Publications
Our teams aspire to make discoveries that impact everyone, and core to our approach is sharing our research and tools to fuel progress in the field.
Our teams aspire to make discoveries that impact everyone, and core to our approach is sharing our research and tools to fuel progress in the field.
Sort By
1 - 15 of 11379 publications
FreshBrew: A Benchmark for Evaluating AI Agents on Java Code Migration
Victor May
Diganta Misra
Yanqi Luo
Anjali Sridhar
Justine Gehring
Silvio Soares Ribeiro Junior
2026
Preview abstract
AI coding assistants are rapidly becoming integral to modern software development. A key challenge in this space is the continual need to migrate and modernize codebases in response to evolving software ecosystems. Traditionally, such migrations have relied on rule-based systems and human intervention. With the advent of powerful large language models (LLMs), AI-driven agentic frameworks offer a promising alternative—but their effectiveness remains underexplored. In this paper, we introduce FreshBrew, a novel benchmark for evaluating AI-based agentic frameworks on project-level Java migrations. We benchmark several such frameworks, powered by state-of-the-art LLMs, and compare their performance against established rule-based tools. Our evaluation of AI agents on this benchmark of 228 repositories shows that the top-performing model, Gemini 2.5 Flash, can successfully migrate 56.5% of projects to JDK 17. Our empirical analysis reveals novel insights into the critical strengths and limitations of current agentic approaches, offering actionable insights into their real-world applicability. By releasing FreshBrew publicly upon acceptance, we aim to facilitate rigorous, reproducible evaluation and catalyze progress in AI-driven codebase modernization.
View details
Taming the Variants Multi-Architecture Continuous Testing at Google
Chandrakanth Chittappa
Ali Esmaeeli
Laura Macaddino
Sam Manfreda
David Margolin
Dharma Naidu
Sabuj Pattanayek
Sachin Sable
Ruslan Sakevych
Dushyant Acharya
Adrian Berding
Kevin Crossan
Wolff Dobson
Abhay Singh
19th IEEE International Conference on Software Testing, Verification and Validation (ICST) 2026, Daejeon, Republic of Korea, IEEE
Preview abstract
Enterprises are increasingly adopting multiple general-purpose computer architectures in the data center. This leads to new testing challenges as it creates demand to qualify the software for the additional architectures. Naively double-testing all software for both architectures is costly and unnecessary. Further, reconfiguring CI/CD to take advantage of the new architecture can be non-trivial at scale. This paper introduces CI/CD variants and an optimized testing cycle to solve these twin challenges. We empirically evaluate our solution's impact on human and machine expenses using 44k projects at Google on real production data. First, we estimate saving ~25% of machine expenses at the negligible cost of a few delayed breakage detections per day. Second, we estimate a 90+% reduction in human cost for migrating the configuration. All features described in this paper are now Generally Available at Google and we report this as an empirical case study in scaling CI/CD to new architectures.
View details
Sexual dimorphism in the complete connectome of the Drosophila male central nervous system
Stuart Berg
Isabella R Beckett
Marta Costa
Philipp Schlegel
Elizabeth C Marin
Aljoscha Nern
Stephan Preibisch
Wei Qiu
Shin-ya Takemura
Andrew Champion
Reed A. George
Gary Huang
William Katz
Christopher Ordish
Ken Hayworth
Eric Trautman
Vivek Jayaraman
Wyatt Korff
Geoffrey W Meissner
Sandro Romani
Jan Funke
Christopher Knecht
Stephan Saalfeld
Louis Scheffer
Scott Waddell
Gwyneth Card
Carlos Ribeiro
Michael B. Reiser
Harald Hess
Gerry Rubin
Gregory S.X.E. Jefferis
bioRxiv (2026)
Preview abstract
Sex differences in behaviour exist across all animals, typically under strong genetic regulation. In Drosophila, fruitless/doublesex transcription factors can identify dimorphic neurons but their organisation into functional circuits remains unclear.
We present the connectome of the entire Drosophila male central nervous system. This contains 166,691 neurons spanning the brain and nerve cord, fully proofread and annotated including fruitless/doublesex expression and 11,691 types. We provide the first comprehensive comparison between male and female brain connectomes to synaptic resolution, finding 7,205 isomorphic, 114 dimorphic, 262 male-specific and 69 female-specific types.
This resource enables analysis of full sensory-to-motor circuits underlying complex behaviours and the impact of dimorphic elements. Sex-specific/dimorphic neurons are concentrated in higher brain centres while the sensory and motor periphery are largely isomorphic. Within higher centres, male-specific connections are organised into hotspots defined by male-specific neurons or arbours. Numerous circuit switches reroute sensory information to form antagonistic circuits controlling opposing behaviours.
