arXiv subjects

Aws Albarghouthi

Publications and source records attributed to Aws Albarghouthi.

At least 19 recordsLinked to original sources

arXiv2026

Can Agents Design Libraries for Agents?

Agents increasingly build on code written by other agents, and they reimplement rather than reuse, growing the codebases later agents must work in. To measure how well agents design libraries for other agents, we introduce LibraryDesignBench, a two-phase benchmark in which an agent implements a full-featured library from a specification that defines required capabilities and potential use cases without prescribing the design. We evaluate the library through the correctness and simplicity of programs written by three user agents from different model families. The benchmark spans 242 expert-validated programming problems across 15 library-design tasks in four languages. On eleven of the fifteen tasks, agent designers reproduce the abstractions of the human-written production library. Downstream agents adopt agent- and human-written libraries alike but underuse them, reimplementing capabilities the library already provides. Our failure analysis finds that downstream agents write extra code mainly because agent-written libraries are rigid or hard to use, not because capabilities are missing. We also experiment with giving designers more prescriptive, agent-first guidance and having them test their library with subagents; this improves downstream scores and yields simpler programs. LibraryDesignBench provides both a testbed for evaluating library-design practices for agent users and an initial design baseline that improves downstream reuse.

cs.AI↗

arXiv2026

Linear-Time T-Gate Optimization via Random Abstraction

Quantum computers promise exponential speedups for problems in cryptography, chemistry, and optimization. Realizing this promise requires fault tolerance: physical qubits are noisy, so logical qubits must be encoded redundantly across many physical ones using quantum error-correcting codes. In most practical fault-tolerance schemes, T gates cannot be implemented transversally and instead require costly magic-state distillation protocols involving a complex set of operations. As a result, T-gate count can dominate the resource budget of large-scale quantum computations, making T-count minimization a central bottleneck on the path to quantum advantage. Existing T-count optimization tools, however, do not scale to the circuits that quantum advantage demands. We present theoretical and practical results on T-gate optimization. On the theoretical side, we give a linear-time randomized algorithm for phase folding, based on a novel randomized static analysis. Our static analysis soundly approximates the set of reachable quantum states with an arbitrarily high probability. Our key insight is a static analysis that does not track symbolic expressions, but propagates constant-width bitstrings down the circuit. On the practical side, our implementation, TZAP, is multiple orders of magnitude faster than state-of-the-art tools -- such as PyZX, VOQC, and Feynman -- closely matches their T-count reductions on standard benchmarks, and within seconds on a laptop computer can optimize circuits with millions of gates.

cs.PL↗

arXiv2026

SlopCodeBench: Benchmarking How Coding Agents Degrade Over Long-Horizon Iterative Tasks

Software development is iterative, yet agentic coding benchmarks hide design issues through their single-shot setup. Recent iterative benchmarks attempt to remedy this but heavily constrain an agent's design decision space, making it impossible to faithfully measure how their decisions shape future extensions. We introduce SlopCodeBench, a benchmark of 36 problems and 196 checkpoints where agents repeatedly extend their own solutions. Unlike prior iterative benchmarks, our evolving specifications demand architectural decisions but leave internal structure to the agent. We measure two forms of degradation: structural erosion (concentrated complexity) and verbosity (redundant code). Evaluating 15 coding agents across open and closed models, we find that no agent fully solves any problem end-to-end, and the best agent passes 14.8% of checkpoints. Quality degrades across checkpoints, with structural erosion rising in 77% of trajectories and verbosity in 75.5%. Compared to 473 open-source Python repositories, agent code is 2.3x more verbose and 2.0x more eroded, and the human repositories degrade less often and by smaller margins across their git histories. Explicit quality guidance reduces initial verbosity and erosion by up to a third, without affecting degradation rates. SlopCodeBench provides the first measurement of code degradation under iterative extension, revealing that agents pass checkpoints while producing code that erodes and bloats with each turn.

cs.SE↗

arXiv2026

U-Define: Designing User Workflows for Hard and Soft Constraints in LLM-Based Planning

