arXiv subjects

Wesley Assunção

Publications and source records attributed to Wesley Assunção.

3 recordsLinked to original sources

arXiv2026

Disentangling Task Difficulty from Run-Level Failure in Agent Failure Prediction

Predicting whether an LLM agent will fail has emerged as a promising direction for supporting intervention during execution. Recent approaches report strong predictive performance, often with AUROC values between 0.85 and 0.94. However, predictors are typically trained by pooling runs from many tasks. We hypothesize that part of this performance comes from recognizing that some tasks are harder than others, rather than detecting whether a particular run is heading toward failure. This distinction matters because task-level difficulty supports decisions about where to allocate computation, while run-level prediction is needed to decide whether to intervene in an ongoing trajectory. We study benchmarks with repeated attempts of the same task by the same agent and separate cross-unit comparisons from comparisons between successful and failed runs of the same model-task unit. Across the evaluated corpora, more than 99.93% of the positive-negative pairs underlying pooled AUROC are cross-unit. Accordingly, predictors that never observe the current run can achieve high pooled performance, including a difficulty oracle with AUROC up to 0.945, while remaining at chance within task. Early run-level discrimination is consistently weak across trajectory predictors, released monitors, and hidden-state probes, although it improves later in execution and is stronger for weaker agents. Under fixed token budgets, task-level allocation outperforms abort-only strategies, while early stopping becomes beneficial only when within-task AUROC reaches about 0.84-0.93, far above the 0.50-0.55 range observed for early monitors. These results show that failure prediction should be evaluated not only by outcome accuracy, but by whether the captured signal supports the intended deployment decision.

cs.LG↗

arXiv2026

Beyond Resolution Rates: Behavioral Drivers of Coding Agent Success and Failure

Coding agents represent a new paradigm in automated software engineering, combining the reasoning capabilities of Large Language Models (LLMs) with tool-augmented interaction loops. However, coding agents still have severe limitations. Top-ranked LLM-based coding agents still fail on over 20% of benchmarked problems. Yet, we lack a systematic understanding of why (i.e., the causes) agents fail, and how failure unfolds behaviorally. We present a large-scale empirical study analyzing 9,374 trajectories from 19 agents (8 coding agent frameworks, 14 LLMs) on 500 tasks. We organize our analysis around three research questions. First, we investigate why agents fail on specific tasks and find that patch complexity alone does not explain difficulty: 12 never-solved tasks require only simple patches and were considered easy by human annotators, yet all agents fail due to gaps in architectural reasoning and domain knowledge. Second, we examine how behavioral patterns differentiate success from failure. The widely reported correlation between trajectory length and failure reverses direction once task difficulty is controlled, revealing it as a confound. Instead, trajectory structure discriminates consistently: agents that gather context before editing and invest in validation succeed more often, and these strategies are agent-determined rather than task-adaptive. Third, we disentangle LLM capability from framework design and find that the LLM is the primary driver of both outcome and behavior: agents sharing the same LLM agree on far more tasks than agents sharing the same framework, and the framework performance gap shrinks with each generation of LLM improvement. Framework prompts do influence agent tactics, but this influence diminishes with stronger LLMs.

cs.SE↗

arXiv2026

Code Quality Analysis of Translations from C to Rust

C/C++ is a prevalent programming language. Yet, it suffers from significant memory and thread-safety issues. Recent studies have explored automated translation of C/C++ to safer languages, such as Rust. However, these studies focused mostly on the correctness and safety of the translated code, which are indeed critical, but they left other important quality concerns (e.g., performance, robustness, and maintainability) largely unexplored. This work investigates strengths and weaknesses of three C-to-Rust translators, namely C2Rust (a transpiler), C2SaferRust (an LLM-guided transpiler), and TranslationGym (an LLM-based direct translation). We perform an in-depth quantitative and qualitative analysis of several important quality attributes for the translated Rust code of the popular GNU coreutils, using human-based translation as a baseline. To assess the internal and external quality of the Rust code, we: (i) apply Clippy, a rule-based state-of-the-practice Rust static analysis tool; (ii) investigate the capability of an LLM (GPT-4o) to identify issues potentially overlooked by Clippy; and (iii) perform a manual analysis of the issues reported by Clippy and GPT-4o. Our results show that while newer techniques reduce some unsafe and non-idiomatic patterns, they frequently introduce new issues, revealing systematic trade-offs that are not visible under existing evaluation practices. Notably, none of the automated techniques consistently match or exceed human-written translations across all quality dimensions, yet even human-written Rust code exhibits persistent internal quality issues such as readability and non-idiomatic patterns. Together, these findings show that translation quality remains a multi-dimensional challenge, requiring systematic evaluation and targeted tool support beyond both naive automation and manual rewriting.

cs.SE↗