slack

This study addresses the challenge of automatically analyzing collaborative processes in task-oriented human-human dialogues by systematically reviewing discourse-level approaches to collaboration analysis. Integrating methods from conversation analysis, collaboration theory, behavioral coding schemes, and computational modeling, the work presents the first multidimensional and structured knowledge framework that comprehensively organizes existing techniques in terms of their task formulations, modeling strategies, and respective strengths and limitations. By offering a clear research roadmap and practical reference for the field, this contribution not only clarifies current methodological constraints but also identifies promising directions for future inquiry, thereby advancing collaboration analysis toward greater systematicity and computational tractability.

This study examines the communication barriers and coordination challenges faced by decentralized workforces in union organizing within the digital era. Drawing on 17 in-depth interviews, it investigates how workers employ text-based digital platforms—such as Discord, WhatsApp, and Slack—in their organizing practices. The findings reveal that while these tools substantially enhance coordination efficiency, they simultaneously introduce new challenges, including information security risks, information overload, and difficulties in trust formation. The paper systematically articulates the dual role of digital communication platforms in labor organizing, highlighting their critical influence on the success or failure of contemporary unions. In doing so, it advances theoretical understanding of digital labor organizing and offers a practical yet critically informed framework to guide future organizing efforts.

To address robots’ insufficient capability in conveying implicit intent during human–robot collaboration (HRC), this work proposes a three-stage paradigm: (1) modeling implicit semantics via natural language inference, (2) designing multimodal implicit feedback and proactive prompting mechanisms, and (3) establishing a multi-large-language-model (LLM) collaborative learning framework. It establishes, for the first time, a systematic research paradigm for implicit communication in HRC. Innovatively, it introduces an adaptive implicit cue generation mechanism and a multi-LLM collaborative reasoning architecture, enabling robots to autonomously acquire implicit communication strategies from interaction. Experiments demonstrate significant improvements in task efficiency and human trust, achieving 82.3% accuracy in implicit intent inference. Furthermore, ablation studies validate the substantial positive impact of implicit feedback channels and proactive prompting on collaborative awareness.

This study addresses the critical gap in social intelligence among current AI coding agents, which hinders effective coordination and consensus-building in collaborative tasks, resulting in team performance significantly below human levels. To investigate this limitation, the authors introduce CooperBench, a novel benchmark comprising over 600 multilingual, multi-repository collaborative coding tasks. Through dual-agent simulations and large-scale communication log analysis, they systematically uncover the “coordination curse”—a phenomenon where state-of-the-art models exhibit an average 30% drop in collaboration success rates. The work proposes a new paradigm for evaluating AI collaboration centered on social intelligence and identifies emergent behaviors such as role specialization and resource allocation. Furthermore, it pinpoints three core bottlenecks: communication breakdowns, commitment violations, and misaligned expectations.

This study investigates whether AI can mitigate persistent collaboration challenges—such as ambiguous performance accountability and poor communication—in project-based software development teams. Drawing on a two-phase longitudinal qualitative study (2023–2025) comprising 15 in-depth interviews and grounded in organizational behavior theory, the research finds that AI does not directly resolve core coordination mechanisms nor substantially enhance cross-role alignment. Instead, AI functions as a “cultural catalyst,” fostering emergent collaborative norms centered on efficiency prioritization, process transparency, and internalized accountability. Although primarily embedded within individual task workflows, AI unexpectedly reshapes team-level professional standards and practice consensus, driving its institutionalization from a tool to a collaborative infrastructure. The study advances beyond technocentric perspectives by arguing that AI’s fundamental impact on collaboration lies in cultural reconfiguration—not functional substitution.

