Search papers, labs, and topics across Lattice.
This paper introduces RetroAgent, an innovative LLM-based agent that integrates structured memory with symbolic search to enhance multi-step retrosynthesis planning in chemistry. By leveraging a comprehensive view of the search state鈥攊ncluding explored routes and properties of intermediates鈥擱etroAgent enables more informed decision-making compared to traditional methods that score candidates in isolation. Experimental results show that RetroAgent outperforms existing approaches, achieving superior performance and generalization on both in-distribution and out-of-distribution benchmarks.
RetroAgent revolutionizes retrosynthesis planning by combining LLMs with structured memory, leading to significantly improved decision-making in complex chemical searches.
Multi-step retrosynthesis planning seeks to decompose a target molecule into commercially available building blocks through a sequence of feasible reactions. The vast combinatorial search space makes this task challenging even for expert chemists. Traditional methods combine tree search with offline-trained value networks that score candidates in isolation, without reasoning about complete multi-step routes. Recent work leverages Large Language Models (LLMs) for this task, but relies on simple interfaces that limit exploration of the full search space. We introduce RetroAgent, an LLM agent that bridges symbolic search and neural reasoning through a harness with structured memory. Through memory and chemistry tools, the agent observes the full search state, including explored routes, available alternatives, and properties of intermediates, enabling informed decisions grounded in both global progress and domain knowledge. Experiments on in-distribution and out-of-distribution benchmarks demonstrate that RetroAgent delivers strong performance and generalization.
Amazon Science