(Full author list included with the paper.)
View details
JAXBench: Benchmarking Autonomous TPU Kernel Optimization
Vijay Janapa Reddi
Charles Hong
Arya Tschand
Julian Walker
Suvinay Subramanian
Shangkun Wang
Sethu Sankaran
Nina Cai
2026
Preview abstract
Evaluation benchmarks have driven progress in automated kernel optimization, yet existing suites target GPUs exclusively. We present JAXBench, a TPU-native benchmark for AI-generated kernel optimization on Google Cloud TPUs. JAXBench comprises 50 JAX workloads, including 17 production LLM operators extracted from architectures in the public MaxText library such as Llama-3.1, DeepSeek-V3, Mixtral, Mamba-2, and AlphaFold2, and 33 fused operator sequences adapted from KernelBench. Eight of the 17 production operators ship with hand-optimized Pallas TPU kernels from the public Tokamax library, whose block sizes we tune via grid search, establishing strong reference baselines. We evaluate one-shot generation, iterative coding agents, the same iterative loop with TPU documentation injected, and a TPU-enabled Autocomp configuration augmented with the same TPU-specific documentation. Across the full 50-benchmark suite with Gemini 3 Flash, best-of-N solves 13/50 benchmarks at 1.01x geomean and iterative refinement reaches 32/50 at 1.18x. Injecting TPU documentation lifts iterative refinement to 48/50 at 1.28x and raises per-sample correctness from 5.8% to 37.3%. Autocomp solves 45/50 but converts those correct kernels into 1.36x geomean with 76% of benchmarks beating XLA. On the 8 hand-tuned references, Autocomp reaches 1.60x against the XLA baseline, showing strong performance against the 2.08x Tokamax geomean but trailing on the specialized paged and ragged attention operators. A Gemini 3.1 Pro ablation lifts Autocomp to 49.1% per-sample correctness and a 3.13x geomean. High-quality TPU kernel generation remains open, and we release the benchmark, profiling harness, and baseline results to support reproducible research.
View details
Preview abstract
This study examines the psychological and ethical implications of generative-AI chatbot use among youth, introducing the CTRL framework (Cognitive Trust, Reliance, and Learning Diminution) to explain how repeated use fosters cognitive offloading and reduced verification behavior. Survey data from 420 participants analyzed through factor analysis and structural equation modeling reveal that higher trust predicts greater reliance and diminished critical evaluation, alongside elevated concerns around privacy and academic integrity. Findings highlight the need for AI literacy and responsible design to mitigate unintended cognitive impacts.
View details
AI-PROPELLER: Warehouse-Scale Inter-Procedural Code Layout Optimization with AlphaEvolve
Chaitanya Mamatha Ananda
Rajiv Gupta
Aiden Grossman
2026
Preview abstract
Post-link optimizers (PLOs) such as Propeller and BOLT have demonstrated that precise, profile-guided code layout can extract significant performance gains from heavily optimized binaries. However, these systems are currently restricted to intra-procedural techniques, leaving the global potential of inter-procedural layout largely untapped. Inter-procedural code layout is historically difficult due to a combinatorially intractable search space and complex call-return semantics that are challenging to model. Consequently, the performance potential of fine-grained inter-procedural layout remains unproven in practice.Ours uses AlphaEvolve, an agentic workflow to evolve the compiler heuristic in Propeller into a fine-grained inter-procedural optimizer. While AlphaEvolve synthesizes novel code layout policies, Vizier fine-tunes the resulting policy hyperparameters.
To ensure high-fidelity, we move away from approximate static cost models and the agentic workflow generates multiple layout variants that are executed on actual hardware to measure real performance counters, providing a precise reward signal for the evolutionary loop. Ours has been evaluated on several benchmarks including large warehouse-scale applications and experiments show performance improvements of 0.23% to 1.6% on these benchmarks optimized with state-of-the-art FDO and PLO.
This is the first time ever that real-world applications have been optimized with fine-grained inter-procedural code layout.
View details
Preview abstract
This paper demonstrates that artificial intelligence can accelerate mathematical discovery by autonomously solving an open problem in theoretical physics. We present a neuro-symbolic system, combining the Gemini Deep Think large language model with a systematic Tree Search (TS) framework and automated numerical feedback, that successfully derived novel, exact analytical solutions for the power spectrum of gravitational radiation emitted by cosmic strings. Specifically, the agent evaluated the core integral for arbitrary loop geometries, directly improving upon recent AI-assisted attempts that only yielded partial asymptotic solutions. To substantiate our methodological claims regarding AI-accelerated discovery and to ensure transparency, we detail system prompts, search constraints, and intermittent feedback loops that guided the model. The agent identified a suite of 6 different analytical methods, the most elegant of which expands the kernel in Gegenbauer polynomials to naturally absorb the integrand's singularities. The methods lead to an asymptotic result for at large that both agrees with numerical results and also connects to the continuous Feynman parameterization of Quantum Field Theory. We detail both the algorithmic methodology that enabled this discovery and the resulting mathematical derivations.
