LARC: Towards Human-level Constrained Retrosynthesis Planning through an Agentic Framework

• URL: http://arxiv.org/abs/2508.11860v1
• Date: Sat, 16 Aug 2025 01:05:26 GMT
• Title: LARC: Towards Human-level Constrained Retrosynthesis Planning through an Agentic Framework
• Abstract summary: We present LARC, the first LLM-based Agentic framework for Retrosynthesis planning under Constraints.<n>LARC incorporates agentic constraint evaluation, through an Agent-as-a-Judge, directly into the retrosynthesis planning process.<n>We rigorously evaluate LARC on a carefully curated set of 48 constrained retrosynthesis planning tasks across 3 constraint types.
• Score: 11.438071610913163
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Large language model (LLM) agent evaluators leverage specialized tools to ground the rational decision-making of LLMs, making them well-suited to aid in scientific discoveries, such as constrained retrosynthesis planning. Constrained retrosynthesis planning is an essential, yet challenging, process within chemistry for identifying synthetic routes from commercially available starting materials to desired target molecules, subject to practical constraints. Here, we present LARC, the first LLM-based Agentic framework for Retrosynthesis planning under Constraints. LARC incorporates agentic constraint evaluation, through an Agent-as-a-Judge, directly into the retrosynthesis planning process, using agentic feedback grounded in tool-based reasoning to guide and constrain route generation. We rigorously evaluate LARC on a carefully curated set of 48 constrained retrosynthesis planning tasks across 3 constraint types. LARC achieves a 72.9% success rate on these tasks, vastly outperforming LLM baselines and approaching human expert-level success in substantially less time. The LARC framework is extensible, and serves as a first step towards an effective agentic tool or a co-scientist to human experts for constrained retrosynthesis.

Related papers

• From Atomic Actions to Standard Operating Procedures: Iterative Tool Optimization for Self-Evolving LLM Agents [90.3279207163486]
  EvoSOP is a framework that empowers agents to extract SOPs from execution trajectories and iteratively optimize the toolset.<n>We show that EvoSOP significantly boosts task success rates while substantially reducing the number of interaction rounds.
  arXiv  Detail & Related papers  (2026-07-08T12:09:49Z)
• URSA: Chemistry-Aware Benchmark for Utilitarian Retrosynthesis Assessment [3.6442441313881706]
  This study introduces the URSA (Utilitarian RetroSynthesis Assessment) evaluation framework.<n>It provides the opportunity to benchmark the synthetic routes not only from a formal perspective, but also from a chemical plausibility perspective.<n>The study covers a comprehensive evaluation of both conventional end-to-end retrosynthesis solutions and LLMs for the synthesis planning task.
  arXiv  Detail & Related papers  (2026-07-06T05:32:09Z)
• Agentic-Ideation: Sample Efficient Agentic Trajectories Synthesis for Scientific Ideation Agents [9.918296068965665]
  Ideation plays a pivotal role in scientific discovery.<n>Agentic-Ideation is a novel framework comprising an automated trajectory synthesis pipeline and a specialized agentic LLM trained for scientific ideation.
  arXiv  Detail & Related papers  (2026-06-30T07:07:51Z)
• A Machine-to-Machine Knowledge-Guided LLM Agent for Generalizable Radiotherapy Treatment Planning [1.1928873764689458]
  In this work, we propose a prototype machine-to-machine (M2M) knowledge-guided Large Language Model (LLM) framework for automated radiotherapy treatment planning.<n>In the proposed paradigm, Treatment Planning.<n>Model (TPP) distribution knowledge discovered by a Deep Reinforcement Learning (DRL) agent is transferred to an.<n>LLM agent through in-context learning, enabling autonomous iterative planning without human intervention.