LLMs are increasingly used for end-user task planning, yet their black-box nature limits users' ability to ensure reliability and control. While recent systems incorporate verification techniques, it remains unclear how users can effectively apply such rigid constraints to represent intent or adapt to real-world variability. For example, prior work finds that hard-only constraints are too rigid, and numeric flexibility weights confuse users. We investigate how interaction workflows can better support users in applying constraints to guide LLM-generated plans, examining whether abstracting strictness into high-level types (i.e., hard and soft) paired with distinct verification mechanisms helps users more reliably express and align intent. We present U-Define, a system that lets users define constraints in natural language and categorize them as either hard rules that must not be violated or soft preferences that allow flexibility. U-Define verifies these types through complementary methods: formal model checking for hard constraints and LLM-as-judge evaluation for soft ones. Through a technical evaluation and user studies with general and expert participants, we find that user-defined constraint types improve perceived usefulness, performance, and satisfaction while maintaining usability. These findings provide insights for designing flexible yet reliable constraint-based workflows.

cs.AI↗

arXiv2026

LiveResearchBench: A Live Benchmark for User-Centric Deep Research in the Wild

Deep research -- producing comprehensive, citation-grounded reports by searching and synthesizing information from hundreds of live web sources -- marks an important frontier for agentic systems. To rigorously evaluate this ability, four principles are essential: tasks should be (1) user-centric, reflecting realistic information needs, (2) dynamic, requiring up-to-date information beyond parametric knowledge, (3) unambiguous, ensuring consistent interpretation across users, and (4) multi-faceted and search-intensive, requiring search over numerous web sources and in-depth analysis. Existing benchmarks fall short of these principles, often focusing on narrow domains or posing ambiguous questions that hinder fair comparison. Guided by these principles, we introduce LiveResearchBench, a benchmark of 100 expert-curated tasks spanning daily life, enterprise, and academia, each requiring extensive, dynamic, real-time web search and synthesis. Built with over 1,500 hours of human labor, LiveResearchBench provides a rigorous basis for systematic evaluation. To evaluate citation-grounded long-form reports, we introduce DeepEval, a comprehensive suite covering both content- and report-level quality, including coverage, presentation, citation accuracy and association, consistency and depth of analysis. DeepEval integrates four complementary evaluation protocols, each designed to ensure stable assessment and high agreement with human judgments. Using LiveResearchBench and DeepEval, we conduct a comprehensive evaluation of 17 frontier deep research systems, including single-agent web search, single-agent deep research, and multi-agent systems. Our analysis reveals current strengths, recurring failure modes, and key system components needed to advance reliable, insightful deep research. Our code is available at: https://github.com/SalesforceAIResearch/LiveResearchBench.

cs.AI↗

arXiv2026

Test-Time Scaling Makes Overtraining Compute-Optimal

Modern LLMs scale at test-time, e.g. via repeated sampling, where inference cost grows with model size and the number of samples. This creates a trade-off that pretraining scaling laws, such as Chinchilla, do not address. We present Train-to-Test ($T^2$) scaling laws that jointly optimize model size, training tokens, and number of inference samples under fixed end-to-end budgets. $T^2$ modernizes pretraining scaling laws with pass@$k$ modeling used for test-time scaling, then jointly optimizes pretraining and test-time decisions. Forecasts from $T^2$ are robust over distinct modeling approaches: measuring joint scaling effect on the task loss and modeling impact on task accuracy. Across eight downstream tasks, we find that when accounting for inference cost, optimal pretraining decisions shift radically into the overtraining regime, well-outside of the range of standard pretraining scaling suites. We validate our results by pretraining heavily overtrained models in the optimal region that $T^2$ scaling forecasts, confirming their substantially stronger performance compared to pretraining scaling alone. Finally, as frontier LLMs are post-trained, we show that our findings survive the post-training stage, making $T^2$ scaling meaningful in modern deployments.

cs.LG↗

arXiv2026

Analyzing Decoders for Quantum Error Correction

Quantum error correction (QEC) enables reliable computation on noisy hardware by encoding logical information across many physical qubits and periodically measuring parities to detect errors. A decoder is the classical algorithm that uses these measurements to infer which error most likely occurred, so that the system can correct it. The decoder's accuracy-how rarely it makes the wrong guess-directly determines the scale of quantum computation that can be reliably executed. With a wealth of competing decoding algorithms, a QEC system designer needs reliable methods to evaluate them. Today, the dominant approach is to evaluate decoders using Monte Carlo simulation. However, simulation has several drawbacks such as requiring many samples to produce low variance estimates. In this work, we develop a new systematic analysis for evaluating decoders. We introduce a novel formal semantics of a core language for QEC programs that captures the de facto standard Stim circuit format, providing a principled theoretical foundation for the emerging space of fault-tolerant quantum systems design. Given a QEC program and a decoder, our verifier can quantify both the decoder accuracy and the decoder robustness to drift in physical error rate. Our approach has two key components: (i) a structured search over the space of possible errors; and (ii) a constrained polynomial optimization kernel. A thorough empirical evaluation of our approach suggests that it can outperform simulation, especially in low error rate regimes, and that it can be deployed to quantify decoder robustness over an interval of physical error rates.

