The paper discusses how large language model (LLM) agents can perform epistemic actions—actions that improve the evidence base before making a decision. It identifies three modes of such actions: acquiring missing evidence, transforming available evidence, and probing the system to generate revealing responses. The authors introduce the concept of epistemic scaffolding, referring to interfaces, tools, and environments that enable and audit these actions, arguing that agent design must explicitly address how decision-ready evidence is produced.
By Yizhi Liu, Balaji Padmanabhan, Siva Viswanathan
arXiv:2609.01588v1 Announce Type: cross
Abstract: Writing involves diverse cognitive activities, from ideation to revision, and writers' needs vary across individuals and moments. Proactive AI promis...
By Chao Zhang, Abe Davis, Chih-Wei Chen, Chin-Chia Hsu
Conversational agents are increasingly embedded in human collaborative work, yet they remain fundamentally passive and reactive: they respond to explicit user requests rather than proactively recognizing moments when a team would benefit from timely intervention as human collaborators often do. This reactive design substantially limits the use of agents as active participants in multi-user collaboration, where disagreements, ambiguous goals, forgotten constraints, underspecified plans, discussion loops, and imbalanced participation can gradually undermine group progress.
The paper introduces a framework for designing proactive large‑language‑model agents, centered on three joint principles—Task Capability, Temporal Allocation, and Trust—alongside a five‑dimensional design space. It proposes PROACTIVITY‑GYM, a simulation testbed for evaluating proactive assistance across multi‑day scenarios, and presents empirical findings that highlight performance gaps and the importance of aligning interventions with user trust. Human studies show that misaligned interventions can sharply reduce trust, even when outcomes are correct, underscoring the need for careful joint optimization of the 3T principles.
By Jio Oh, Seunghyun Do, Young-Jun Lee, Steven Euijong Whang, Dongyeop Kang
arXiv:2608.22266v1 Announce Type: new
Abstract: In the context of information seeking, conversational agents are undergoing an evolution from reactive tools to proactive, personalized assistants. A c...
By Zhihong Cao, Chen Huang
arXiv:2607. 11053v1 Announce Type: cross Abstract: Fruitful collaborations rely on cooperative communications, including of contextual cues to incorporate into reasoning.
By Hannah VanderHoeven, Abhijnan Nath, Nikhil Krishnaswamy
Proactive LLM agents can turn idle compute into useful support before users ask. Yet even correct work can misread user context, impose review costs, or undermine trust. This work proposes foundations...
arXiv:2606. 06388v1 Announce Type: new Abstract: Recent advances in LLM agents have enabled complex cognitive capabilities, such as multi-step reasoning, planning, and tool use, that increasingly position these agents as human collaborators.
By Jiaju Chen, Yuxuan Lu, Jiayi Su, Chaoran Chen, Songlin Xiao, Zheng Zhang, Yun Wang, Yunyao Li, Jian Zhao, Tongshuang Wu, Toby Jia-Jun Li, Dakuo Wang, Bingsheng Yao
arXiv:2606. 09832v1 Announce Type: cross Abstract: As AI systems evolve from single conversational agents to complex multi-agent architectures, a critical design dimension has been overlooked: how the social identity of individual agents shapes human behavior within the collaboration.
By Meng-Han Lee
arXiv:2607. 02975v1 Announce Type: new Abstract: Effective agency in social environments depends on when an agent seeks knowledge, when it acts, and whether its actions are justified by acquired information.
By Dan C. Hsu, Luke Lu
PersonaTeaming introduces a workflow that incorporates personas into adversarial prompt generation for generative AI, achieving higher attack success rates than the state‑of‑the‑art RainbowPlus while preserving prompt diversity. The system is extended into a user‑facing playground that lets red‑teamers create their own personas and collaborate with AI to refine prompts, fostering diverse strategies. A user study with 11 industry practitioners found the playground produced useful outputs and encouraged out‑of‑the‑box thinking, even when suggestions were not strictly followed.
By Wesley Hanwen Deng, Mingxi Yan, Sunnie S. Y. Kim, Akshita Jha, Lauren Wilcox, Kenneth Holstein, Motahhare Eslami, Leon A. Gatys
arXiv:2606. 12268v1 Announce Type: new Abstract: Advanced AI systems have extensive knowledge of their environments; in fact, their knowledge may (far) exceed that of their developers or users.
By Korbinian Friedl, Francis Rhys Ward, Paul Yushin Rapoport, Tom Everitt, Jonathan Richens