arXiv subjects

Jonathan Bragg

Publications and source records attributed to Jonathan Bragg.

At least 19 recordsLinked to original sources

arXiv2026

Querying Multimodal Scientific Papers with AI: Practices and Preferences Across Blind, Low-Vision, and Sighted Scientists

Visual diagrams, figures, and tables are central to scientific papers, and convey information beyond what is captured in text. While blind or low-vision (BLV) scientists have traditionally relied on static alternative text to access figures in papers, the rise of artificial intelligence (AI) has made interactive question-answering (QA) a feasible paradigm for visual exploration; yet little is known about how scientists use visual QA in practice or how to improve its accessibility. In this work, we interview five BLV and five sighted scientists across different STEM fields to understand how they use two AI tools, ChatGPT and Gemini, to query multimodal scientific documents. Our findings characterize how scientists review multimodal content, including existing practices (along with accessibility workarounds) for engaging with visuals, and feedback on the suitability of AI-generated responses to multimodal queries. We further find that vague or incomplete image descriptions, as well as incorrect AI outputs more broadly, can cause both BLV and sighted scientists to abandon AI workflows. To support future research, we additionally contribute a dataset of 115 queries and responses from our participants' interactions with the AI tools for papers in their field. We close by discussing implications for AI-powered scientific QA systems, emphasizing considerations for access across abilities and domains.

cs.HC↗

arXiv2026

Scientific reasoning does not reliably translate into scientific forecasting in frontier AI

AI systems are increasingly used to support forward-looking scientific judgment, but it remains unclear whether they can form reliable expectations about future scientific advances. Here we show that strong scientific reasoning does not reliably translate into accurate forecasting of future scientific advances. To study this question, we introduce CUSP, a temporally grounded evaluation suite for event-level scientific forecasting across eight scientific disciplines. Across six frontier AI models, we observe a striking asymmetry in forecasting performance together with systematic error patterns. Models often identify plausible mechanisms underlying future scientific advances, yet perform near chance on feasibility assessment, generate solution strategies that only weakly align with realized advances, and systematically predict scientific advances later than they become publicly observable. Providing additional pre-cutoff scientific knowledge improves performance but does not eliminate these forecasting limitations. These findings suggest that current AI systems possess substantial retrospective scientific competence but limited forward-looking predictive capability. Scientific forecasting should therefore be evaluated as a complementary dimension of AI scientific capability when deploying AI systems for research prioritization and scientific decision-making.

cs.AI↗

arXiv2026

Omakase: proactive assistance with actionable suggestions for evolving scientific research projects

As AI agents become increasingly capable of complex knowledge tasks, the lack of context limits their capability to proactively reason about a user's latent needs throughout a long evolving project. In scientific research, many researchers still manually query a deep research system and compress their rich project contexts into short, targeted queries. Further, a deep research system produces exhaustive reports, making it difficult to identify concrete actions. To explore the opportunities of research assistants that are proactive throughout a research project, we conducted several studies (N=42) with a technology probe and an iterative prototype. The latest iteration of our system, Omakase, is a research assistant that monitors a user's project documents to infer timely queries to a deep research system. Omakase then distills long reports into suggestions contextualized to their evolving projects. Our evaluations showed that participants found the generated queries to be useful and timely, and rated Omakase's suggestions as significantly more actionable than the original reports.

cs.HC↗

arXiv2026

LitPivot: Developing Well-Situated Research Ideas Through Dynamic Contextualization and Critique within the Literature Landscape

Developing a novel research idea is hard. It must be distinct enough from prior work to claim a contribution while also building on it. This requires iteratively reviewing literature and refining an idea based on what a researcher reads; yet when an idea changes, the literature that matters often changes with it. Most tools offer limited support for this interplay: literature tools help researchers understand a fixed body of work, while ideation tools evaluate ideas against a static, pre-curated set of papers. We introduce literature-initiated pivots, a mechanism where engagement with literature prompts revision to a developing idea, and where that revision changes which literature is relevant. We operationalize this in LitPivot, where researchers concurrently draft and vet an idea. LitPivot dynamically retrieves clusters of papers relevant to a selected part of the idea and proposes literature-informed critiques for how to revise it. A lab study ($n{=}17$) shows researchers produced higher-rated ideas with stronger self-reported understanding of the literature space; an open-ended study ($n{=}5$) reveals how researchers use LitPivot to iteratively evolve their own ideas.