This paper addresses the practical challenges hindering the adoption of generative-AI-driven conversational bots and intelligent agents in software engineering (SE), where real-world deployment often yields suboptimal outcomes or introduces new risks. To systematically investigate this research-practice gap, the authors conduct a multi-source literature review—integrating peer-reviewed academic papers and industrial reports—employing thematic modeling and cross-source comparative analysis. They propose the first SE-specific taxonomy for bot applications and introduce a novel “Motivation–Challenge–Mitigation” tri-dimensional framework. This framework identifies seven core technical and organizational challenges, synthesizes twelve empirically grounded best practices, and prioritizes five high-impact research directions. The key innovation lies in bridging the theory-practice divide: by articulating actionable mitigation strategies and concrete translation pathways, the work provides both theoretical grounding and pragmatic guidance for effective bot deployment in SE contexts.

Existing intent communication methods are rigid, task-specific, and poorly generalizable—primarily because “what to convey” is not systematically integrated with “when and how to convey it.” This work introduces the first three-dimensional design space for intent communication, orthogonally modeling *content*, *timing*, and *modality* along the dimensions of transparency, abstraction level, and modality. This unified framework enables adaptive, multimodal communication strategy generation across diverse tasks, environments, and user preferences. We instantiate and empirically validate our approach in three canonical human-robot collaboration scenarios: bystander interaction, collaborative task execution, and shared control. By bridging the theoretical gap between intent modeling and communication implementation, our method yields scalable, reusable, and human-intuitive strategies that significantly improve both safety and efficiency in human-robot collaboration.

This study addresses the critical issue of frequent failures in GitHub Actions workflows, which severely undermine automation reliability and maintainability. For the first time, it systematically maps 197 language constructs to 14 workflow capability features through a large-scale quantitative analysis of over 260,000 workflows across 49,000 repositories. By integrating language construct categorization with metadata mining, the work uncovers prevalent usage patterns, evolutionary trends, and their impact on workflow reliability. The findings reveal that only a small subset of constructs is heavily used, and that specific capability features are significantly associated with elevated failure rates and maintenance costs. These empirical insights provide actionable guidance for optimizing workflow design and improving robustness in continuous integration and delivery pipelines.

This study addresses the lack of systematic understanding regarding how GitHub Actions workflows are used in real-world scenarios, how developers respond to workflow failures, and how these practices relate to project characteristics. Combining large-scale quantitative analysis of 258,300 workflow runs with qualitative case studies across 21 diverse repositories, this work identifies three typical patterns developers employ to handle workflow failures and uncovers a “configuration–usage gap”—where YAML configurations exist but workflows remain effectively unused. Furthermore, the study empirically validates five hypotheses linking project features to workflow usage intensity, revealing a significant positive correlation between high usage intensity and low failure rates. These findings provide actionable empirical evidence for improving CI/CD practices.

This study addresses coordination inefficiencies in human–AI collaboration within shared workspaces, where the absence of effective coordination mechanisms often incurs process losses and can even reduce team performance when new collaborators are introduced. To mitigate these issues, this work proposes a scaffolding mechanism that integrates shared group memory with human-in-the-loop (HITL) approval gating, employing structured coordination strategies to optimize responsibility allocation and expert knowledge scheduling. Evaluated across 1,482 experimental sessions using the Collaborative Gym environment and DiscoveryBench tasks, the approach significantly enhances joint decision-making performance in three-person teams, sharpens the clarity of responsibility signaling, and more effectively channels expert knowledge to guide collective action.

This study investigates the collaborative patterns and citation intents between human developers and AI coding agents in code reviews centered on agent-generated pull requests (PRs). Leveraging the AIDev dataset, it introduces the first taxonomy for classifying citation intent in agent-generated PRs and conducts an empirical analysis of PR citation relationships in large-scale open-source projects through data mining and content analysis. The findings reveal a clear division of labor: humans predominantly cite PRs to integrate new features, whereas AI agents focus on bug fixes. Moreover, PRs involved in citation networks—either citing or being cited—exhibit significantly longer lifecycles and review durations than isolated PRs, indicating higher coordination costs. The work further identifies the emergence of a “meta-collaboration” workflow and outlines three directions for optimizing AI agent integration in code review processes.