Solvent: Long-Horizon Reasoning for Multi-Step Retrosynthesis

arXiv cs.AI Papers
retrosynthesis llm-reasoning reinforcement-learning chemistry long-horizon-planning post-training

Summary

Researchers introduce Solvent, an 8B LLM that extends long-horizon reasoning to multi-step retrosynthesis through a two-round post-training curriculum combining RL and iterative route revision, achieving 61.86% across four benchmarks and rivaling frontier trillion-parameter models.

arXiv:2610.32308v1 Announce Type: new Abstract: Multi-step retrosynthesis requires recursively transforming a target molecule through successive reaction steps into purchasable building blocks, and recent work has begun to draw on large language model (LLM) reasoning to tackle the task. In its latest evolution, LLM reasoning has entered the long-horizon regime: models pursue objectives across interdependent steps, interact with environments, and adapt to feedback. This shift has markedly advanced LLM capabilities, as illustrated by breakthroughs in AI-driven mathematical research. At this frontier, we introduce Solvent, an 8B LLM that successfully extends long-horizon reasoning to multi-step retrosynthesis. Through a two-round post-training curriculum, Solvent learns to interleave iterative synthesis planning, external availability verification, and adaptive route revision. Experiments show that, following a $2.1\times$ performance boost from RL, Solvent scores 61.86% across four benchmarks, surpassing mid-scale language models and prior search-based retrosynthesis systems, and rivaling frontier trillion-parameter LLMs.
Original Article

Similar Articles

NVIDIA's Cosmos Framework (6 minute read)

TLDR AI

NVIDIA introduces Cosmos Framework, an open, modular platform for training, post-training, optimizing, and deploying world foundation models for physical AI, covering RL pipelines like DPO, GRPO, PPO, and serving via Cosmos NIM microservices.

GPU-accelerated Weight Teleportation (17 minute read)

TLDR AI

A technical write-up introduces GPU-accelerated Weight Teleportation, a Blackwell-native delta weight sync pipeline that brings sampler pause time below 0.23s and end-to-end weight sync below 4s for large-scale RL, beating intra-cluster P2P RDMA for most workloads.