  arXiv  Detail & Related papers  (2026-05-30T23:14:30Z)
• Understanding by Reconstruction: Reversing the Software Development Process for LLM Pretraining [66.89012795621349]
  Large Language Models (LLMs) often struggle with the deep, long-horizon reasoning required for complex software engineering.<n>We propose a novel paradigm: understanding via reconstruction.<n>We introduce a framework that synthesizes latent agentic trajectories using a multi-agent simulation.
  arXiv  Detail & Related papers  (2026-03-11T09:23:20Z)
• RAVEL: Reasoning Agents for Validating and Evaluating LLM Text Synthesis [78.32151470154422]
  We introduce RAVEL, an agentic framework that enables the testers to autonomously plan and execute typical synthesis operations.<n>We present C3EBench, a benchmark comprising 1,258 samples derived from professional human writings.<n>By augmenting RAVEL with SOTA LLMs as operators, we find that such agentic text synthesis is dominated by the LLM's reasoning capability.
  arXiv  Detail & Related papers  (2026-02-28T14:47:34Z)
• When Single Answer Is Not Enough: Rethinking Single-Step Retrosynthesis Benchmarks for LLMs [3.973137925060284]
  We propose a new benchmarking framework for single-step retrosynthesis.<n>By emphasizing plausibility over exact match, this approach better aligns with human synthesis planning practices.<n>We also introduce CREED, a novel dataset comprising millions of ChemCensor-validated reaction records for LLM training.
  arXiv  Detail & Related papers  (2026-02-03T14:03:32Z)
• Synthelite: Chemist-aligned and feasibility-aware synthesis planning with LLMs [3.7129661557601854]
  We introduce Synthelite, a synthesis planning framework that uses large language models to propose retrosynthetic transformations.<n> Synthelite can generate end-to-end synthesis routes by harnessing the intrinsic chemical knowledge and reasoning capabilities of LLMs.<n>Our experiments demonstrate that Synthelite can flexibly adapt its planning trajectory to diverse user-specified constraints, achieving up to 95% success rates.
  arXiv  Detail & Related papers  (2025-12-18T11:24:30Z)
• rSIM: Incentivizing Reasoning Capabilities of LLMs via Reinforced Strategy Injection [49.74493901036598]
  Large language models (LLMs) are post-trained through reinforcement learning (RL) to evolve into Reasoning Language Models (RLMs)<n>This paper proposes a novel reinforced strategy injection mechanism (rSIM) that enables any LLM to become an RLM by employing a small planner.<n> Experimental results show that rSIM enables Qwen2.5-0.5B to become an RLM and significantly outperform Qwen2.5-14B.
  arXiv  Detail & Related papers  (2025-12-09T06:55:39Z)
• AgentFrontier: Expanding the Capability Frontier of LLM Agents with ZPD-Guided Data Synthesis [69.06292316741126]
  Training large language model agents on tasks at the frontier of their capabilities is key to unlocking advanced reasoning.<n>We introduce a data synthesis approach inspired by the educational theory of the Zone of Proximal Development (ZPD)<n>We present the AgentFrontier Engine, an automated pipeline that synthesizes high-quality, multidisciplinary data situated precisely within the ZPD.
  arXiv  Detail & Related papers  (2025-10-28T17:50:47Z)
• Agentic Reinforced Policy Optimization [66.96989268893932]
  Large-scale reinforcement learning with verifiable rewards (RLVR) has demonstrated its effectiveness in harnessing the potential of large language models (LLMs) for single-turn reasoning tasks.<n>Current RL algorithms inadequately balance the models' intrinsic long-horizon reasoning capabilities and their proficiency in multi-turn tool interactions.<n>We propose Agentic Reinforced Policy Optimization (ARPO), a novel agentic RL algorithm tailored for training multi-turn LLM-based agents.
  arXiv  Detail & Related papers  (2025-07-26T07:53:11Z)
• DeepRetro: Retrosynthetic Pathway Discovery using Iterative LLM Reasoning [0.0]
  DeepRetro is an open-source, iterative, hybrid LLM-based retrosynthetic framework.<n>Our approach integrates the strengths of conventional template-based/Monte Carlo tree search tools with the generative power of LLMs in a step-wise, feedback-driven loop.<n>This approach successfully generates novel pathways for complex natural product compounds.
