As designers become familiar with Generative AI, a new concept is emerging: Agentic AI. While generative AI produces output in response to prompts, agentic AI systems promise to perform mundane tasks autonomously, potentially freeing designers to focus on what they love: being creative. But how do designers feel about integrating agentic AI systems into their workflows? Through design fiction, we investigated how designers want to interact with a collaborative agentic AI platform. Ten professional designers imagined and discussed collaborating with an AI agent to organise inspiration sources and ideate. Our findings highlight the roles AI agents can play in supporting designers, the division of authority between humans and AI, and how designers' intent can be explained to AI agents beyond prompts. We synthesise our findings into a conceptual framework that identifies authority distribution among humans and AI agents and discuss directions for utilising AI agents in future design workflows.

Human-AI collaboration is typically offered in one of two of user control levels: guidance, where the AI provides suggestions and the human makes the final decision, and delegation, where the AI acts autonomously within user-defined constraints. Systems that integrate both modes, common in robotic surgery or driving assistance, often overlook shifts in user preferences within a task in response to factors like evolving trust, decision complexity, and perceived control. In this work, we investigate how users dynamically switch between higher and lower levels of control during a sequential decision-making task. Using a hand-and-brain chess setup, participants either selected a piece and the AI decided how it moved (brain mode), or the AI selected a piece and the participant decided how it moved (hand mode). We collected over 400 mode-switching decisions from eight participants, along with gaze, emotional state, and subtask difficulty data. Statistical analysis revealed significant differences in gaze patterns and subtask complexity prior to a switch and in the quality of the subsequent move. Based on these results, we engineered behavioral and task-specific features to train a lightweight model that predicted control level switches ($F1 = 0.65$). The model performance suggests that real-time behavioral signals can serve as a complementary input alongside system-driven mode-switching mechanisms currently used. We complement our quantitative results with qualitative factors that influence switching including perceived AI ability, decision complexity, and level of control, identified from post-game interview analysis. The combined behavioral and modeling insights can help inform the design of shared autonomy systems that need dynamic, subtask-level control switches aligned with user intent and evolving task demands.

Despite the rapid advancements in LLM agents, they still face the challenge of generating meaningful reflections due to inadequate error analysis and a reliance on rare successful trajectories, especially in complex tasks. In this work, we propose SAMULE, a new framework for self-learning agents powered by a retrospective language model that is trained based on Multi-Level Reflection Synthesis. It first synthesizes high-quality reflections across three complementary levels: Single-Trajectory Learning (micro-level) for detailed error correction; Intra-Task Learning (meso-level) to build error taxonomies across multiple trials of the same task, and Inter-Task Learning (macro-level) to extract transferable insights based on same typed errors from diverse task failures. Then we fine-tune a language model serving as the retrospective model to generate reflections during inference. We further extend our framework to interactive settings through a foresight-based reflection mechanism, enabling agents to proactively reflect and adapt during user interactions by comparing predicted and actual responses. Extensive experiments on three challenging benchmarks - TravelPlanner, NATURAL PLAN, and Tau-bench - demonstrate that our approach significantly outperforms reflection-based baselines. Our results highlight the critical role of well-designed reflection synthesis and failure-centric learning in building self-improving LLM agents.

Recent advances in multi-agent systems (MAS) enable tools for information search and ideation by assigning personas to agents. However, how users can effectively control, steer, and critically evaluate collaboration among multiple domain-expert agents remains underexplored. We present Perspectra, an interactive MAS that visualizes and structures deliberation among LLM agents via a forum-style interface, supporting @-mention to invite targeted agents, threading for parallel exploration, with a real-time mind map for visualizing arguments and rationales. In a within-subjects study with 18 participants, we compared Perspectra to a group-chat baseline as they developed research proposals. Our findings show that Perspectra significantly increased the frequency and depth of critical-thinking behaviors, elicited more interdisciplinary replies, and led to more frequent proposal revisions than the group chat condition. We discuss implications for designing multi-agent tools that scaffold critical thinking by supporting user control over multi-agent adversarial discourse.

Large language models (LLMs) have achieved impressive results in natural language understanding, yet their reasoning capabilities remain limited when operating as single agents. Multi-Agent Debate (MAD) has been proposed to address this limitation by enabling collaborative reasoning among multiple models in a round-table debate manner. While effective, MAD introduces substantial computational overhead due to the number of agents involved and the frequent communication required. In this paper, we propose MARS (Multi-Agent Review System), a role-based collaboration framework inspired by the review process. In MARS, an author agent generates an initial solution, reviewer agents provide decisions and comments independently, and a meta-reviewer integrates the feedback to make the final decision and guide further revision. This design enhances reasoning quality while avoiding costly reviewer-to-reviewer interactions, thereby controlling token consumption and inference time. We compared MARS with both MAD and other state-of-the-art reasoning strategies across multiple benchmarks. Extensive experiments with different LLMs show that MARS matches the accuracy of MAD while reducing both token usage and inference time by approximately 50\%. Code is available at https://github.com/xwang97/MARS.

Generative flow networks utilize a flow-matching loss to learn a stochastic policy for generating objects from a sequence of actions, such that the probability of generating a pattern can be proportional to the corresponding given reward. However, a theoretical framework for multi-agent generative flow networks (MA-GFlowNets) has not yet been proposed. In this paper, we propose the theory framework of MA-GFlowNets, which can be applied to multiple agents to generate objects collaboratively through a series of joint actions. We further propose four algorithms: a centralized flow network for centralized training of MA-GFlowNets, an independent flow network for decentralized execution, a joint flow network for achieving centralized training with decentralized execution, and its updated conditional version. Joint Flow training is based on a local-global principle allowing to train a collection of (local) GFN as a unique (global) GFN. This principle provides a loss of reasonable complexity and allows to leverage usual results on GFN to provide theoretical guarantees that the independent policies generate samples with probability proportional to the reward function. Experimental results demonstrate the superiority of the proposed framework compared to reinforcement learning and MCMC-based methods.