Tag
This position paper discusses the challenges and opportunities of integrating agentic AI into safety-critical multi-drone systems, advocating for human-centered, socio-technical design approaches to ensure trust, governance, and adoption in professional contexts.
This position paper advocates computational argumentation as a formal foundation for Evaluative AI, which supports human decision-making by presenting competing hypotheses with evidence for and against, rather than single recommendations.
TA-RAG is a conceptual framework proposing tone awareness as a core design objective for Retrieval-Augmented Generation, addressing communicative misalignments (linguistic, cognitive, relational) that persist when RAG systems optimize only for factual accuracy. It outlines four constraints and an evaluation agenda for socially sensitive high-stakes contexts.
Microsoft Research's Atlas Playbook provides frameworks and tools for designing, deploying, and evaluating human-centered AI systems across diverse cultural contexts, based on fieldwork in Kenya and India.
This paper presents CoPlan, a co-intelligent and contestable interface for human-AI care planning that uses a multi-agent workflow to generate candidate interventions and arguments, allowing human care planners to inspect, challenge, and revise recommendations before final plan generation. It demonstrates the approach in an aging-in-place scenario and contributes a design framing for trustworthy human-AI care planning.
WeClawArena is an auditable benchmark and runtime sandbox for evaluating multi-party cross-user agent collaboration and security in human-centered agent networks, measuring task utility and attack success rates across personal workspace tasks.
This paper presents ConnectED, a human-centered AI system for Vietnamese education that uses the VietEduQwen LLM to support curriculum-aligned lesson planning and interactive student learning, reducing teacher prep time from hours to ~30-45 minutes while achieving 87% accuracy on national exam questions.
This paper shows that the choice of agent harness (scaffold) can cause up to a 40x difference in tokens per solved task, while model pass rates vary only slightly, demonstrating that harness–model pairs, not model alone, should be compared for human-centered coding-agent evaluation.
This paper compares socio-technical design principles with guidelines for human-centered AI, analyzing their similarities and differences to inform future AI design approaches.
Thinking Machines, the lab founded by ex-OpenAI researchers, released a manifesto arguing for distributed AI over centralized AGI, emphasizing local knowledge, human-AI collaboration, and user-encoded alignment.
This paper proposes ASMR, an agentic framework with a Field Generation Agent and a Structural Optimizer Agent that uses reinforcement learning to automatically generate compact and informative schemas from historical ship maintenance reports, aiming to improve report completeness and consistency.
A critique of the Pope's text on AI and human dignity argues that AI ethics requires a pluralistic framework incorporating diverse moral traditions such as Islamic justice, Buddhist compassion, and Ubuntu, rather than relying solely on human dignity.
Jeremy Howard argues against training AI models to autonomously do everything, advocating instead for LLMs that support human learning, creativity, and iterative experimentation.
This paper presents a framework for Human-Centered Large Language Models (HCLLMs), integrating HCI and NLP perspectives to prioritize human values throughout the model development lifecycle.