  arXiv  Detail & Related papers  (2025-07-07T19:41:39Z)
• Structured Program Synthesis using LLMs: Results and Insights from the IPARC Challenge [1.4591178662983573]
  The IPARC Challenge, inspired by ARC, provides controlled program synthesis tasks over synthetic images.<n>This paper presents a structured inductive programming approach with LLMs that successfully solves tasks across all IPARC categories.
  arXiv  Detail & Related papers  (2025-06-15T04:33:00Z)
• The Influence of Human-inspired Agentic Sophistication in LLM-driven Strategic Reasoners [3.5083201638203154]
  We evaluate the role of agentic sophistication in shaping artificial reasoners' performance.<n>We benchmarked three agent designs: a simple game-theoretic model, an unstructured LLM-as-agent model, and an LLM integrated into a traditional agentic framework.<n>Our analysis, covering over 2000 reasoning samples across 25 agent configurations, shows that human-inspired cognitive structures can enhance LLM agents' alignment with human strategic behaviour.
  arXiv  Detail & Related papers  (2025-05-14T13:51:24Z)
• LLM-Augmented Chemical Synthesis and Design Decision Programs [18.41721617026997]
  We introduce an efficient scheme for encoding reaction pathways and present a new route-level search strategy.<n>We show that our LLM-augmented approach excels at retrosynthesis planning and extends naturally to the broader challenge of synthesizable molecular design.
  arXiv  Detail & Related papers  (2025-05-11T15:43:00Z)
• Exploring the Necessity of Reasoning in LLM-based Agent Scenarios [74.35956310688164]
  We propose the LaRMA framework, encompassing nine tasks across Tool Usage, Plan Design, and Problem Solving.<n>Our findings address four research questions: LRMs surpass LLMs in reasoning-intensive tasks like Plan Design, leveraging iterative reflection for superior outcomes.<n>LRMs' enhanced reasoning incurs higher computational costs, prolonged processing, and behavioral challenges, including overthinking and fact-ignoring tendencies.
  arXiv  Detail & Related papers  (2025-03-14T04:34:31Z)
• Automated Retrosynthesis Planning of Macromolecules Using Large Language Models and Knowledge Graphs [11.191853171170516]
  We propose an agent system that integrates large language models (LLMs) and knowledge graphs.<n>Our system fully automates the retrieval of relevant literatures, extraction of reaction data, database querying, construction of retrosynthetic pathway trees.<n>This work represents the first attempt to develop a fully automated retrosynthesis planning agent tailored specially for macromolecules powered by LLMs.
  arXiv  Detail & Related papers  (2025-01-15T16:06:10Z)
• Towards Efficient LLM Grounding for Embodied Multi-Agent Collaboration [70.09561665520043]
  We propose a novel framework for multi-agent collaboration that introduces Reinforced Advantage feedback (ReAd) for efficient self-refinement of plans. We provide theoretical analysis by extending advantage-weighted regression in reinforcement learning to multi-agent systems. Experiments on Over-AI and a difficult variant of RoCoBench show that ReAd surpasses baselines in success rate, and also significantly decreases the interaction steps of agents.
  arXiv  Detail & Related papers  (2024-05-23T08:33:19Z)
• AdaPlanner: Adaptive Planning from Feedback with Language Models [56.367020818139665]
  Large language models (LLMs) have recently demonstrated the potential in acting as autonomous agents for sequential decision-making tasks. We propose a closed-loop approach, AdaPlanner, which allows the LLM agent to refine its self-generated plan adaptively in response to environmental feedback. To mitigate hallucination, we develop a code-style LLM prompt structure that facilitates plan generation across a variety of tasks, environments, and agent capabilities.
  arXiv  Detail & Related papers  (2023-05-26T05:52:27Z)

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.