One Run Is Not an Idea: The Implementation Lottery in Automated Research

Automated research systems use experimental scores both to deliver artifacts and to decide which ideas to retain, transfer, and pursue. Yet one run scores one implementation of an idea. Crediting that realization-level score as evidence about the parent mechanism creates the \emph{implementation lottery}, in which an idea-level conclusion depends on which plausible implementation was sampled. The mismatch is structural whenever one run updates beliefs about a mechanism. We estimate its magnitude. The \emph{Idea Reliability Audit} measures \emph{idea reliability} by validating and freezing candidate cards, sampling fresh-session implementations, using outcome-blind fidelity labels, and rerunning saved artifacts. It reports idea ICC and leave-one-implementation-out (LOO) winner reversal. Prior work generally repeats the task; we repeat the idea. Across 312 assignments on 13 tabular tasks and two coding-agent setups, implementation variance was more than five and ten times same-artifact rerun variance, respectively, and the winner from one implementation draw differed from the winner under the other-two mean in 25.6\% and 43.6\% of decisions. Reversal survives card-level filtering under two outcome-blind review rules. An exploratory diagnostic on three materials-regression workflows with a deterministic evaluator also finds implementation variation dominating the decomposition. These findings distinguish idea reliability from best-of-$N$ artifact utility. Before a score guides idea-level branching, transfer, or research memory, evidence should cover multiple implementations.

ACM: Agentic Context Management for Long Horizon Tasks

Agentic tasks are inherently long-horizon and multi-turn, constantly accumulating context through interactions with the environment. Existing context compression methods inevitably incur information loss and are triggered by rigid heuristic rules, leaving them misaligned with the agent's evolving reasoning focus. We propose Agentic Context Management (ACM), a framework that equips agents with purpose-built context editing tools for lossless context management. Inspired by the interaction between short-term and long-term human memory, the agent autonomously decides when to compress its context, offloads discarded content to an external memory system, and queries it on demand for later retrieval. Building on this framework, we further develop a post-training pipeline that constructs high-quality demonstrations of context management and improves model performance on both agentic search and coding tasks. Further analysis reveals that effective context management reduces peak token pressure, enables extended explorations, and yields more consistent solutions across independent trials. Code, data, and model checkpoints are available at https://github.com/lixiaochuan2020/agentic-context-management.

Auto Research for Materials: Auditable AI-Scientist Workflows with Held-Out Transfer

An AI research agent can improve the score it sees without finding a modelling change that works on new materials. We ask a stricter question. After repeated experiments, does the selected change survive on data that never entered the loop, and can its code be reused? We separate the search into changes to features, models, representations, and training data. Seven searches produce 701 evaluated changes across ten Matbench endpoints. Agents receive only the mean over five inner folds, reducing reliance on any single development split. We then freeze the selected code and evaluate it once on an untouched holdout. Nine of ten choices remain the best tested single intervention. The surviving changes reveal two materials modelling regimes. With composition alone, feature, model, and representation changes provide comparable routes to improvement. They include held-out MAE reductions of 17.4\% for band gap and 18.6\% for steel strength, as well as gains on both classification endpoints, while screened external data adds little. For structure tasks, richer geometry descriptors and model or calibration changes lower mean held-out MAE by 14.6\% and 7.1\% and lead on different property families, whereas composition embeddings do not transfer. Combining separately found feature and model changes yields a 26.3\% mean held-out improvement. These results show in materials prediction that closed-loop agents can produce decisions that survive unseen evidence and code changes that can be reused across tasks and combined. More broadly, they provide an evaluation design for testing executable discoveries beyond the feedback loop.

