公开论文雷达

Leading benchmarks for formal theorem proving with large language models are small collections drawn from competition math, such as the IMO and Putnam, that poorly represent field-specific applications. We introduce StochBench, a Lean 4 benchmark of 450 graduate stochastic-processes problems at varying abstraction levels, each paired with its natural-language source. Addressing a field underrepresented in Mathlib, it covers finite and countable Markov chains, renewal processes, random walks, martingales, stopping times, queues, Brownian motion, stochastic calculus, weak convergence, and Poisson and continuous-time Markov processes. Our Opus 4.8-based agent achieves a 34.9% proof rate (157/450) under a 15-minute per-problem limit. StochBench better represents domain-specific applied mathematics while remaining challenging for advanced provers.

Translating high-level controls from security standards into concrete, system-specific requirements is central to cybersecurity requirements engineering. Large language models (LLMs) can accelerate this labor-intensive, recall-sensitive task, but any single run is unreliable: it misses valid safeguards while introducing plausible hallucinations, and outputs shift across runs and models. We reframe this variability as a resource: rather than selecting one output, we study post-generation ensembling, aggregating stochastic runs with information-retrieval data-fusion operators. We propose two strategies: Uniform fusion rewards mere cross-run agreement, whereas Naive-Bayes fusion weights each run by its estimated reliability. We evaluate both over 24 runs from 12 configurations across four model families, generated for ten ISO/IEC 27002:2022 controls and expert-judged against a gold standard of 72 valid requirements. Pooling every run's output recovers all 72 (whereas single configurations recover on average under half) but also 111 hallucinations. Fusion separates the wheat from the chaff, ranking valid requirements well ahead of hallucinations. In the areas under the precision-recall and ROC curves, Uniform fusion alone largely surpasses every original run and configuration by 0.142 and 0.118 over the best configuration. Naive-Bayes weighting adds a further 0.039 and 0.052, reaching 0.864 and 0.869 while attaining useful operating points earlier. Internal validation confirms the stability of these gains: they stay positive in at least 92% of out-of-bag bootstrap resamples and every structured-perturbation sample. Post-generation fusion thus turns apparent noise into a practical asset: a lightweight layer giving analysts broader coverage and a better prioritized review queue, using affordable, below-frontier models alone.

Large language models (LLMs) have become ubiquitous in software development, with LLM-based automated program repair tools increasingly used during code review. In this report, we explore the iterative blind use of LLMs as bug-fixers. Across multiple models and repair environments, we find that LLMs consistently claim to detect bugs in entirely bug-free programs while the rate of repair of buggy programs is less than that of the damage to correct programs. We also explore the long-term dynamics of this iterative process, and find that this frequently reaches a pseudo-bug-fixing cycle where the same changes are added and removed again ad infinitum. Lastly, via mechanistic probing, we unveil the existence of a steering vector which controls the editing propensity, suggesting that LLMs have an internal representation of ``buggy code", and that this representation is what is falsely activated to induce pseudo-bug fixing. These results provide insight towards the dynamics of fully autonomous bug-fixing systems, as well as stopping conditions under ambiguous goals.

This project investigates how software architecture practices in Free/Libre Open Source Software (FLOSS) are shaped by socio-technical and ethical factors, and how education can support more explicit, inclusive, and reflective architectural work. Motivated by FLOSS's role in digital sovereignty, it is observed that architectural decisions are often undocumented and scattered across issues, pull requests, and mailing lists. While prior research has studied architectural artifacts, erosion, and communication, the interplay between architectural work, governance arrangements, and ethical commitments in FLOSS remains underexplored. The research follows a three-phase design: (1) multi-method case studies of 3-4 domain-pairs of architecturally non-trivial FLOSS projects, (2) framework and intervention design with practitioners and educators, and (3) pilot evaluations in projects and courses. It will produce (i) cross-case empirical evidence on FLOSS architecture practices, (ii) a conceptual framework linking architecture practices to socio-technical conditions and ethical dimensions, and (iii) lightweight practices and teaching formats that render architectural work more explicit and inclusive.

