The computational role of imagination remains debated. While classical accounts emphasize reward maximization, emerging evidence suggests imagination serves a broader function: accessing internal world models (IWMs). Here, we employ psychological network analysis to compare IWMs in humans and large language models (LLMs) through imagination vividness ratings. Using the Vividness of Visual Imagery Questionnaire (VVIQ-2) and Plymouth Sensory Imagery Questionnaire (PSIQ), we construct imagination networks from three human populations (Florida, Poland, London; N=2,743) and six LLM variants in two conversation conditions. Human imagination networks demonstrate robust correlations across centrality measures (expected influence, strength, closeness) and consistent clustering patterns, indicating shared structural organization of IWMs across populations. In contrast, LLM-derived networks show minimal clustering and weak centrality correlations, even when manipulating conversational memory. These systematic differences persist across environmental scenes (VVIQ-2) and sensory modalities (PSIQ), revealing fundamental disparities between human and artificial world models. Our network-based approach provides a quantitative framework for comparing internally-generated representations across cognitive agents, with implications for developing human-like imagination in artificial intelligence systems.

We study what actually works and what doesn't for training large language models as agents via multi-turn reinforcement learning. Despite rapid progress, existing frameworks and definitions are fragmented, and there is no systematic formulation or analysis of which design choices matter across tasks. We address this gap by first breaking down the design space into three inter-related pillars--environment, reward, and policy--and empirically derive a recipe for training LLM agents in situated textual domains. In particular, we test TextWorld and ALFWorld, popular domains for testing situated embodied reasoning, as well as SWE-Gym for more software engineering style tasks. Training LLMs as autonomous agents to navigate open-ended environments presents unique challenges: planning across extended horizons, making multi-turn sequential decisions, and optimizing for multi-turn rewards. The transition from static single-turn problem-solving to dynamic multi-step reasoning is essential for agentic benchmarks such as interactive text and embodied simulations (TextWorld (C ˆ ot e et al., 2018), ALFWorld (Shridhar et al., 2021), etc.), real-world software programming (OSWorld (Xie et al., 2024), SWE-gym (Pan et al., 2025), etc.), and abstract reasoning in novel situations (ARC-AGI (Chollet et al., 2025)). However, existing multi-turn RL implementations vary widely: some refer to tool-augmented single queries as multi-turn (Zeng et al., 2025), while many rely on model-based assumptions (Wang et al., 2025). This fragmentation has led to incomparable results across papers and confusion about what constitutes true multi-turn learning versus pseudo-multi-turn adaptations of single-turn methods. This paper aims to facilitate research efforts on the open research question: What factors are practically important in making multi-turn RL for LLM agent learning work. Motivated by the lack of standardization of multi-turn RL approaches, we systematically decompose the design space into three interdependent pillars--environment, reward, and policy--and empirically derive a recipe for training LLM agents in situated textual domains (Figure 1). We evaluate our approach on TextWorld and ALFWorld for embodied reasoning, and SWE-gym for real-world programming, revealing critical insights for each pillar.

Identifying key temporal intervals within long videos, known as temporal grounding (TG), is important to video understanding and reasoning tasks. In this paper, we introduce a new form of the temporal grounding problem, \textbf{Task-oriented Temporal Grounding} (\textbf{ToTG}), which is driven by the requirements of downstream tasks rather than explicit time-interval descriptions. For example, a ToTG input may be "explain why the man in the video is sent to the hospital," whereas traditional TG would take an explicit temporal description such as "the moments when the man is tripped by a stone and falls to the ground." This new ToTG formulation presents significant challenges for existing TG methods, as it requires jointly performing deep task comprehension and fine-grained temporal localization within long videos. To address these challenges, we conduct a systematic set of studies. First, we construct \textbf{a new benchmark ToTG-Bench}, which comprehensively evaluates ToTG performance across diverse settings. Second, we introduce \textbf{a new temporal-ground method TimeScope}, which performs coarse-to-fine localization through a progressive reasoning process. Leveraging extensive supervised fine-tuning with carefully curated chain-of-thought (CoT) data from a variety of scenarios, TimeScope generalizes effectively across tasks and domains. Our evaluation demonstrates \textbf{TimeScope's empirical advantages} over existing baselines from three perspectives: (1) substantial improvements in grounding precision, (2) significant benefits to downstream tasks, and (3) strong generalizability across different scenarios. All models, datasets, and source code will be fully open-sourced to support future research in this area.