View details
Preview abstract
Object-Counting for remote-sensing (RS) imagery is raising increasing research interest due to its crucial role in a wide and diverse set of applications. While several promising methods for RS object-counting have been proposed, existing methods focus on a closed, pre-defined set of object classes. This limitation necessitates costly re-annotation and model re-training to adapt current approaches for counting of novel objects that have not been seen during training, and severely inhibits their application in dynamic, real-world monitoring scenarios.
To address this gap, in this work we propose RS-OVC - an adaptation of existing work for Open Vocabulary Counting (OVC) approach from general computer vision to the RS domain. We show that our model is capable of accurate counting of novel object classes, that are unseen during training, based solely on textual and/or visual conditioning.
View details
Towards AI as a Collaborative Partner: A Taxonomy of AI Agent Behavior in Software Engineering
Proceedings of the 3rd ACM International Conference on AI-Powered Software (AIware '26), ACM, Montreal, QC, Canada (2026) (to appear)
Preview abstract
The ongoing transition of Large Language Models (LLMs) in software engineering from one-shot code generators into agentic partners requires a shift in how we define and measure success. While models are becoming more capable, the industry lacks a clear understanding of the behavioral norms that make an interactive software engineering (SWE) agent effective in collaborative software development in the enterprise. This work addresses this gap by presenting a taxonomy of desirable SWE agent behaviors, synthesized from 91 sets of developer-defined rules for SWE agents and validated through interviewing 15 experienced professional developers. In this taxonomy, we identify four core expectations: Adhere to Standards and Processes, Ensure Code Quality and Reliability, Solve Problems Effectively, and Collaborate with the Developer. These findings offer a concrete vocabulary for aligning SWE agent behavior with developer preferences, enabling researchers and practitioners to move beyond correctness-only benchmarks and start designing evaluations that reflect the socio-technical nature of professional software development in enterprises.
View details
An experimental evaluation of an AI-powered interactive learning platform
Nicole Miller
Yael Haramaty
Lidan Hackmon
Lior Belinsky
Abraham Oritz Tapia
Lucy Tootill
Scott Siebert
Frontiers in Artificial Intelligence (2026) (to appear)
Preview abstract
Generative AI, which is capable of transforming static content into dynamic learning experiences, holds the potential to revolutionize student engagement in educational contexts. However, questions still remain around whether or not these tools are effective at facilitating student learning. In this research, we test the effectiveness of an AI-powered platform incorporating multiple representations and assessment through Learn Your Way, an experimental research platform that transforms textbook chapters into dynamic visual and audio representations. Through a between-subjects, mixed methods experiment with 60 US-based students, we demonstrate that students who used Learn Your Way had a more positive learning experience and had better learning outcomes compared to students learning the same content through a digital textbook. These findings indicate that AI-driven tools, capable of providing choice among interactive representations of content, constitute an effective and promising method for enhancing student learning.
View details
VeriGuard: Enhancing LLM Agent Safety via Verified Code Generation
Dj Dvijotham
Mirko Montanari
ACL 2026
Preview abstract
Artificial intelligence is rapidly evolving, marked by the emergence of Large Language Model (LLM) agents – systems capable of complex reasoning, planning, and interaction with digital and physical environments. These agents, powered by advancements in LLMs, demonstrate remarkable capabilities across diverse domains, including finance, healthcare, web navigation, software development, and daily task assistance. Unlike traditional AI systems, LLM agents can perceive their surroundings, formulate multi-step plans, utilize external tools and APIs, access memory or knowledge bases, and execute actions to achieve specified goals. This ability to act upon the world, however, introduces significant safety and security challenges.
The safety paradigms developed for traditional LLMs, primarily focused on mitigating harmful textual outputs (e.g., toxicity, bias), are insufficient for safeguarding LLM agents. Agents interacting with dynamic environments and executing actions present a broader attack surface and new categories of risk. These include performing unsafe operations, violating privacy constraints through improper data handling or access control failures, deviating from user objectives (task misalignment), and susceptibility to novel manipulation techniques like indirect prompt injection and memory poisoning. Ensuring the trustworthy operation of these powerful agents is paramount, especially as they are integrated into high-stakes applications. To address this critical challenge, we introduce VeriGuard, a novel framework designed to enhance the safety and reliability of LLM agents by interactively verifying their policies and the actions. VeriGuard integrates a verification module that intercepts code-based actions proposed by the agent. In the first step, VeriGuard will generates and verifies the policies. The policies are rigorously checked against a set of predefined safety and security specifications Then each action will be verified to make sure it will align with the agent specification. This interactive verification loop ensures that the agent's behavior remains within safe operational bounds, effectively preventing the execution of harmful or unintended operations. By verifying each step, VeriGuard provides a robust safeguard, substantially improving the trustworthiness of LLM agents in complex, real-world environments.