cs.HC↗

arXiv2026

Deep Research, Shallow Evaluation: A Case Study in Meta-Evaluation for Long-Form QA Benchmarks

Recent advances have made long-form report-generating systems widely available. This has prompted evaluation frameworks that use LLM-as-judge protocols and claim verification, along with meta-evaluation frameworks that seek to validate these methods. Many of the meta-evaluations estimate an evaluation quality's by comparing its assessments against human pairwise preferences. Prior work, however, suggests that human pairwise preference may be overly simplistic and can fail to capture nuances of expert expectations. We conduct a case study in meta-evaluation for long-form QA benchmarks using ScholarQA-CS2, a benchmark designed for assessing retrieval-augmented deep-research QA in the scientific domain. We comprehensively validate the benchmark through human pairwise preference judgments, then critically examine the strengths, weaknesses, and confounders of this approach. We show that pairwise preference rankings are best suited for system-level evaluation, while explicit metric-wise annotations and expert annotators are critical for reliable metric-level assessment, with subjectivity remaining a key challenge. Based on our findings, we offer practical guidelines for designing future meta-evaluations that better align evaluation methods, annotator expertise, and reporting practices. By surfacing these methodological challenges, we aim to advance evaluation standards for deep-research systems.

cs.CL↗

arXiv2026

Understanding Usage and Engagement in AI-Powered Scientific Research Tools: The Asta Interaction Dataset

AI-powered scientific research tools are rapidly being integrated into research workflows, yet the field lacks a clear lens into how researchers use these systems in real-world settings. We present and analyze the Asta Interaction Dataset, a large-scale resource comprising over 200,000 user queries and interaction logs from two deployed tools (a literature discovery interface and a scientific question-answering interface) within an LLM-powered retrieval-augmented generation platform. Using this dataset, we characterize query patterns, engagement behaviors, and how usage evolves with experience. We find that users submit longer and more complex queries than in traditional search, and treat the system as a collaborative research partner, delegating tasks such as drafting content and identifying research gaps. Users treat generated responses as persistent artifacts, revisiting and navigating among outputs and cited evidence in non-linear ways. With experience, users issue more targeted queries and engage more deeply with supporting citations, although keyword-style queries persist even among experienced users. We release the anonymized dataset and analysis with a new query intent taxonomy to inform future designs of real-world AI research assistants and to support realistic evaluation.

cs.HC↗

arXiv2025

AstaBench: Rigorous Benchmarking of AI Agents with a Scientific Research Suite

AI agents hold the potential to revolutionize scientific productivity by automating literature reviews, replicating experiments, analyzing data, and even proposing new directions of inquiry; indeed, there are now many such agents, ranging from general-purpose "deep research" systems to specialized science-specific agents, such as AI Scientist and AIGS. Rigorous evaluation of these agents is critical for progress. Yet existing benchmarks fall short on several fronts: they often (1) lack reproducible agent tools necessary for a controlled comparison of core agentic capabilities; (2) do not account for confounding variables such as model cost and tool access; (3) do not provide standardized interfaces for quick agent prototyping and evaluation; (4) fail to provide holistic, product-informed measures of real-world use cases such as science research; and (5) lack comprehensive baseline agents necessary to identify true advances. In response, we define principles and tooling for more rigorously benchmarking agents. Using these, we present AstaBench, a suite that provides a holistic measure of agentic ability to perform scientific research, comprising 2400+ problems spanning the entire scientific discovery process and multiple scientific domains, and including many problems inspired by actual user requests to deployed Asta agents. Our suite comes with the first scientific research environment with production-grade search tools that enable controlled, reproducible evaluation, better accounting for confounders. Alongside, we provide a comprehensive suite of nine science-optimized classes of Asta agents and numerous baselines. Our extensive evaluation of 57 agents across 22 agent classes reveals several interesting findings, most importantly that despite meaningful progress on certain individual aspects, AI remains far from solving the challenge of science research assistance.