This paper explores adaptive problem solving with a game designed to support the development of problem-solving skills. Using an adaptive, AI-powered puzzle game, our adaptive problem-solving system dynamically generates pathfinding-based puzzles using a genetic algorithm, tailoring the difficulty of each puzzle to individual players in an online real-time approach. A player-modeling system records user interactions and informs the generation of puzzles to approximate a target difficulty level based on various metrics of the player. By combining procedural content generation with online adaptive difficulty adjustment, the system aims to maintain engagement, mitigate frustration, and maintain an optimal level of challenge. A pilot user study investigates the effectiveness of this approach, comparing different types of adaptive difficulty systems and interpreting players' responses. This work lays the foundation for further research into emotionally informed player models, advanced AI techniques for adaptivity, and broader applications beyond gaming in educational settings.

Tool agents interact with users through multi-turn dialogues to accomplish various tasks. Recent studies have adopted user simulation methods to develop these agents in multi-turn settings. However, existing user simulators tend to be agent-friendly, exhibiting only cooperative behaviors, which fails to train and test agents against non-collaborative users in the real world. To address this, we propose a novel user simulator architecture that simulates four categories of non-collaborative behaviors: requesting unavailable services, digressing into tangential conversations, expressing impatience, and providing incomplete utterances. Our user simulator can simulate challenging and natural non-collaborative behaviors while reliably delivering all intents and information necessary to accomplish the task. Our experiments on MultiWOZ and $τ$-bench reveal significant performance degradation in state-of-the-art tool agents when encountering non-collaborative users. We provide detailed analyses of agents' weaknesses under each non-collaborative condition, such as escalated hallucinations and dialogue breakdowns. Ultimately, we contribute an easily extensible user simulation framework to help the research community develop tool agents and preemptively diagnose them under challenging real-world conditions within their own services.

As Artificial Intelligence (AI) becomes increasingly integrated into daily life, there is a growing need to equip the next generation with the ability to apply, interact with, evaluate, and collaborate with AI systems responsibly. Prior research highlights the urgent demand from K-12 educators to teach students the ethical and effective use of AI for learning. To address this need, we designed an Large-Language Model (LLM)-based module to teach prompting literacy. This includes scenario-based deliberate practice activities with direct interaction with intelligent LLM agents, aiming to foster secondary school students' responsible engagement with AI chatbots. We conducted two iterations of classroom deployment in 11 authentic secondary education classrooms, and evaluated 1) AI-based auto-grader's capability; 2) students' prompting performance and confidence changes towards using AI for learning; and 3) the quality of learning and assessment materials. Results indicated that the AI-based auto-grader could grade student-written prompts with satisfactory quality. In addition, the instructional materials supported students in improving their prompting skills through practice and led to positive shifts in their perceptions of using AI for learning. Furthermore, data from Study 1 informed assessment revisions in Study 2. Analyses of item difficulty and discrimination in Study 2 showed that True/False and open-ended questions could measure prompting literacy more effectively than multiple-choice questions for our target learners. These promising outcomes highlight the potential for broader deployment and highlight the need for broader studies to assess learning effectiveness and assessment design.

Multimodal Large Language Models (MLLMs) have demonstrated remarkable proficiency in multimodal tasks. Despite their impressive performance, MLLMs suffer from the modality imbalance issue, where visual information is often underutilized compared to textual representations in deeper layers, leading to degraded visual performance or hallucinations. This issue stems from the predominant reliance on next-text-token-prediction during training, which fails to provide direct visual supervisory signals, resulting in progressive homogenization of visual representations throughout the layers. To this end, we propose Latent Visual Reconstruction (LaVer), a novel training framework that facilitates MLLMs in learning more discriminative visual representations via masked image modeling in the joint latent semantic space of LLM. Our method offers direct visual activation to MLLMs, which exhibit increased visual attention allocation, indicating enhanced utilization of visual information. Extensive experiments across diverse benchmarks prove the superiority of our approach in various scenarios, especially those requiring dense visual capabilities. Code of LaVer is available at https://github.com/Fir-lat/LaVer.

