POSEIDON is an automated pipeline that generates diverse, verifiable training environments from scientific code repositories, scaling up the number of environments by nearly tenfold compared to previous methods. It decomposes scientific workflows into four task types—Reproduction, Subflow, Completion, and Correction—to target distinct scientific research capabilities, and uses a recursive improvement loop to refine and recover environments. Using Poseidon, the authors created Pearl, a collection of 97,659 executable and verifiable environments from 7,110 public repositories across ten scientific disciplines, the largest multidisciplinary set to date, which enabled Qwen3.5 models to achieve consistent gains on six scientific-agent benchmarks.
arXiv:2609.19134v1 Announce Type: new Abstract: Scientific code repositories encode decades of human knowledge in executable models, methods, and tools. Yet fragmented toolchains, implicit domain con...
D3‑Gym is the first automatically constructed dataset that provides verifiable environments for scientific data‑driven discovery, comprising 565 tasks from 239 real scientific repositories across four disciplines. Each task includes a natural‑language instruction, an executable environment with pre‑installed dependencies, dataset previews, a reference solution, and an automatically synthesized evaluation script that achieves 87.5% agreement with human‑annotated gold standards. Training on trajectories sampled from D3‑Gym consistently improves Qwen3 models on ScienceAgentBench, and the platform also serves as a testbed for studying agentic optimization loops such as Autoresearch on real scientific workflows.
arXiv:2602. 02905v2 Announce Type: replace Abstract: Autonomous agents powered by large language models (LLMs) promise to accelerate scientific discovery end-to-end, but rigorously evaluating their capacity for verifiable discovery remains a central challenge.
arXiv:2606. 12736v1 Announce Type: new Abstract: AI agents are increasingly being developed to accelerate scientific discovery, yet their practical capabilities in real research settings remain poorly understood.
SAIL is an open model with 35 B total and 3 B active parameters designed for literature research, scientific coding, and multi‑step research workflows. It is developed through a science‑aware improvement loop in which agents built on frontier AI models analyze task failures, create training tasks to address capability gaps, and iterate this process across multiple development cycles. The training pipeline combines supervised fine‑tuning, specialist training, multi‑teacher on‑policy distillation, and agentic reinforcement learning, enabling SAIL to achieve competitive performance on scientific research tasks with fewer parameters than leading open‑weight models.
arXiv:2606. 13662v1 Announce Type: new Abstract: LLM-based agents have shown increasing potential in automating scientific discovery.
arXiv:2610.32441v1 Announce Type: new Abstract: Large language model (LLM) agents are increasingly capable of supporting scientific workflows, but their capabilities across diverse research activitie...
arXiv:2610.28578v1 Announce Type: new Abstract: In this report, we introduce Sage-A1.5, a 35B Mixture-of-Experts agentic model that builds on A1 to advance long-horizon problem solving through adapti...
arXiv:2607. 28990v1 Announce Type: new Abstract: Large language model agents have shown promising capabilities in data-driven scientific discovery tasks, where an agent interacts with an execution environment and produces a statistical claim.
arXiv:2604. 17406v3 Announce Type: replace Abstract: The convergence of large language models and agents is catalyzing a new era of scientific discovery: Agentic Science.
The paper "Beyond Execution: Auditing Experimental Fidelity in LLM-Driven Scientific Research" argues that large language model agents must faithfully implement reference methods, design experiments that truly test claims, and provide supporting evidence. It reports that agents often hallucinate methodology—reducing datasets, substituting components, or drawing conclusions from limited resources—leading to false claims. To counter this, the authors introduce ABE‑Ralph, a reference‑anchored auditing framework that structures experimental constraints, guides implementation, and verifies results, achieving a 93% robust execution rate across 30 reproduction runs and matching or exceeding state‑of‑the‑art performance on 5 NatureBench tasks. "whyItMatters":"The study demonstrates that evaluating AI scientists requires more than code execution; it must ensure experimental design and evidence truly support the claimed scientific outcomes."
arXiv:2512. 03476v3 Announce Type: replace-cross Abstract: Progress in computational science depends on complex numerical workflows that must faithfully encode physical laws, yet translating conceptual insight into reliable code remains a major bottleneck.