View details
Preview abstract
This paper introduces Operationalized Temporal Entity Resolution, a distributed system architecture designed to resolve data consistency challenges in modern Security Information and Event Management (SIEM) environments. processing petabytes of high-velocity telemetry. We address the critical failure mode of ”State Smearing”—a temporal discrepancy between an entity’s state at event time versus analysis time—which frequently corrupts forensic timelines, particularly regarding ephemeral assets like containers and DHCP leases. Our approach coalesces heterogeneous data from diverse log sources into a single, canonical representation, processing over 2 billion entity fragments daily. By leveraging a deterministic Dynamic Graph Resolution via modified distributed connected components and a novel Density-Aware Temporal Checkpointing algorithm, we generate precise validity intervals. This method embeds temporal state directly into the resolution graph, eliminating the need for computationally expensive query-time joins. Ultimately, this architecture enables security analysts to perform ”time-travel” queries to reconstruct historical states accurately. Analysis of a production environment demonstrates that 8–16% of threat detection rules critically depend on this enriched temporal merging.
View details
Preview abstract
Voice activity detection (VAD) plays a vital role in enabling applications such as speech recognition. We analyze the impact of window size on the accuracy of three VAD algorithms: Silero, WebRTC, and Root Mean Square (RMS) across a set of diverse real-world digital audio streams. We additionally explore the use of hysteresis on top of each VAD output. Our results offer practical references for optimizing VAD systems. Silero significantly outperforms WebRTC and RMS, and hysteresis provides a benefit for WebRTC.
View details
Preview abstract
Automating AI research differs from general software engineering due to computationally expensive evaluation (e.g., model training) and opaque performance attribution. Current LLM-based agents struggle here, often generating monolithic scripts that ignore execution costs and causal factors. We introduce MARS (Modular Agent with Reflective Search), a framework optimized for autonomous AI research. MARS relies on three pillars: (1) Budget-Aware Planning via cost-constrained Monte Carlo Tree Search (MCTS) to explicitly balance performance with execution expense; (2) Modular Construction, employing a "Design-Decompose-Implement" pipeline to manage complex research repositories; and (3) Comparative Reflective Memory, which addresses credit assignment by analyzing solution differences to distill high-signal insights. MARS achieves state-of-the-art performance among open-source frameworks on MLE-Bench under comparable settings, maintaining competitiveness with the global leaderboard's top methods. Furthermore, the system exhibits qualitative "Aha!" moments, where 63% of all utilized lessons originate from cross-branch transfer, demonstrating that the agent effectively generalizes insights across search paths.
View details
Preview abstract
Large language models have achieved remarkable capabilities across domains, yet mechanisms underlying sophisticated reasoning continue to be explored1,2. Recent reasoning-reinforced models, including OpenAI’s o-series and DeepSeek-r1, outperform other merely instruction-tuned models on complex cognitive tasks3,4, attributed to extended test-time computation through longer chains of thought5. Here we show that enhanced reasoning emerges not from extended computation alone, but from the systematic simulation of complex, multi-agent interactions—a society of thought—which enables the deliberate diversification and debate among internal cognitive perspectives characterized by distinct personality traits and domain expertise. Through quantitative analysis using classified outputs and mechanistic interpretability methods applied to reasoning traces6–8, we find that reasoning models like DeepSeek-r1 exhibit much greater perspective diversity than baseline models, activating broader and more conflict between heterogeneous personality- and expertise-related features during reasoning. This multi-agent structure manifests in conversational behaviors including question-answering sequences, perspective shifts, and reconciliation of conflicting views, as well as in socio-emotional roles that characterize back-and-forth conversation, which together account for over 60% of the accuracy advantage in reasoning tasks through both direct and indirect facilitation of cognitive strategies9,10. Controlled reinforcement learning experiments further reveal that priming models with conversational scaffolding—even when dialogues lead to incorrect solutions—substantially accelerates reasoning improvement compared to answer-only training. These findings indicate that the social organization of thought, rather than correctness alone, enables effective exploration of solution spaces. We suggest that reasoning models establish a computational parallel to collective intelligence in human groups11–13, where diversity enables superior problem-solving when systematically structured and suggest new opportunities for agent organization to harness the wisdom of crowds.
View details
