Probe Before You Edit: Probing-Guided Molecular Optimization for LLM Agents in Structure-Based Drug Design

• URL: http://arxiv.org/abs/2606.00555v2
• Date: Tue, 02 Jun 2026 07:09:41 GMT
• Title: Probe Before You Edit: Probing-Guided Molecular Optimization for LLM Agents in Structure-Based Drug Design
• Abstract summary: Two diagnostic metrics measure how often a single edit improves both objectives.<n>Applying these metrics to current LLM-agent pipelines exposes a consistent failure mode.<n>We propose textbfPROBE, an optimization framework built around edit-response probing.
• Score: 15.697564598284833
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Structure-based drug design increasingly employs LLM agents to iteratively refine ligands against a target pocket, yet a viable ligand must satisfy two often-conflicting objectives -- binding affinity and druggability -- which single optimization steps rarely improve together. To quantify this difficulty, we introduce two diagnostic metrics: the first measures how often a single edit improves both objectives, and the second measures how often a gain on one objective comes with a loss on the other. Applying these diagnostics to current LLM-agent pipelines exposes a consistent failure mode: the agent performs molecular editing without knowing how the pocket-ligand complex responds to local modifications, thus rarely achieving joint improvement. Inspired by medicinal chemists, who probe the pocket-ligand complex with controlled analog edits before choosing an optimization direction, we propose \textbf{PROBE}, an optimization framework built around edit-response probing. PROBE first decomposes the ligand into editable sites and builds a pocket-specific \textbf{site map} that flags where joint gains are plausible, where the two objectives are likely in tension, and where liability substructures should be changed; it then performs controlled probe edits whose responses are distilled into an \textbf{EditManual}. Guided by the site map and EditManual, PROBE runs an iterative multi-agent loop in which an affinity agent, a druggability agent, and a co-optimization agent jointly produce edits. On the CrossDocked2020 benchmark, PROBE achieves state-of-the-art performance and substantially mitigates the failure modes exposed by our diagnostics metrics.

Related papers

• PETA:Parameter-Efficient Test-Time Adaptation for Virtual Screening [49.976632553053285]
  We propose PETA, a parameter-efficient framework that directly adapts pretrained model at test time.<n>PETA constructs pocket-specific negatives through molecular diffusion and chemical validity filtering.<n>A ranking objective places greater emphasis on suppressing high-scoring invalid candidates that could contaminate the top-ranked screening results.
  arXiv  Detail & Related papers  (2026-08-20T11:17:27Z)
• IterInject: Indirect Prompt Injection Against LLM Agents via Feedback-Guided Iterative Optimization [33.58630045185762]
  Existing attacks rely on static payloads that cannot adapt to agent-specific defenses.<n>We introduce oursys, a feedback-guided iterative framework that closes the loop between injection, diagnosis, and diagnosis.<n>A step generates new disguise seeds from failure patterns, enabling the strategy space to self-evolve.
  arXiv  Detail & Related papers  (2026-05-23T17:00:06Z)
• From I/O to Code with Discovery Agent [103.88427301265669]
  We propose DIO-Agent, a discovery agent for IO2Code.<n>Our method frames IO2Code as an evolutionary search over discrete program space.<n>Extensive experiments show that DIO-Agent consistently outperforms both traditional program-by-example method and SOTA evolution-agent baselines.
  arXiv  Detail & Related papers  (2026-05-14T18:57:32Z)
• From Single-Step Edit Response to Multi-Step Molecular Optimization [9.685693410049495]
  Conditional molecular optimization aims to edit a molecule to realize a specified property shift.<n>In practice, structurally similar molecule data is scarce, while decisions are inherently action-level.<n>We propose a response-oriented discrete edit optimization approach comprising a single-step molecular edit response predictor and a multi-step planner.
  arXiv  Detail & Related papers  (2026-05-11T06:00:16Z)
• AdaExplore: Failure-Driven Adaptation and Diversity-Preserving Search for Efficient Kernel Generation [59.964989458924585]
  AdaExplore is an agent framework that enables self-improvement via accumulated execution feedback for performance-critical kernel code generation.<n>In the adaptation stage, the agent synthesizes tasks and converts recurring failures into a reusable memory of validity rules.<n>In the search stage, the agent organizes candidate kernels as a tree and alternates between small local refinements and larger structural regeneration.
  arXiv  Detail & Related papers  (2026-04-17T18:25:03Z)
• The Anatomy of an Edit: Mechanism-Guided Activation Steering for Knowledge Editing [52.315369633116255]
  Large language models (LLMs) are increasingly used as knowledge bases, but keeping them up to date requires targeted knowledge editing (KE)<n>We take a mechanistic view of KE using neuron-level knowledge attribution (NLKA)<n>Across representative KE methods, we find a consistent pattern: mid-to-late attention predominantly promotes the new target, while attention and FFN modules cooperate to suppress the original fact.<n>Motivated by these findings, we propose MEGA, a MEchanism-Guided Activation steering method that performs attention-residual interventions in attribution-aligned regions.
  arXiv  Detail & Related papers  (2026-03-21T12:40:15Z)
• MetaKE: Meta-learning Aligned Knowledge Editing via Bi-level Optimization [11.430206422495829]
  State-of-the-art methods suffer from an open-loop control mismatch.<n>We identify a critical "Semantic-Execution Disconnect"<n>We propose MetaKE, a new framework that reframes KE as a bi-level optimization problem.
  arXiv  Detail & Related papers  (2026-03-13T05:47:00Z)
• Coder as Editor: Code-driven Interpretable Molecular Optimization [36.84386817559159]
  We introduce MECo, a framework that bridges reasoning and execution by translating editing actions into executable code.<n>Our approach achieves over 98% accuracy in reproducing held-out realistic edits from chemical reactions and target-specific compound pairs.
  arXiv  Detail & Related papers  (2025-10-16T08:55:06Z)
• Metacognitive Self-Correction for Multi-Agent System via Prototype-Guided Next-Execution Reconstruction [58.51530390018909]
  Large Language Model based multi-agent systems excel at collaborative problem solving but remain brittle to cascading errors.<n>We present MASC, a metacognitive framework that endows MAS with real-time, unsupervised, step-level error detection and self-correction.
  arXiv  Detail & Related papers  (2025-10-16T05:35:37Z)
• MedREK: Retrieval-Based Editing for Medical LLMs with Key-Aware Prompts [70.64143198545031]
  We propose MedREK, a retrieval-based editing framework that integrates a shared query-key module for precise matching with an attention-based prompt encoder for informative guidance.<n>Our results on various medical benchmarks demonstrate that our MedREK achieves superior performance across different core metrics.
  arXiv  Detail & Related papers  (2025-10-15T12:50:33Z)
• An Auditable Agent Platform For Automated Molecular Optimisation [0.0]
  Drug discovery frequently loses momentum when data, expertise, and tools are scattered.<n>To shorten this loop we built a hierarchical, tool using agent framework that automates molecular optimisation.
  arXiv  Detail & Related papers  (2025-08-05T13:41:32Z)
• DrugImproverGPT: A Large Language Model for Drug Optimization with Fine-Tuning via Structured Policy Optimization [53.27954325490941]
  Finetuning a Large Language Model (LLM) is crucial for generating results towards specific objectives.<n>This research introduces a novel reinforcement learning algorithm to finetune a drug optimization LLM-based generative model.
  arXiv  Detail & Related papers  (2025-02-11T04:00:21Z)

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.