cs.AI↗

arXiv2025

SciArena: An Open Evaluation Platform for Non-Verifiable Scientific Literature-Grounded Tasks

We present SciArena, an open and collaborative platform for evaluating foundation models on scientific literature-grounded tasks. Unlike traditional benchmarks for scientific literature understanding and synthesis, SciArena engages the research community directly, following the Chatbot Arena evaluation approach of community voting on model comparisons. By leveraging collective intelligence, SciArena offers a community-driven evaluation of model performance on open-ended scientific tasks that demand literature-grounded, long-form responses. The platform currently supports 47 foundation models and has collected over 20,000 votes from human researchers across diverse scientific domains. Our analysis of the data collected so far confirms its high quality. We discuss the results and insights based on the model ranking leaderboard. To further promote research in building model-based automated evaluation systems for literature tasks, we release SciArena-Eval, a meta-evaluation benchmark based on collected preference data. It measures the accuracy of models in judging answer quality by comparing their pairwise assessments with human votes. Our experiments highlight the benchmark's challenges and emphasize the need for more reliable automated evaluation methods.

cs.CL↗

arXiv2025

Facets, Taxonomies, and Syntheses: Navigating Structured Representations in LLM-Assisted Literature Review

Comprehensive literature review requires synthesizing vast amounts of research -- a labor intensive and cognitively demanding process. Most prior work focuses either on helping researchers deeply understand a few papers (e.g., for triaging or reading), or retrieving from and visualizing a vast corpus. Deep analysis and synthesis of large paper collections (e.g., to produce a survey paper) is largely conducted manually with little support. We present DimInd, an interactive system that scaffolds literature review across large paper collections through LLM-generated structured representations. DimInd scaffolds literature understanding with multiple levels of compression, from papers, to faceted literature comparison tables with information extracted from individual papers, to taxonomies of concepts, to narrative syntheses. Users are guided through these successive information transformations while maintaining provenance to source text. In an evaluation with 23 researchers, DimInd supported participants in extracting information and conceptually organizing papers with less effort compared to a ChatGPT-assisted baseline workflow.

cs.HC↗

arXiv2024

Re-evaluating Automatic LLM System Ranking for Alignment with Human Preference

Evaluating and ranking the capabilities of different LLMs is crucial for understanding their performance and alignment with human preferences. Due to the high cost and time-consuming nature of human evaluations, an automatic LLM bencher (i.e., an automatic evaluation framework that aims to rank LLMs based on their alignment with human preferences) is indispensable. An automatic LLM bencher consists of four components: the input set (e.g., a user instruction), the evaluation model (e.g., an LLM), the evaluation type (e.g., pairwise comparison), and the aggregation method (e.g., the ELO rating system). However, previous work has not thoroughly explored how to select these components or how their different combinations influence the results. In this work, through controlled experiments, we provide a series of recommendations on how to choose each component to better automate the evaluation of LLMs. Furthermore, we discovered that when evaluating LLMs with similar performance, the performance of the automatic LLM bencher declines sharply, underscoring the limitations of current benchers and calling for future work. Lastly, we found that the evaluation models' performance at the instance level (e.g., the accuracy of selecting the best output) does not always align with their effectiveness when used as a component of a bencher, highlighting the importance of dedicated system-level evaluation of benchers.

cs.CL↗

arXiv2024

Cocoa: Co-Planning and Co-Execution with AI Agents

As AI agents take on increasingly long-running tasks involving sophisticated planning and execution, there is a corresponding need for novel interaction designs that enable deeper human-agent collaboration. However, most prior works leverage human interaction to fix "autonomous" workflows that have yet to become fully autonomous or rigidly treat planning and execution as separate stages. Based on a formative study with 9 researchers using AI to support their work, we propose a design that affords greater flexibility in collaboration, so that users can 1) delegate agency to the user or agent via a collaborative plan where individual steps can be assigned; and 2) interleave planning and execution so that plans can adjust after partial execution. We introduce Cocoa, a system that takes design inspiration from computational notebooks to support complex research tasks. A lab study (n=16) found that Cocoa enabled steerability without sacrificing ease-of-use, and a week-long field deployment (n=7) showed how researchers collaborated with Cocoa to accomplish real-world tasks.