cs.PL↗

arXiv2026

Managing Classical Processing Requirements for Quantum Error Correction

Large-scale quantum computers promise transformative speedups, but their viability hinges on fast and reliable quantum error correction (QEC). At the center of QEC are decoders-classical algorithms running on hardware such as FPGAs, GPUs, or CPUs that process error syndromes to detect errors every microsecond to preserve fault-tolerance. Quantum processors, therefore, operate not in isolation, but as accelerators tightly coupled with powerful classical digital hardware. A key challenge is that decoder demand fluctuates unpredictably: bursts of activity can require orders of magnitude more decodes than idle periods. Provisioning hardware for the worst case wastes resources, while provisioning for the average case risks catastrophic slowdowns. We show that this mismatch is a systems problem of capacity planning and scheduling, and propose a two-level framework that treats decoders as shared accelerators managed by the quantum operating system. Our approach reduces decoder requirements by 10-40% across fault-tolerant benchmarks, demonstrating that efficient decoder scheduling is essential to making FTQC practical.

quant-ph↗

arXiv2026

Pareto Optimal Code Generation

Generate-then-rank is the dominant test-time scaling (TTS) paradigm for code generation, but scaling accuracy by sampling and executing more candidates makes comprehensive verification a major computational bottleneck. This creates an inherent trade-off between accuracy and compute that, despite its importance to TTS, is often ignored. Specifically, faster but noisier signals, such as outcome reward models (ORMs), are dismissed as suboptimal. We frame verifier selection as a Pareto optimization problem and empirically map the accuracy-throughput frontier across signals, including the full test suite, heuristics for selective execution, and ORMs, across four Python benchmarks. We show that ORMs are most effective at optimizing the Pareto curve when pruning is used in the generate-then-rank pipeline--known as staged verification--where lightweight filters remove obviously incorrect solutions, including candidates with small syntactic or character-level bugs, before expensive verification. Our pruning analysis shows that eliminating incorrect yet highly ranked candidates (often character-level bugs) prevents wasted compute on incorrect tokens. We find that ORMs with staged verification shift the Pareto frontier outward, achieving 11.64x higher throughput at a cost of 8.26% accuracy relative to full test-suite verification.

cs.SE↗

arXiv2026

SkillOrchestra: Learning to Route Agents via Skill Transfer

Compound AI systems promise capabilities beyond those of individual models, yet their success depends critically on effective orchestration. Existing routing approaches face two limitations: (1) input-level routers make coarse query-level decisions that ignore evolving task requirements; (2) RL-trained orchestrators are expensive to adapt and often suffer from routing collapse, repeatedly invoking one strong but costly option in multi-turn scenarios. We introduce SkillOrchestra, a framework for skill-aware orchestration. Instead of directly learning a routing policy end-to-end, SkillOrchestra learns fine-grained skills from execution experience and models agent-specific competence and cost under those skills. At deployment, the orchestrator infers the skill demands of the current interaction and selects agents that best satisfy them under an explicit performance-cost trade-off. Extensive experiments across ten benchmarks demonstrate that SkillOrchestra outperforms SoTA RL-based orchestrators by up to 22.5% with 700x and 300x learning cost reduction compared to Router-R1 and ToolOrchestra, respectively. These results show that explicit skill modeling enables scalable, interpretable, and sample-efficient orchestration, offering a principled alternative to data-intensive RL-based approaches. The code is available at: https://github.com/jiayuww/SkillOrchestra.