We present Nanbeige4-3B, a family of small-scale but high-performing language models. Pretrained on 23T high-quality tokens and finetuned on over 30 million diverse instructions, we extend the boundary of the scaling law for small language models. In pre-training, we design a Fine-Grained Warmup-Stable-Decay (FG-WSD) training scheduler, which progressively refines data mixtures across stages to boost model performance. In post-training, to improve the quality of the SFT data, we design a joint mechanism that integrates deliberative generation refinement and chain-of-thought reconstruction, yielding substantial gains on complex tasks. Following SFT, we employ our flagship reasoning model to distill Nanbeige4-3B through our proposed Dual Preference Distillation (DPD) method, which leads to further performance gains. Finally, a multi-stage reinforcement learning phase was applied, leveraging verifiable rewards and preference modeling to strengthen abilities on both reasoning and human alignment. Extensive evaluations show that Nanbeige4-3B not only significantly outperforms models of comparable parameter scale but also rivals much larger models across a wide range of benchmarks. The model checkpoints are available at https://huggingface.co/Nanbeige.

Sentence simplification aims to modify a sentence to make it easier to read and understand while preserving the meaning. Different applications require distinct simplification policies, such as replacing only complex words at the lexical level or rewriting the entire sentence while trading off details for simplicity. However, achieving such policy-driven control remains an open challenge. In this work, we introduce a simple yet powerful approach that leverages Large Language Model-as-a-Judge (LLM-as-a-Judge) to automatically construct policy-aligned training data, completely removing the need for costly human annotation or parallel corpora. Our method enables building simplification systems that adapt to diverse simplification policies. Sentence simplification could benefit users with reading difficulties, such as second-language (L2) learners and people with reading impairments (e.g., dyslexic individuals), by making text easier to read and understand (Alva-Manchego et al., 2020b). It involves a series of edits, such as lexical paraphrasing, sentence splitting, and removing irrelevant details (Xu et al., 2015). The preferred edit policy, i.e., permissible or appropriate edits in given texts, varies significantly depending on the target audience. In L2 education, one of the major application areas for simplification, previous work in both NLP and language education research has shown that the desired type and degree of simplification edits change depending on learner proficiency and readability levels (Agrawal et al., 2021; Zhong et al., 2020). Specifically, low-to intermediate-level learners benefit from a combination of lexical paraphrasing, structural modifications, and selective deletions to reduce cognitive load. In contrast, advanced learners benefit from lexical paraphrasing, which supports vocabulary acquisition (Chen, 2019), but they gain comparatively less from added cohesion or deletion (Hosoda, 2016; Zhong et al., 2020). Motivated by these findings, we introduce two distinct edit policies. As illustrated in Table 1, overall-rewriting simplification often combines lexical paraphrasing, structural modifications, and deletions to improve readability for intermediate-level language learners. In contrast, lexical-paraphrasing (Paetzold & Specia, 2016; Li et al., 2025) adheres to the original sentence closely while supporting more efficient vocabulary acquisition for advanced learners.

What if users could meet their future selves today? AI-generated future selves simulate meaningful encounters with a digital twin decades in the future. As AI systems advance, combining cloned voices, age-progressed facial rendering, and autobiographical narratives, a central question emerges: Does the modality of these future selves alter their psychological and affective impact? How might a text-based chatbot, a voice-only system, or a photorealistic avatar shape present-day decisions and our feeling of connection to the future? We report a randomized controlled study (N=92) evaluating three modalities of AI-generated future selves (text, voice, avatar) against a neutral control condition. We also report a systematic model evaluation between Claude 4 and three other Large Language Models (LLMs), assessing Claude 4 across psychological and interaction dimensions and establishing conversational AI quality as a critical determinant of intervention effectiveness. All personalized modalities strengthened Future Self-Continuity (FSC), emotional well-being, and motivation compared to control, with avatar producing the largest vividness gains, yet with no significant differences between formats. Interaction quality metrics, particularly persuasiveness, realism, and user engagement, emerged as robust predictors of psychological and affective outcomes, indicating that how compelling the interaction feels matters more than the form it takes. Content analysis found thematic patterns: text emphasized career planning, while voice and avatar facilitated personal reflection. Claude 4 outperformed ChatGPT 3.5, Llama 4, and Qwen 3 in enhancing psychological, affective, and FSC outcomes.