papers  (2026-03-27T11:34:41Z)
• Bayesian-guided inverse design of hyperelastic microstructures: Application to stochastic metamaterials [0.34376560669160394]
  Our aim is to identify a structure that achieves a target macroscopic stress response.<n>For each candidate design, the response is obtained from a high-fidelity oracle.<n>We propose a Bayesian-guided inverse design framework.
  arXiv  Detail & Related papers  (2026-03-16T21:09:57Z)
• Not All Preferences Are Created Equal: Stability-Aware and Gradient-Efficient Alignment for Reasoning Models [52.48582333951919]
  We propose a dynamic framework designed to enhance alignment reliability by maximizing the Signal-to-Noise Ratio of policy updates.<n>SAGE (Stability-Aware Gradient Efficiency) integrates a coarse-grained curriculum mechanism that refreshes candidate pools based on model competence.<n> Experiments on multiple mathematical reasoning benchmarks demonstrate that SAGE significantly accelerates convergence and outperforms static baselines.
  arXiv  Detail & Related papers  (2026-02-01T12:56:10Z)
• Coverage Improvement and Fast Convergence of On-policy Preference Learning [67.36750525893514]
  Online on-policy preference learning algorithms for language model alignment can significantly outperform their offline counterparts.<n>We analyze how the sampling policy's coverage evolves throughout on-policy training.<n>We develop principled on-policy schemes for reward distillation in the general function class setting.
  arXiv  Detail & Related papers  (2026-01-13T10:46:06Z)
• 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)
• AT$^2$PO: Agentic Turn-based Policy Optimization via Tree Search [19.443576967819684]
  LLM agents have emerged as powerful systems for tackling multi-turn tasks by interleaving internal reasoning and external tool interactions.<n>We present AT$2$PO, a unified framework for multi-turn agentic RL that addresses three core challenges: limited exploration diversity, sparse credit assignment, and misaligned policy optimization.
  arXiv  Detail & Related papers  (2026-01-08T09:35:49Z)
• Anchoring Values in Temporal and Group Dimensions for Flow Matching Model Alignment [61.80228667422234]
  VGPO redefines value estimation across both temporal and group dimensions.<n>It transforms the sparse terminal reward into dense, process-aware value estimates.<n>It replaces standard group normalization with a novel process enhanced by absolute values to maintain a stable optimization signal.
  arXiv  Detail & Related papers  (2025-12-13T16:31:26Z)
• ADARL: Adaptive Low-Rank Structures for Robust Policy Learning under Uncertainty [28.291179179647795]
  We propose textbfAdaptive Rank Representation (AdaRL), a bi-level optimization framework that improves robustness.<n>At the lower level, AdaRL performs policy optimization under fixed-rank constraints with dynamics sampled from a Wasserstein ball around a centroid model.<n>At the upper level, it adaptively adjusts the rank to balance the bias--variance trade-off, projecting policy parameters onto a low-rank manifold.
  arXiv  Detail & Related papers  (2025-10-13T20:05:34Z)
• ALoRE: Efficient Visual Adaptation via Aggregating Low Rank Experts [71.91042186338163]
  ALoRE is a novel PETL method that reuses the hypercomplex parameterized space constructed by Kronecker product to Aggregate Low Rank Experts.<n>Thanks to the artful design, ALoRE maintains negligible extra parameters and can be effortlessly merged into the frozen backbone.
  arXiv  Detail & Related papers  (2024-12-11T12:31:30Z)

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.