cs.AI↗

arXiv2026

Generating Compilers for Qubit Mapping and Routing

To evaluate a quantum circuit on a quantum processor, one must find a mapping from circuit qubits to processor qubits and plan the instruction execution while satisfying the processor's constraints. This is known as the qubit mapping and routing (QMR) problem. High-quality QMR solutions are key to maximizing the utility of scarce quantum resources and minimizing the probability of logical errors affecting computation. The challenge is that the landscape of quantum processors is incredibly diverse and fast-evolving. Given this diversity, dozens of papers have addressed the QMR problem for different qubit hardware, connectivity constraints, and quantum error correction schemes by a developing a new algorithm for a particular context. We present an alternative approach: automatically generating qubit mapping and routing compilers for arbitrary quantum processors. Though each QMR problem is different, we identify a common core structure-device state machine-that we use to formulate an abstract QMR problem. Our formulation naturally leads to a compact domain-specific language for specifying QMR problems and a powerful parametric algorithm that can be instantiated for any QMR specification. Our thorough evaluation on case studies of important QMR problems shows that generated compilers are competitive with handwritten, specialized compilers in terms of runtime and solution quality.

cs.PL↗

arXiv2025

Beyond Accuracy: Dissecting Mathematical Reasoning for LLMs Under Reinforcement Learning

Reinforcement learning (RL) has become the dominant paradigm for improving the performance of language models on complex reasoning tasks. Despite the substantial empirical gains demonstrated by RL-based training methods like GRPO, a granular understanding of why and how RL enhances performance is still lacking. To bridge this gap, we introduce SPARKLE, a fine-grained analytic framework to dissect the effects of RL across three key dimensions: (1) plan following and execution, (2) knowledge integration, and (3) chain of subproblems. Using this framework, we gain insights beyond mere accuracy. For instance, providing models with explicit human-crafted, step-by-step plans can surprisingly degrade performance on the most challenging benchmarks, yet RL-tuned models exhibit greater robustness, experiencing markedly smaller performance drops than base or SFT models. This suggests that RL may not primarily enhance the execution of external plans but rather empower models to formulate and follow internal strategies better suited to their reasoning processes. Conversely, we observe that RL enhances models' ability to integrate provided knowledge into their reasoning process, yielding consistent gains across diverse tasks. Finally, we study whether difficult problems -- those yielding no RL signals and mixed-quality reasoning traces -- can still be effectively used for training. We introduce SparkleRL-PSS, a multi-stage RL pipeline that reuses hard problems with partial step scaffolding, guiding exploration effectively without additional data generation. Together, our findings provide a principled foundation for understanding how RL shapes model behavior, offering practical insights for building more adaptive, data-efficient, and interpretable RL pipelines for reasoning tasks. Our code, data, and checkpoints are available at: https://sparkle-reasoning.github.io/.

cs.AI↗

arXiv2025

COSMOS: Predictable and Cost-Effective Adaptation of LLMs

Large language models (LLMs) achieve remarkable performance across numerous tasks by using a diverse array of adaptation strategies. However, optimally selecting a model and adaptation strategy under resource constraints is challenging and often requires extensive experimentation. We investigate whether it is possible to accurately predict both performance and cost without expensive trials. We formalize the strategy selection problem for LLMs and introduce COSMOS, a unified prediction framework that efficiently estimates adaptation outcomes at minimal cost. We instantiate and study the capability of our framework via a pair of powerful predictors: embedding-augmented lightweight proxy models to predict fine-tuning performance, and low-sample scaling laws to forecast retrieval-augmented in-context learning. Extensive evaluation across eight representative benchmarks demonstrates that COSMOS achieves high prediction accuracy while reducing computational costs by 92.72% on average, and up to 98.71% in resource-intensive scenarios. Our results show that efficient prediction of adaptation outcomes is not only feasible but can substantially reduce the computational overhead of LLM deployment while maintaining performance standards.

