Lyle Ungar

Voice-Based Chatbots for English Speaking Practice in Multilingual Low-Resource Schools: A Multi-Stakeholder Mixed-Methods Study

AI-Assisted Submissions in Online Research Are Rare and Highly Concentrated but Routinely Approved

The results do not support the view that AI assistance currently poses an existential threat to online research, but reveal limited payment consequences for prohibited use and gaps in platform safeguards, leaving platforms poorly prepared should that threat materialize.

AgentWorld: Benchmarking Long-Horizon Collaboration of Multi-agent LLMs

To quantify collaboration effectiveness in addition to conventional binary task success, Causal Collaboration Effectiveness (CCE) is proposed, a graph-based metric that traces causal dependencies between agent actions and measures what fraction of a team's effort actually contributed to the outcome.

Optimized but Unowned: How AI-Authored Goals Undermine the Motivation They Are Meant to Drive

Findings reveal a quality-motivation dissociation in AI-assisted goal-setting and identify authorship preservation as a design priority for AI tools deployed in identity-relevant, behavior-dependent tasks.

PersonaMem-v3: Toward Omni-Platform Personal Intelligence for Holistic User Understanding, Recommendation, and Agentic Tasks

PersonaMem-v3 is introduced, a real-world-grounded benchmark and evaluation harness for omni-platform personal intelligence that evaluates whether AI agents can infer holistic user understanding from cross-platform evidence, personalize responses, rerank recommendations on social media, follow user steering through nat...

Real-Time Deadlines Reveal Fragile Temporal Adaptation in LLM Strategic Dialogues

This work uses simulated negotiations between paired agents under strict deadlines to study adaptation to real-time pressure, finding real-time temporal adaptation is fragile, model-dependent, and sensitive to how temporal constraints are presented.

Depression Symptoms and Relational Patterns in 187k ChatGPT Histories

ChatGPT histories should not be treated as clinical screening data but as evidence LLMs are increasingly used as informal support infrastructure, which is private, persistent, responsive, and available outside ordinary hours.