cs.HC↗

arXiv2024

Social-RAG: Retrieving from Group Interactions to Socially Ground AI Generation

AI agents are increasingly tasked with making proactive suggestions in online spaces where groups collaborate, yet risk being unhelpful or even annoying if they fail to match group preferences or behave in socially inappropriate ways. Fortunately, group spaces have a rich history of prior interactions and affordances for social feedback that can support grounding an agent's generations to a group's interests and norms. We present Social-RAG, a workflow for socially grounding agents that retrieves context from prior group interactions, selects relevant social signals, and feeds them into a language model to generate messages in a socially aligned manner. We implement this in \textsc{PaperPing}, a system for posting paper recommendations in group chat, leveraging social signals determined from formative studies with 39 researchers. From a three-month deployment in 18 channels reaching 500+ researchers, we observed PaperPing posted relevant messages in groups without disrupting their existing social practices, fostering group common ground.

cs.HC↗

arXiv2024

IdeaSynth: Iterative Research Idea Development Through Evolving and Composing Idea Facets with Literature-Grounded Feedback

Research ideation involves broad exploring and deep refining ideas. Both require deep engagement with literature. Existing tools focus primarily on idea broad generation, yet offer little support for iterative specification, refinement, and evaluation needed to further develop initial ideas. To bridge this gap, we introduce IdeaSynth, a research idea development system that uses LLMs to provide literature-grounded feedback for articulating research problems, solutions, evaluations, and contributions. IdeaSynth represents these idea facets as nodes on a canvas, and allow researchers to iteratively refine them by creating and exploring variations and composing them. Our lab study (N=20) showed that participants, while using IdeaSynth, explored more alternative ideas and expanded initial ideas with more details compared to a strong LLM-based baseline. Our deployment study (N=7) demonstrated that participants effectively used IdeaSynth for real-world research projects at various ideation stages from developing initial ideas to revising framings of mature manuscripts, highlighting the possibilities to adopt IdeaSynth in researcher's workflows.

cs.HC↗

arXiv2024

Papers-to-Posts: Supporting Detailed Long-Document Summarization with an Interactive LLM-Powered Source Outline

Compressing long and technical documents (e.g., >10 pages) into shorter-form articles (e.g., <2 pages) is critical for communicating information to different audiences, for example, blog posts of scientific research paper or legal briefs of dense court proceedings. While large language models (LLMs) are powerful tools for condensing large amounts of text, current interfaces to these models lack support for understanding and controlling what content is included in a detailed summarizing article. Such capability is especially important for detail- and technical-oriented domains, in which tactical selection and coherent synthesis of key details is critical for effective communication to the target audience. For this, we present interactive reverse source outlines, a novel mechanism for controllable long-form summarization featuring outline bullet points with automatic point selections that the user can iteratively adjust to obtain an article with the desired content coverage. We implement this mechanism in Papers-to-Posts, a new LLM-powered system for authoring research-paper blog posts. Through a within-subjects lab study (n=20) and a between-subjects deployment study (n=37 blog posts, 26 participants), we compare Papers-to-Posts to a strong baseline tool that provides an LLM-generated draft and access to free-form prompting. Under time constraints, Papers-to-Posts significantly increases writer satisfaction with blog post quality, particularly with respect to content coverage. Furthermore, quantitative results showed an increase in editing power (change in text for an amount of time or writing actions) while using Papers-to-Posts, and qualitative results showed that participants found incorporating key research-paper insights in their blog posts easier while using Papers-to-Posts.

cs.HC↗

arXiv2024

PaperWeaver: Enriching Topical Paper Alerts by Contextualizing Recommended Papers with User-collected Papers

