A case study of evaluating AI agents on a neuroscience data-to-discovery pipeline

Agentic AI tools offer a promising path to automating software development bottlenecks in scientific research pipelines, particularly for stages that take domain experts days to months to build, where scientists care about correctness and robustness, not implementation details. We present an empirical study of general-purpose coding agents on a fly optogenetics data-to-discovery pipeline. We assess agents on tasks substantially larger than existing benchmarks, datasets orders of magnitude bigger, and evaluation criteria grounded in domain expert standards. We show that agents can solve several individual pipeline stages, suggesting stage-level automation is tractable. By analyzing agents' code iterations, we show that they struggle most when there is not a pre-defined criterion to iterate on, and they must instead use their scientific judgment to assess their current solution, a key open challenge. Mirroring scientific practice, they sometimes attempt visual inspection of intermediate outputs for self-evaluation, but largely fail to interpret what they see or act on it appropriately. Solving the end-to-end pipeline correctly requires stringing together successes across all pipeline stages, and this is beyond agents' current abilities. We identify challenges largely absent from existing benchmarks, including computational resource management and generalization to large held-out data collections. Finally, we distill principles for constructing scientific tasks and rigorous evaluation criteria for open-ended problems.

Live Interactive Training for Video Segmentation

Interactive video segmentation often requires many user interventions for robust performance in challenging scenarios (e.g., occlusions, object separations, camouflage, etc.). Yet, even state-of-the-art models like SAM2 use corrections only for immediate fixes without learning from this feedback, leading to inefficient, repetitive user effort. To address this, we introduce Live Interactive Training (LIT), a novel framework for prompt-based visual systems where models also learn online from human corrections at inference time. Our primary instantiation, LIT-LoRA, implements this by continually updating a lightweight LoRA module on-the-fly. When a user provides a correction, this module is rapidly trained on that feedback, allowing the vision system to improve performance on subsequent frames of the same video. Leveraging the core principles of LIT, our LIT-LoRA implementation achieves an average 18-34% reduction in total corrections on challenging video segmentation benchmarks, with a negligible training overhead of ~0.5s per correction. We further demonstrate its generality by successfully adapting it to other segmentation models and extending it to CLIP-based fine-grained image classification. Our work highlights the promise of live adaptation to transform interactive tools and significantly reduce redundant human effort in complex visual tasks. Project: https://youngxinyu1802.github.io/projects/LIT/.

Evaluating Agentic Optimization on Large Codebases

Large language model (LLM) coding agents increasingly operate at the repository level, motivating benchmarks that evaluate their ability to optimize entire codebases under realistic constraints. Existing code benchmarks largely rely on synthetic tasks, binary correctness signals, or single-objective evaluation, limiting their ability to assess holistic optimization behavior. We introduce FormulaCode, a benchmark for evaluating agentic optimization on large, real-world codebases with fine-grained, multi-objective performance metrics. FormulaCode comprises 957 performance bottlenecks mined from scientific Python repositories on GitHub, each paired with expert-authored patches and, on average, 264.6 community-maintained performance workloads per task, enabling the holistic ability of LLM agents to optimize codebases under realistic correctness and performance constraints. Our evaluations reveal that repository-scale, multi-objective optimization remains a major challenge for frontier LLM agents. Project website at: https://formula-code.github.io

Tracking and Understanding Object Transformations

Real-world objects frequently undergo state transformations. From an apple being cut into pieces to a butterfly emerging from its cocoon, tracking through these changes is important for understanding real-world objects and dynamics. However, existing methods often lose track of the target object after transformation, due to significant changes in object appearance. To address this limitation, we introduce the task of Track Any State: tracking objects through transformations while detecting and describing state changes, accompanied by a new benchmark dataset, VOST-TAS. To tackle this problem, we present TubeletGraph, a zero-shot system that recovers missing objects after transformation and maps out how object states are evolving over time. TubeletGraph first identifies potentially overlooked tracks, and determines whether they should be integrated based on semantic and proximity priors. Then, it reasons about the added tracks and generates a state graph describing each observed transformation. TubeletGraph achieves state-of-the-art tracking performance under transformations, while demonstrating deeper understanding of object transformations and promising capabilities in temporal grounding and semantic reasoning for complex object transformations. Code, additional results, and the benchmark dataset are available at https://tubelet-graph.github.io.

How many classes do we need to see for novel class discovery?

Novel class discovery is essential for ML models to adapt to evolving real-world data, with applications ranging from scientific discovery to robotics. However, these datasets contain complex and entangled factors of variation, making a systematic study of class discovery difficult. As a result, many fundamental questions are yet to be answered on why and when new class discoveries are more likely to be successful. To address this, we propose a simple controlled experimental framework using the dSprites dataset with procedurally generated modifying factors. This allows us to investigate what influences successful class discovery. In particular, we study the relationship between the number of known/unknown classes and discovery performance, as well as the impact of known class 'coverage' on discovering new classes. Our empirical results indicate that the benefit of the number of known classes reaches a saturation point beyond which discovery performance plateaus. The pattern of diminishing return across different settings provides an insight for cost-benefit analysis for practitioners and a starting point for more rigorous future research of class discovery on complex real-world datasets.