Test adequacy criteria are widely used to evaluate and guide software testing. Although prior research has extensively examined these criteria using human-written programs, faults, and tests, the increasing adoption of Large Language Models (LLMs) for code generation raises important questions about their effectiveness in detecting LLM-induced faults. To investigate this, we conduct an empirical study involving 5 LLMs and 4 benchmarks, simulating end-to-end workflows in which both code and tests are automatically generated. We collect 6,000+ faulty program instances and evaluate the effectiveness and efficiency of 3 widely used adequacy criteria: statement coverage, branch coverage, and mutation testing. Our findings reveal several key insights. First, most faults introduced by LLMs are relatively trivial to catch. Second, the challenging faults are difficult to trigger using either traditional coverage-based or mutation-based criteria. Third, actual fault detection rates remain extremely low, often near zero, because test oracles fail to capture faulty behavior triggered by the generated test prefixes, exposing a critical limitation of automated test generation. Fourth, prompt-aware oracles can improve fault detection, but their overall effectiveness remains limited, highlighting the need for users to manually reason about test assertions. We further observe that mutation testing only marginally outperforms traditional coverage criteria in both triggering and detecting faults, raising questions about whether its significantly higher application cost is justified in this context.

Automated GUI testing is a widely adopted technique for ensuring mobile application quality by simulating user interactions to exercise functionalities. Despite the research breakthroughs in the past decades, covering complex functionalities that require multi-step action sequences still remains challenging. Traditional tools lack semantic understanding capability and can rarely synthesize such action sequences. Recent LLM-based tools can generate test intents describing target functionalities and leverage the LLM to fulfill the intents, but suffer from three key limitations: 1) loss of historical context for identifying uncovered functionalities, 2) synchronous intent generation that blocks exploration, and 3) per-step LLM-driven fulfillment incurring high cost and latency. To address these limitations, we propose GraphDroid, an intent-driven GUI testing framework that integrates a cluster-based memory mechanism to effectively identify uncovered functionalities from historically visited states for comprehensive application testing. For improving testing efficiency, GraphDroid adopts an asynchronous intent generation paradigm that eliminates the latency bottleneck and a hybrid intent fulfillment strategy that reserves the LLM for fulfilling complex intents while delegating simple intents to a lightweight heuristic algorithm. We evaluate GraphDroid on 41 real-world Android apps against six state-of-the-art baselines. Results show that GraphDroid outperforms all baselines, achieving up to 36.4% higher code coverage while incurring less than one eighth of the cost of the best pure LLM-based baseline. GraphDroid also exposes 19 bugs in the 41 apps and detects 13 of 52 crashes in the Themis bug benchmark, surpassing all the six baselines. Seven of the 19 bugs were previously unknown and we reported them to the developers. So far, four bugs have been confirmed and fixed.

We approach a cognitive simulation perspective on episodic and semantic memory in multiple-choice question answering by incorporating text from individual text corpora (ITC) into retrieval-augmented generation and DoRA fine-tuning. We web-crawl the search histories of 515 participants who answered 36 multiple-choice knowledge items and analyze a stratified subsample of 150 participants. For each participant, one DoRA adapter consolidates their ITC into a small language model (SLM) whose baseline correctness falls below the participants' lowest quartile. The adapter measurably writes the ITC into the weights: it fits its own participant's held-out text better than other participants' texts (dz =1.27), an individuality effect that increases with ITC size in rank order. On the generalized knowledge test, however, the adapter adds knowledge rather than alignment with the individual: log-loss match improves, whereas match accuracy under a bias-corrected PMI readout does not, and retrieval adds nothing on top. Our results demonstrate that ITCs can be consolidated into the weights of SLMs, an encouraging basis for individualized tutoring agents, and we discuss how to move from there toward a realistic simulation of episodic and semantic memory at the individual level.