… The following papers were recommended by the Semantic Scholar API Agentic AI Ecosystems in Higher Education: A Perspective on AI Agents to Emerging Inclusive, Agentic Multi-Agent AI Framework for Learning, Teaching and Institutional Intelligence 2026 SocialCoach: Personalized Social Skill Learning … …
Papers arxiv:2605.11378 An Empirical Study of Automating Agent Evaluation Published on May 12 Submitted by Sangmin Woo on May 14 Amazon Authors: , , , , , , , , , , , , , , , , Abstract Automated agent evaluation using AI assistants requires specialized domain knowledge and procedural skills to ach… …
… Together, the camroll dataset and camroll-agent highlight the gap in AI agents' long-context reasoning: personalized visual memory requires different approaches from standard long-context textual memory, especially when consistency, visual details, and user-specific context are present. …
Papers arxiv:2606.08857 PaperMentor: A Human-Centered Multi-Agent Writing Tutor for AI Research Papers on Overleaf Published on Jun 7 Submitted by Jiarui Liu on Jun 10 Jinesis Authors: Jiarui Liu , , , , , , , , , , , , , , , , , , , Abstract A human-centered writing assistant system called PaperMe… …
… The following papers were recommended by the Semantic Scholar API Hera: Learning Long-Horizon Coordination for Device-Cloud Collaborative LLM Agents 2026 Rethinking Scale: Deployment Trade-offs of Small Language Models under Agent Paradigms 2026 AgentStop: Terminating Local AI Agents Early to Save … …
… Generated by Qwen/Qwen2.5-Coder-32B-Instruct Agents are widely deployed as assistants over documents, tools, and code. …
… Generated by Qwen/Qwen2.5-Coder-32B-Instruct AI glasses present a compelling platform for AI agents to serve as personalized memory assistants . …
… Orchard-Claw targets personal assistant agents. Trained with only 0.2K synthetic tasks, it achieves 59.6% pass@3 on Claw-Eval and 73.9% when paired with a stronger ZeroClaw harness . …
… Abaqus Agent is composed of six agents, including interpreter, architect, input writer, runner, reviewer, and visualizer agents, encompassing all the essential pre-processing and post-processing steps of standard FEA analyses. …
… Generated by Qwen/Qwen2.5-Coder-32B-Instruct Effective real-world assistance requires AI agents with robust Theory of Mind ToM : inferring human mental states from their behavior. …