Pre-trained Large Language Models Learn Hidden Markov Models In-context

Hidden Markov Models (HMMs) are foundational tools for modeling sequential data with latent Markovian structure, yet fitting them to real-world data remains computationally challenging. In this work, we show that pre-trained large language models (LLMs) can effectively model data generated by HMMs via in-context learning (ICL)$\unicode{x2013}$their ability to infer patterns from examples within a prompt. On a diverse set of synthetic HMMs, LLMs achieve predictive accuracy approaching the theoretical optimum. We uncover novel scaling trends influenced by HMM properties, and offer theoretical conjectures for these empirical observations. We also provide practical guidelines for scientists on using ICL as a diagnostic tool for complex data. On real-world animal decision-making tasks, ICL achieves competitive performance with models designed by human experts. To our knowledge, this is the first demonstration that ICL can learn and predict HMM-generated sequences$\unicode{x2013}$an advance that deepens our understanding of in-context learning in LLMs and establishes its potential as a powerful tool for uncovering hidden structure in complex scientific data.

Pre-training Large Memory Language Models with Internal and External Knowledge

Neural language models are black-boxes -- both linguistic patterns and factual knowledge are distributed across billions of opaque parameters. This entangled encoding makes it difficult to reliably inspect, verify, or update specific facts. We propose a new class of language models, Large Memory Language Models (LMLM) with a pre-training recipe that stores factual knowledge in both internal weights and an external database. Our approach strategically masks externally retrieved factual values from the training loss, thereby teaching the model to perform targeted lookups rather than relying on memorization in model weights. Our experiments demonstrate that LMLMs achieve competitive performance compared to significantly larger, knowledge-dense LLMs on standard benchmarks, while offering the advantages of explicit, editable, and verifiable knowledge bases. This work represents a fundamental shift in how language models interact with and manage factual knowledge.

Self-Evolving Visual Concept Library using Vision-Language Critics

We study the problem of building a visual concept library for visual recognition. Building effective visual concept libraries is challenging, as manual definition is labor-intensive, while relying solely on LLMs for concept generation can result in concepts that lack discriminative power or fail to account for the complex interactions between them. Our approach, ESCHER, takes a library learning perspective to iteratively discover and improve visual concepts. ESCHER uses a vision-language model (VLM) as a critic to iteratively refine the concept library, including accounting for interactions between concepts and how they affect downstream classifiers. By leveraging the in-context learning abilities of LLMs and the history of performance using various concepts, ESCHER dynamically improves its concept generation strategy based on the VLM critic's feedback. Finally, ESCHER does not require any human annotations, and is thus an automated plug-and-play framework. We empirically demonstrate the ability of ESCHER to learn a concept library for zero-shot, few-shot, and fine-tuning visual classification tasks. This work represents, to our knowledge, the first application of concept library learning to real-world visual tasks.

Video Creation by Demonstration

We explore a novel video creation experience, namely Video Creation by Demonstration. Given a demonstration video and a context image from a different scene, we generate a physically plausible video that continues naturally from the context image and carries out the action concepts from the demonstration. To enable this capability, we present $\delta$-Diffusion, a self-supervised training approach that learns from unlabeled videos by conditional future frame prediction. Unlike most existing video generation controls that are based on explicit signals, we adopts the form of implicit latent control for maximal flexibility and expressiveness required by general videos. By leveraging a video foundation model with an appearance bottleneck design on top, we extract action latents from demonstration videos for conditioning the generation process with minimal appearance leakage. Empirically, $\delta$-Diffusion outperforms related baselines in terms of both human preference and large-scale machine evaluations, and demonstrates potentials towards interactive world simulation. Sampled video generation results are available at https://delta-diffusion.github.io/.

Learning Keypoints for Multi-Agent Behavior Analysis using Self-Supervision

The study of social interactions and collective behaviors through multi-agent video analysis is crucial in biology. While self-supervised keypoint discovery has emerged as a promising solution to reduce the need for manual keypoint annotations, existing methods often struggle with videos containing multiple interacting agents, especially those of the same species and color. To address this, we introduce B-KinD-multi, a novel approach that leverages pre-trained video segmentation models to guide keypoint discovery in multi-agent scenarios. This eliminates the need for time-consuming manual annotations on new experimental settings and organisms. Extensive evaluations demonstrate improved keypoint regression and downstream behavioral classification in videos of flies, mice, and rats. Furthermore, our method generalizes well to other species, including ants, bees, and humans, highlighting its potential for broad applications in automated keypoint annotation for multi-agent behavior analysis. Code available under: https://danielpkhalil.github.io/B-KinD-Multi