Closed-loop Auto Research for Molecular Property Prediction: Discovering and Certifying Generalizable Improvements

Closed-loop Auto Research extends automated machine learning from fixed-dataset fitting to changing the research workflow, with language-model agents editing representations and model code and acquiring external evidence. Molecular property prediction spans many small endpoints. We ask whether this action space yields improvements generalizing beyond the validation signal selecting them. We isolate three Auto Research axes, features, models, and external evidence, under a file-level ablation lock attributing each gain to one axis over a strong baseline. Across 36 endpoints in three benchmark suites we score each selected configuration once on a held-out test whose labels the search never read. A routed pipeline taking each endpoint's best validation axis reaches positive held-out gains of 0.013, 0.011, and 0.042, the transferable axis differing by suite, data on TDC, model on Polaris, feature and model on MoleculeNet. The largest model-search gain falls from 0.041 on validation to 0.003 on test, while curated data reaches 0.022 but negative 0.019 on test, two non-transfer signatures. Curated external data raises held-out CYP2C9-substrate performance by 0.17 and half-life by 0.08, admitted through a contamination filter rejecting same-source files overlapping 64 to 89 percent of test structures, necessary but not sufficient for transfer. A matched-trial automated machine learning control did not reproduce the agent's code-level model intervention, reaching 0.006 against 0.042, and the pipeline stays competitive with an 84M-parameter pretrained 3D model on the shared training split. The experiments stay within molecular property prediction, but separating discovery from held-out certification is a domain-agnostic lesson for any closed-loop system optimising a proxy for a held-out quantity.

Auto Research with Specialist Agents Develops Effective and Non-Trivial Training Recipes

We study auto research as a closed empirical loop driven by external measurement. Each submitted trial carries a hypothesis, an executable code edit, an evaluator-owned outcome, and feedback that shapes the next proposal. The output is not a generated paper or a single model checkpoint, but an auditable trajectory of proposals, code diffs, experiments, scores, and failure labels. We instantiate this loop with specialist agents that partition recipe surfaces and share measured lineage across trials. The central empirical finding is that lineage feedback lets agents turn evaluator outcomes, including crashes, budget overruns, size failures, and accuracy-gate misses, into later program-level recipe edits rather than one-shot suggestions. Across 1,197 headline-run trials plus 600 Parameter Golf control trials after one-time setup and launch, humans did not choose proposals, edit recipes, override scores, or repair failed trials during the search. In the three headline runs, the same submitted-trial loop reduces Parameter Golf validation bpb by $0.81\%$, raises NanoChat-D12 CORE by $38.7\%$, and reduces CIFAR-10 Airbench96 wallclock by $4.59\%$, with each task measured by its own external evaluator and legality checks. The trace includes a strict architecture-domain audit of 157 headline-run submissions and program rewrites such as a NanoChat attention-kernel path change. Within this scope the loop autonomously writes code, submits experiments, absorbs feedback, applies and combines known techniques inside each environment, and improves public starting recipes.

Benchmark Test-Time Scaling of General LLM Agents

LLM agents are increasingly expected to function as general-purpose systems capable of resolving open-ended user requests. While existing benchmarks focus on domain-aware environments for developing specialized agents, evaluating general-purpose agents requires more realistic settings that challenge them to operate across multiple skills and tools within a unified environment. We introduce General AgentBench, a benchmark that provides such a unified framework for evaluating general LLM agents across search, coding, reasoning, and tool-use domains. Using General AgentBench, we systematically study test-time scaling behaviors under sequential scaling (iterative interaction) and parallel scaling (sampling multiple trajectories). Evaluation of ten leading LLM agents reveals a substantial performance degradation when moving from domain-specific evaluations to this general-agent setting. Moreover, we find that neither scaling methodology yields effective performance improvements in practice, due to two fundamental limitations: context ceiling in sequential scaling and verification gap in parallel scaling. Code is publicly available at https://github.com/cxcscmu/General-AgentBench.

OpenCUA: Open Foundations for Computer-Use Agents

Vision-language models have demonstrated impressive capabilities as computer-use agents (CUAs) capable of automating diverse computer tasks. As their commercial potential grows, critical details of the most capable CUA systems remain closed. As these agents will increasingly mediate digital interactions and execute consequential decisions on our behalf, the research community needs access to open CUA frameworks to study their capabilities, limitations, and risks. To bridge this gap, we propose OpenCUA, a comprehensive open-source framework for scaling CUA data and foundation models. Our framework consists of: (1) an annotation infrastructure that seamlessly captures human computer-use demonstrations; (2) AgentNet, the first large-scale computer-use task dataset spanning 3 operating systems and 200+ applications and websites; (3) a scalable pipeline that transforms demonstrations into state-action pairs with reflective long Chain-of-Thought reasoning that sustain robust performance gains as data scales. Our end-to-end agent models demonstrate strong performance across CUA benchmarks. In particular, OpenCUA-32B achieves an average success rate of 34.8% on OSWorld-Verified, establishing a new state-of-the-art (SOTA) among open-source models and surpassing OpenAI CUA (GPT-4o). Further analysis confirms that our approach generalizes well across domains and benefits significantly from increased test-time computation. We release our annotation tool, datasets, code, and models to build open foundations for further CUA research.

