Constraint-Aware Corrective Memory for Language-Based Drug Discovery Agents

2026-04-10

AI Summary

Current language model–driven drug discovery agents struggle to ensure that the entire set of candidate molecules collectively satisfies protocol-level constraints—such as quantity, diversity, binding affinity, and developability—leading to ambiguous failure causes and accumulated planning noise. This work proposes the CACM framework, which introduces, for the first time, a precise diagnosis and correction memory mechanism tailored to set-level constraints. By conducting protocol audits and leveraging multimodal evidence to pinpoint constraint violations, CACM generates actionable correction prompts and employs a three-channel memory system—static, dynamic, and corrective—to compress and update planning context in a compact, decision-relevant manner. Experiments demonstrate a 36.4% improvement in target-level success rate over state-of-the-art baselines, underscoring the critical role of precise diagnostic capability and economical agent state management in language-driven drug discovery.

Technology Category

• Constraint Satisfaction and Optimization: Constraint Learning and Acquisition
• Cognitive Modeling & Cognitive Systems: Computational Creativity
• Planning, Routing, and Scheduling: Planning with Language Models

Application Category

• Search and Retrieval-Augmented AI: Agentic search
• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

Large language models are making autonomous drug discovery agents increasingly feasible, but reliable success in this setting is not determined by any single action or molecule. It is determined by whether the final returned set jointly satisfies protocol-level requirements such as set size, diversity, binding quality, and developability. This creates a fundamental control problem: the agent plans step by step, while task validity is decided at the level of the whole candidate set. Existing language-based drug discovery systems therefore tend to rely on long raw history and under-specified self-reflection, making failure localization imprecise and planner-facing agent states increasingly noisy. We present CACM (Constraint-Aware Corrective Memory), a language-based drug discovery framework built around precise set-level diagnosis and a concise memory write-back mechanism. CACM introduces protocol auditing and a grounded diagnostician, which jointly analyze multimodal evidence spanning task requirements, pocket context, and candidate-set evidence to localize protocol violations, generate actionable remediation hints, and bias the next action toward the most relevant correction. To keep planning context compact, CACM organizes memory into static, dynamic, and corrective channels and compresses them before write-back, thereby preserving persistent task information while exposing only the most decision-relevant failures. Our experimental results show that CACM improves the target-level success rate by 36.4% over the state-of-the-art baseline. The results show that reliable language-based drug discovery benefits not only from more powerful molecular tools, but also from more precise diagnosis and more economical agent states.

Problem

• language-based drug discovery
• constraint satisfaction
• set-level validity
• protocol compliance
• autonomous agents

Innovation

• Constraint-Aware Corrective Memory
• protocol auditing
• set-level diagnosis
• memory compression
• language-based drug discovery