坦佩雷大学

Large Language Models (LLMs) have enabled multi-agent systems to perform autonomous code generation for complex tasks. Despite the recent growth in research and industrial applications in this area, there is little work on synthesizing evidence from both academic and industrial sources to capture the current state of research on LLM-based multi-agent systems for code generation. To this end, we conducted a Multi-Vocal Literature Review (MLR), combining insights from both academia and industry, including peer-reviewed studies and grey literature. The aim of this study is to systematically synthesize and analyze existing knowledge on LLM-based multi-agent systems for code generation. Specifically, the review examines the motivations for their use, employed benchmarks and models, key challenges, proposed solutions, and potential directions for future research.We selected and reviewed 114 studies, and the key findings are: (1) the identified reasons for adopting multi-agent systems for code generation were classified into nine categories; (2) the models and evaluation benchmarks utilized across the studies were systematically analyzed to provide a structured overview of commonly adopted LLM configurations and assessment practices; (3) the reported challenges and corresponding solutions were synthesized into seven main categories and 26 subcategories; and (4) future research directions were identified and organized into six main categories and 18 subcategories. The results of this MLR will assist researchers and practitioners in pursuing further studies and supporting the real-world adoption of multi-agent systems in industrial settings.

Background: Emotions play an important role in learning. Activating teaching methods, such as flipped learning, can provide positive learning experiences but also pose emotional challenges to students. Aims: This intensive longitudinal study investigated 1) how students' emotional valence before a learning event, learning mode (individual, peer, teacher-led), teaching implementation (lecture-based vs. flipped), and physiological arousal (electrodermal activity, EDA) during the learning event related to emotional valence after a learning event, and 2) how EDA varies across within-event segments and teaching implementations during learning events. Sample: Participants were 69 students enrolled in an engineering mathematics course implemented either as lecture-based (n = 34) or flipped learning (n = 35). Methods: Students reported their emotional states via a smartphone application and wore smart rings to measure EDA. A series of multilevel binomial logistic regression and linear mixed-effects models were analyzed across 546 learning events, totaling 827 h of data. Results: Positive pre-event emotional valence predicted positive post-event emotional valence. Teacher-led events were associated with more positive post-event emotional valence than individual events, particularly in the lecture-based group. The main effect of the teaching implementation was not significant. EDA did not show robust associations with post-event emotional valence; however, lecture-based events showed a clearer decline in EDA across event segments than flipped learning events. Conclusions: The results highlight the importance of supporting social and individual learning processes and examining physiological arousal as a temporal learning-event process rather than a simple proxy for post-event emotional valence.

Municipal wastewater treatment plants face increasing pressure to improve energy recovery while reducing sludge volumes and operational costs. In this context, low-input process intensification strategies are of growing interest. This study evaluated a continuous side-stream magnetization strategy applied during 44 days of mesophilic anaerobic digestion (37 +/- 2 degrees C) of sewage sludge, where digesting sludge was continuously recirculated through a tubular rare-earth-material magnetic polarizer generating a low-intensity static magnetic field (20 mT). The experimental results revealed a substantial increase in AD performance, with the SMF-exposed reactor achieving a 48.3% increase in specific biomethane production and a 15% higher reduction in volatile solids compared to the control reactor. Additionally, the digestate exposed to the SMF showed an improved dewaterability, evidenced by a 26.8% reduction in capillary suction time compared to the non-magnetized digestate. Microbial community analysis at the end of the AD process indicated that continuous exposure to SMF significantly enhanced the abundance of key methanogens, including Methanosarcina and Methanobacterium, which contributed to the higher biomethane production observed during AD. These findings indicate that continuous SMF exposure during AD can significantly enhance biomethane production and can be regarded as a promising approach to improve energy recovery from sewage sludge.

Infostealer malware infects devices worldwide and harvests their most sensitive contents: credentials, browser sessions, private keys, and access certificates. Yet its impact on victims remains difficult to study without an ethical, legal, and curated research dataset. To close this gap, we build a privacy-preserving pipeline that turns illicitly sourced infostealer logs into a reproducible research artifact, minimizing sensitive data while preserving measurement utility, and use it to construct a dataset of 170,298 victims from logs of multiple infostealer families. Analyzing these victims, we find that the most compromised services mirror the world's most popular platforms, with gaming and entertainment services strongly overrepresented. Within the sample we identify compromised credentials for high-value organizations, including law-enforcement domains, government and military services, and all eight Ivy League universities, as well as substantial exposure of security-critical infrastructure and of financial, remote-access, and development platforms. Victims also show widespread credential reuse and significant revictimization risk, overlapping with phishing and ransomware victim populations. We release the first anonymized victim-level infostealer dataset under controlled access to enable ethical, privacy-preserving, and reproducible research on information security and victim behavior.

As technologies increasingly converge with users’ psychophysiology and mental states, perception and mind-altering are emerging as plausibly designable components of user experience. This gives rise to emergent phenomena of digitally induced altered states of consciousness (DIAL) that find application not only in therapeutic and mental health contexts but also in communication and leisure. Modern consciousness-altering technologies primarily exist as early prototypes, and their empirical research tends to constrain the context of use to instrumental functionality. Fictional narrative analysis proposes to push these limitations by considering concepts of technology in imaginary contexts, thereby examining the experiences, social rituals, and ethical issues associated with their use far beyond traditional technical scenarios. This article employs a reflexive thematic analysis of popular science fiction narratives to expand our understanding of how ASCs are integrated into HCI, considering broader sociocultural and socio-technical contexts. As a result, we identify key aspects of interaction (purpose and context) and combine their subcategories into a framework that facilitates rethinking traditional HCI, revealing potentials that remain inaccessible within clear consciousness. This framework was used to construct five themes, highlighting that the benefits of mitigating cognitive load and deepening technology-mediated communication with DIAL might entail sacrificing identity and autonomy and increasing the pressures of the modern, overcompetitive, hyper-individualistic lifestyle. Thus, the article contributes to the HCI agenda by expanding existing paradigms of interaction with mind-altering technologies and by demonstrating the use of science fiction as a powerful avenue for exploring the design space and critical inquiries about these types of interactions.