arXiv:2608. 03283v1 Announce Type: new Abstract: Identifying promising scientific ideas remains an important challenge in research practice.
Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.
Identifying promising scientific ideas remains an important challenge in research practice. Researchers commonly rely on small-group discussions or one-to-one interactions with a single large language model, yet these approaches often expose them to only a limited range of perspectives and directions.
DocuTeam is a mixed‑initiative multi‑agent discussion system that allows both users and agents to start and steer conversations around evolving documents. Agents monitor changes to the document and proactively initiate or redirect discussions, while users can shape the dialogue or adopt agent suggestions. In a within‑subjects study with 20 participants, DocuTeam produced outcomes that were rated as more novel, relevant, and specific compared to a baseline, without increasing cognitive load.
arXiv:2606. 10402v1 Announce Type: cross Abstract: Scientific discovery is often a collective process: researchers share partial results, inspect failed attempts, and build on each other's ideas over long time horizons.
arXiv:2606. 12736v1 Announce Type: new Abstract: AI agents are increasingly being developed to accelerate scientific discovery, yet their practical capabilities in real research settings remain poorly understood.
IDRBench is a benchmark designed to evaluate the interactive capabilities of deep research agents that use large language models. It introduces controlled opportunities for clarification within a common workflow, comparing autonomous and interactive trajectories by measuring task‑specific report alignment and interaction cost. Experiments on 100 tasks with seven LLMs show that interaction consistently improves alignment, though its effectiveness varies depending on the agents’ questions and feedback integration.
arXiv:2606. 26614v1 Announce Type: cross Abstract: Large language model (LLM) agents enable natural language interaction for scientific visualization (SciVis).