With the rapid growth of scholarly archives, researchers subscribe to "paper alert" systems that periodically provide them with recommendations of recently published papers that are similar to previously collected papers. However, researchers sometimes struggle to make sense of nuanced connections between recommended papers and their own research context, as existing systems only present paper titles and abstracts. To help researchers spot these connections, we present PaperWeaver, an enriched paper alerts system that provides contextualized text descriptions of recommended papers based on user-collected papers. PaperWeaver employs a computational method based on Large Language Models (LLMs) to infer users' research interests from their collected papers, extract context-specific aspects of papers, and compare recommended and collected papers on these aspects. Our user study (N=15) showed that participants using PaperWeaver were able to better understand the relevance of recommended papers and triage them more confidently when compared to a baseline that presented the related work sections from recommended papers.

cs.DL↗

arXiv2024

Mitigating Barriers to Public Social Interaction with Meronymous Communication

In communities with social hierarchies, fear of judgment can discourage communication. While anonymity may alleviate some social pressure, fully anonymous spaces enable toxic behavior and hide the social context that motivates people to participate and helps them tailor their communication. We explore a design space of meronymous communication, where people can reveal carefully chosen aspects of their identity and also leverage trusted endorsers to gain credibility. We implemented these ideas in a system for scholars to meronymously seek and receive paper recommendations on Twitter and Mastodon. A formative study with 20 scholars confirmed that scholars see benefits to participating but are deterred due to social anxiety. From a month-long public deployment, we found that with meronymity, junior scholars could comfortably ask ``newbie'' questions and get responses from senior scholars who they normally found intimidating. Responses were also tailored to the aspects about themselves that junior scholars chose to reveal.

cs.HC↗

arXiv2023

Papeos: Augmenting Research Papers with Talk Videos

Research consumption has been traditionally limited to the reading of academic papers-a static, dense, and formally written format. Alternatively, pre-recorded conference presentation videos, which are more dynamic, concise, and colloquial, have recently become more widely available but potentially under-utilized. In this work, we explore the design space and benefits for combining academic papers and talk videos to leverage their complementary nature to provide a rich and fluid research consumption experience. Based on formative and co-design studies, we present Papeos, a novel reading and authoring interface that allow authors to augment their papers by segmenting and localizing talk videos alongside relevant paper passages with automatically generated suggestions. With Papeos, readers can visually skim a paper through clip thumbnails, and fluidly switch between consuming dense text in the paper or visual summaries in the video. In a comparative lab study (n=16), Papeos reduced mental load, scaffolded navigation, and facilitated more comprehensive reading of papers.

cs.HC↗

arXiv2023

RCT Rejection Sampling for Causal Estimation Evaluation

Confounding is a significant obstacle to unbiased estimation of causal effects from observational data. For settings with high-dimensional covariates -- such as text data, genomics, or the behavioral social sciences -- researchers have proposed methods to adjust for confounding by adapting machine learning methods to the goal of causal estimation. However, empirical evaluation of these adjustment methods has been challenging and limited. In this work, we build on a promising empirical evaluation strategy that simplifies evaluation design and uses real data: subsampling randomized controlled trials (RCTs) to create confounded observational datasets while using the average causal effects from the RCTs as ground-truth. We contribute a new sampling algorithm, which we call RCT rejection sampling, and provide theoretical guarantees that causal identification holds in the observational data to allow for valid comparisons to the ground-truth RCT. Using synthetic data, we show our algorithm indeed results in low bias when oracle estimators are evaluated on the confounded samples, which is not always the case for a previously proposed algorithm. In addition to this identification result, we highlight several finite data considerations for evaluation designers who plan to use RCT rejection sampling on their own datasets. As a proof of concept, we implement an example evaluation pipeline and walk through these finite data considerations with a novel, real-world RCT -- which we release publicly -- consisting of approximately 70k observations and text data as high-dimensional covariates. Together, these contributions build towards a broader agenda of improved empirical evaluation for causal estimation.

cs.AI↗