cs.LG↗

arXiv2025

Verified Foundations for Differential Privacy

Differential privacy (DP) has become the gold standard for privacy-preserving data analysis, but implementing it correctly has proven challenging. Prior work has focused on verifying DP at a high level, assuming the foundations are correct and a perfect source of randomness is available. However, the underlying theory of differential privacy can be very complex and subtle. Flaws in basic mechanisms and random number generation have been a critical source of vulnerabilities in real-world DP systems. In this paper, we present SampCert, the first comprehensive, mechanized foundation for differential privacy. SampCert is written in Lean with over 12,000 lines of proof. It offers a generic and extensible notion of DP, a framework for constructing and composing DP mechanisms, and formally verified implementations of Laplace and Gaussian sampling algorithms. SampCert provides (1) a mechanized foundation for developing the next generation of differentially private algorithms, and (2) mechanically verified primitives that can be deployed in production systems. Indeed, SampCert's verified algorithms power the DP offerings of Amazon Web Services (AWS), demonstrating its real-world impact. SampCert's key innovations include: (1) A generic DP foundation that can be instantiated for various DP definitions (e.g., pure, concentrated, Rényi DP); (2) formally verified discrete Laplace and Gaussian sampling algorithms that avoid the pitfalls of floating-point implementations; and (3) a simple probability monad and novel proof techniques that streamline the formalization. To enable proving complex correctness properties of DP and random number generation, SampCert makes heavy use of Lean's extensive Mathlib library, leveraging theorems in Fourier analysis, measure and probability theory, number theory, and topology.

cs.CR↗

arXiv2025

Dependency-Aware Compilation for Surface Code Quantum Architectures

Practical applications of quantum computing depend on fault-tolerant devices with error correction. Today, the most promising approach is a class of error-correcting codes called surface codes. We study the problem of compiling quantum circuits for quantum computers implementing surface codes. Optimal or near-optimal compilation is critical for both efficiency and correctness. The compilation problem requires (1) mapping circuit qubits to the device qubits and (2) routing execution paths between interacting qubits. We solve this problem efficiently and near-optimally with a novel algorithm that exploits the dependency structure of circuit operations to formulate discrete optimization problems that can be approximated via simulated annealing, a classic and simple algorithm. Our extensive evaluation shows that our approach is powerful and flexible for compiling realistic workloads.

quant-ph↗

arXiv2025

Perceptions of the Fairness Impacts of Multiplicity in Machine Learning

Machine learning (ML) is increasingly used in high-stakes settings, yet multiplicity - the existence of multiple good models - means that some predictions are essentially arbitrary. ML researchers and philosophers posit that multiplicity poses a fairness risk, but no studies have investigated whether stakeholders agree. In this work, we conduct a survey to see how multiplicity impacts lay stakeholders' - i.e., decision subjects' - perceptions of ML fairness, and which approaches to address multiplicity they prefer. We investigate how these perceptions are modulated by task characteristics (e.g., stakes and uncertainty). Survey respondents think that multiplicity threatens the fairness of model outcomes, but not the appropriateness of using the model, even though existing work suggests the opposite. Participants are strongly against resolving multiplicity by using a single model (effectively ignoring multiplicity) or by randomizing the outcomes. Our results indicate that model developers should be intentional about dealing with multiplicity in order to maintain fairness.

cs.CY↗

arXiv2024

Optimizing Quantum Circuits, Fast and Slow

Optimizing quantum circuits is critical: the number of quantum operations needs to be minimized for a successful evaluation of a circuit on a quantum processor. In this paper we unify two disparate ideas for optimizing quantum circuits, rewrite rules, which are fast standard optimizer passes, and unitary synthesis, which is slow, requiring a search through the space of circuits. We present a clean, unifying framework for thinking of rewriting and resynthesis as abstract circuit transformations. We then present a radically simple algorithm, GUOQ, for optimizing quantum circuits that exploits the synergies of rewriting and resynthesis. Our extensive evaluation demonstrates the ability of GUOQ to strongly outperform existing optimizers on a wide range of benchmarks.

cs.PL↗

arXiv2024

A One-Layer Decoder-Only Transformer is a Two-Layer RNN: With an Application to Certified Robustness

This paper reveals a key insight that a one-layer decoder-only Transformer is equivalent to a two-layer Recurrent Neural Network (RNN). Building on this insight, we propose ARC-Tran, a novel approach for verifying the robustness of decoder-only Transformers against arbitrary perturbation spaces. Compared to ARC-Tran, current robustness verification techniques are limited either to specific and length-preserving perturbations like word substitutions or to recursive models like LSTMs. ARC-Tran addresses these limitations by meticulously managing position encoding to prevent mismatches and by utilizing our key insight to achieve precise and scalable verification. Our evaluation shows that ARC-Tran (1) trains models more robust to arbitrary perturbation spaces than those produced by existing techniques and (2) shows high certification accuracy of the resulting models.

cs.CL↗