Scaling Computer-Use Grounding via User Interface Decomposition and Synthesis

Graphical user interface (GUI) grounding, the ability to map natural language instructions to specific actions on graphical user interfaces, remains a critical bottleneck in computer use agent development. Current benchmarks oversimplify grounding tasks as short referring expressions, failing to capture the complexity of real-world interactions that require software commonsense, layout understanding, and fine-grained manipulation capabilities. To address these limitations, we introduce OSWorld-G, a comprehensive benchmark comprising 564 finely annotated samples across diverse task types including text matching, element recognition, layout understanding, and precise manipulation. Additionally, we synthesize and release the largest computer use grounding dataset Jedi, which contains 4 million examples through multi-perspective decoupling of tasks. Our multi-scale models trained on Jedi demonstrate its effectiveness by outperforming existing approaches on ScreenSpot-v2, ScreenSpot-Pro, and our OSWorld-G. Furthermore, we demonstrate that improved grounding with Jedi directly enhances agentic capabilities of general foundation models on complex computer tasks, improving from 5% to 27% on OSWorld. Through detailed ablation studies, we identify key factors contributing to grounding performance and verify that combining specialized data for different interface elements enables compositional generalization to novel interfaces. All benchmark, data, checkpoints, and code are open-sourced and available at https://osworld-grounding.github.io.

DropletVideo: A Dataset and Approach to Explore Integral Spatio-Temporal Consistent Video Generation

Spatio-temporal consistency is a critical research topic in video generation. A qualified generated video segment must ensure plot plausibility and coherence while maintaining visual consistency of objects and scenes across varying viewpoints. Prior research, especially in open-source projects, primarily focuses on either temporal or spatial consistency, or their basic combination, such as appending a description of a camera movement after a prompt without constraining the outcomes of this movement. However, camera movement may introduce new objects to the scene or eliminate existing ones, thereby overlaying and affecting the preceding narrative. Especially in videos with numerous camera movements, the interplay between multiple plots becomes increasingly complex. This paper introduces and examines integral spatio-temporal consistency, considering the synergy between plot progression and camera techniques, and the long-term impact of prior content on subsequent generation. Our research encompasses dataset construction through to the development of the model. Initially, we constructed a DropletVideo-10M dataset, which comprises 10 million videos featuring dynamic camera motion and object actions. Each video is annotated with an average caption of 206 words, detailing various camera movements and plot developments. Following this, we developed and trained the DropletVideo model, which excels in preserving spatio-temporal coherence during video generation. The DropletVideo dataset and model are accessible at https://dropletx.github.io.

Montessori-Instruct: Generate Influential Training Data Tailored for Student Learning

Synthetic data has been widely used to train large language models, but their generative nature inevitably introduces noisy, non-informative, and misleading learning signals. In this paper, we propose Montessori-Instruct, a novel data synthesis framework that tailors the data synthesis ability of the teacher language model toward the student language model's learning process. Specifically, we utilize local data influence of synthetic training data points on students to characterize students' learning preferences. Then, we train the teacher model with Direct Preference Optimization (DPO) to generate synthetic data tailored toward student learning preferences. Experiments with Llama3-8B-Instruct (teacher) and Llama3-8B (student) on Alpaca Eval and MT-Bench demonstrate that Montessori-Instruct significantly outperforms standard synthesis methods by 18.35\% and 46.24\% relatively. Our method also beats data synthesized by a stronger teacher model, GPT-4o. Further analysis confirms the benefits of teacher's learning to generate more influential training data in the student's improved learning, the advantages of local data influence in accurately measuring student preferences, and the robustness of Montessori-Instruct across different student models. Our code and data are open-sourced at https://github.com/cxcscmu/Montessori-Instruct.