{"slug": "retroagent-harnessing-llms-to-search-over-structured-memory-for-agentic-planning", "title": "RetroAgent: Harnessing LLMs to Search Over Structured Memory for Agentic Retrosynthesis Planning", "summary": "Researchers introduced RetroAgent, an LLM agent that combines symbolic search with neural reasoning for multi-step retrosynthesis planning in chemistry. The agent uses structured memory and chemistry tools to observe the full search state, enabling informed decisions that improve performance and generalization on both in-distribution and out-of-distribution benchmarks.", "body_md": "arXiv:2607.14512v1 Announce Type: new\nAbstract: 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.", "url": "https://wpnews.pro/news/retroagent-harnessing-llms-to-search-over-structured-memory-for-agentic-planning", "canonical_source": "https://www.machinebrief.com/news/retroagent-harnessing-llms-to-search-over-structured-memory-wd4m", "published_at": "2026-07-17 04:00:00+00:00", "updated_at": "2026-07-17 05:02:42.643388+00:00", "lang": "en", "topics": ["artificial-intelligence", "large-language-models", "ai-agents", "ai-research"], "entities": ["RetroAgent"], "alternates": {"html": "https://wpnews.pro/news/retroagent-harnessing-llms-to-search-over-structured-memory-for-agentic-planning", "markdown": "https://wpnews.pro/news/retroagent-harnessing-llms-to-search-over-structured-memory-for-agentic-planning.md", "text": "https://wpnews.pro/news/retroagent-harnessing-llms-to-search-over-structured-memory-for-agentic-planning.txt", "jsonld": "https://wpnews.pro/news/retroagent-harnessing-llms-to-search-over-structured-memory-for-agentic-planning.jsonld"}}