The study demonstrates that providing scientific performance feedback to generative models can shift their search distribution toward productive regions that lie outside conventional training data. In reactor lattice design and chemical reaction-condition selection, this adaptation improves performance and increases the generation of previously excluded choices. The results also show that the identified productive regions can be reused to enhance random search and that removing target penalties alters the direction of adaptation toward the scientific objective.
arXiv:2608.30952v1 Announce Type: new Abstract: Chemistry questions often demand exact computation and database lookups that a language model cannot supply from its parameters, so it must reach for e...
The study investigates whether large language models (LLMs) rely solely on their initial task context or adapt based on experimental feedback when selecting fine‑tuning configurations for neural operators. Experiments across partial differential equation families show that LLMs outperform random search and Bayesian optimisation, with early configurations already near the top of a random‑search pool and subsequent proposals changing in response to validation scores. Controlled interventions confirm that the LLM combines a task‑dependent prior with sensitivity to observed outcomes.
The paper introduces Conformal Interval-Driven Self-Evolution (CISE), a method that uses conditional conformal inference and online density-ratio estimation to create candidate‑specific reward intervals for self‑evolving search in materials science. CISE applies conservative interval‑based rewards, ensuring that only candidates whose required property intervals lie entirely within feasible regions are returned. Experiments on three self‑evolving search tasks show that all candidates returned by CISE are true positives under high‑fidelity evaluation, whereas baseline methods produce more candidates but include false positives.
Chemistry questions often demand exact computation and database lookups that a language model cannot supply from its parameters, so it must reach for external tools. Tool use here is a three-part prob...
arXiv:2607. 00531v1 Announce Type: cross Abstract: Scientific reasoning is an increasingly important capability of large language models, yet improving the robustness and efficiency of training such reasoning remains a key open challenge.
The paper proposes ANCHOR, a composition policy that decouples crystal structure prediction (CSP) from de novo crystal generation (DNG) by using a frozen CSP model as a fixed evaluator and training the policy with multi‑objective rewards, including adaptive novelty. ANCHOR significantly improves metrics such as MSUN and SUN compared to traditional DNG approaches, and demonstrates transferability across different CSP backbones and distillation into Crystalite‑CSP. The study shows that fine‑tuning DNG models directly on these rewards yields limited gains, whereas the ANCHOR framework better leverages the CSP prior for more efficient crystal discovery.
The paper presents an agentic retrobiosynthesis framework that uses a learned frontier selection policy to guide multistep retrosynthesis in a deterministic biochemical engine. By fine‑tuning a Qwen2.5‑7B policy with LoRA, the authors achieve higher solve rates than traditional MCTS across several benchmarks, demonstrating that route‑supervised frontier selection can improve search efficiency without changing the underlying reaction model.
The paper introduces Feedback‑Enriched Environments (FEEs) as a new approach to training large language models as autonomous agents for long‑horizon tasks. By shifting from action guidance to observation enrichment during later stages of exploration, FEEs improve performance across SciWorld and BFCL benchmarks with various Qwen3 model scales and RL algorithms. The study shows that FEEs stabilize training, promote proactive exploration, embed environmental guidance into policy weights, and highlight intra‑group feedback consistency as key for stable optimization.
The paper investigates reflective prompt optimization (GEPA) for a multi‑agent deep‑research language‑model, focusing on a topic‑disjoint train/validation/test split to avoid memorization. Across three random seeds, the optimized prompts improve held‑out citation reward from 0.702 to 0.781, with a 95% confidence interval of [0.051, 0.107]. The study shows that the gain is driven by decomposed per‑dimension feedback rather than a single scalar reward, and that the improvement persists even with an out‑of‑family verifier and a hand‑written version of the discovered recipe.
arXiv:2606. 11256v1 Announce Type: cross Abstract: Designing molecules with target properties is most useful when candidate structures are accompanied by feasible synthetic routes.
arXiv:2607. 02834v1 Announce Type: new Abstract: Molecular optimization often starts from a pretrained generative model that captures a broad prior over valid molecular structures.
arXiv:2606. 29082v1 Announce Type: cross Abstract: Would experience designing faster GPU kernels also help close in on a long-standing open mathematical conjecture?