Alisia Lupidi

Alisia Lupidi, Bhavul Gauri, Thomas Simon Foster et al.

LLM agents hold significant promise for advancing scientific research. To accelerate this progress, we introduce AIRS-Bench (the AI Research Science Benchmark), a suite of 20 tasks sourced from state-of-the-art machine learning papers. These tasks span diverse domains, including language modeling, mathematics, bioinformatics, and time series forecasting. AIRS-Bench tasks assess agentic capabilities over the full research lifecycle -- including idea generation, experiment analysis and iterative refinement -- without providing baseline code. The AIRS-Bench task format is versatile, enabling easy integration of new tasks and rigorous comparison across different agentic frameworks. We establish baselines using frontier models paired with both sequential and parallel scaffolds. Our results show that agents exceed human SOTA in four tasks but fail to match it in sixteen others. Even when agents surpass human benchmarks, they do not reach the theoretical performance ceiling for the underlying tasks. These findings indicate that AIRS-Bench is far from saturated and offers substantial room for improvement. We open-source the AIRS-Bench task definitions and evaluation code to catalyze further development in autonomous scientific research.

Alisia Lupidi, Carlos Gemmell, Nicola Cancedda et al.

Synthetic data generation has recently emerged as a promising approach for enhancing the capabilities of large language models (LLMs) without the need for expensive human annotations. However, existing methods often generate data that can be low quality or contrived. In this paper, we introduce Source2Synth, a scalable approach for synthetic data generation and curation that is grounded in real-world data sources. Source2Synth takes as input a custom data source and produces synthetic data examples with intermediate reasoning steps. Our method improves the dataset quality by discarding low-quality generations based on their answerability. We demonstrate the generality of this approach by applying it to two tasks that leverage two different types of data: multi-hop question answering (MHQA), where we test complex reasoning abilities leveraging documents, and tabular question answering (TQA), where we test tool usage leveraging tables. Our method improves performance by 25.51% for TQA on WikiSQL and 22.57% for MHQA on HotpotQA compared to the fine-tuned baselines.

Karen Hambardzumyan, Nicolas Baldwin, Edan Toledo et al.

Existing research has identified three structural performance bottlenecks in AI research agents: (1) synchronous single-GPU execution constrains sample throughput, limiting the benefit of search; (2) a generalization gap where validation-based selection causes performance to degrade over extended search horizons; and (3) the limited capability of fixed, single-turn LLM operators imposes a ceiling on search performance. We introduce AIRA$_2$, which addresses these bottlenecks through three architectural choices: an asynchronous multi-GPU worker pool that increases experiment throughput linearly; a Hidden Consistent Evaluation protocol that delivers a reliable evaluation signal; and ReAct agents that dynamically scope their actions and debug interactively. On MLE-bench-30, AIRA$_2$ achieves a mean Percentile Rank of 71.8% at 24 hours - surpassing the previous best of 69.9% - and steadily improves to 76.0% at 72 hours. Ablation studies reveal that each component is necessary and that the "overfitting" reported in prior work was driven by evaluation noise rather than true data memorization.

Alisia Lupidi, Yonatan Gideoni, Dulhan Jayalath

Most investigations into double descent have focused on supervised models while the few works studying self-supervised settings find a surprising lack of the phenomenon. These results imply that double descent may not exist in self-supervised models. We show this empirically using a standard and linear autoencoder, two previously unstudied settings. The test loss is found to have either a classical U-shape or to monotonically decrease instead of exhibiting a double-descent curve. We hope that further work on this will help elucidate the theoretical underpinnings of this phenomenon.

Yuan He, Bailan He, Zifeng Ding et al.

Understanding and mitigating hallucinations in Large Language Models (LLMs) is crucial for ensuring reliable content generation. While previous research has primarily focused on "when" LLMs hallucinate, our work explains "why" and directly links model behaviour to the pre-training data that forms their prior knowledge. Specifically, we demonstrate that an asymmetry exists in the recognition of logically equivalent facts, which can be attributed to frequency discrepancies of entities appearing as subjects versus objects. Given that most pre-training datasets are inaccessible, we leverage the fully open-source OLMo series by indexing its Dolma dataset to estimate entity frequencies. Using relational facts (represented as triples) from Wikidata5M, we construct probing datasets to isolate this effect. Our experiments reveal that facts with a high-frequency subject and a low-frequency object are better recognised than their inverse, despite their logical equivalence. The pattern reverses in low-to-high frequency settings, and no statistically significant asymmetry emerges when both entities are high-frequency. These findings highlight the influential role of pre-training data in shaping model predictions and provide insights for inferring the characteristics of pre-training data in closed or partially closed LLMs.

Bingchen Zhao, Despoina Magka, Minqi Jiang et al. · meta-ai, oxford

Rapid advancements in large language models (LLMs) have the potential to assist in scientific progress. A critical capability toward this endeavor is the ability to reproduce existing work. To evaluate the ability of AI agents to reproduce results in an active research area, we introduce the Automated LLM Speedrunning Benchmark, leveraging the research community contributions on the NanoGPT speedrun, a competition to train a GPT-2 model in the shortest time. Each of the 19 speedrun tasks provides the agent with the previous records training script, optionally paired with one of three hint formats, ranging from pseudocode to paper-like descriptions of the new records improvements. Records execute quickly by design and speedrun improvements encompass diverse code-level changes, ranging from high-level algorithmic advancements to hardware-aware optimizations. These features make the benchmark both accessible and realistic for the frontier problem of improving LLM training. We find that recent reasoning LLMs combined with SoTA scaffolds struggle to reimplement already-known innovations in our benchmark, even when given detailed hints. Our benchmark thus provides a simple, non-saturated measure of an LLMs ability to automate scientific reproduction, a necessary (but not sufficient) skill for an autonomous research agent.