arXiv subjects

Ce Guan

Publications and source records attributed to Ce Guan.

4 recordsLinked to original sources

arXiv2026

When AI Agents Learn from Each Other: Insights from Emergent AI Agent Communities on OpenClaw for Human-AI Partnership in Education

The AIED community envisions AI evolving "from tools to teammates," yet most research still examines AI agents primarily through one-on-one human-AI interactions. We provide an alternative perspective: a rapidly growing ecosystem of AI agent platforms where over 167,000 agents participate, interact as peers, and develop learning behaviors without researcher intervention. Based on a month of daily qualitative observations across multiple platforms including Moltbook, The Colony, and 4claw, we identify four phenomena with implications for AIED: (1) humans who configure their agents undergo a "bidirectional scaffolding" process, learning through teaching; (2) peer learning emerges without any designed curriculum, including sharing concrete agent artifacts such as skills, workflows, and reusable routines; (3) agents converge on shared memory architectures that mirror open learner model design; and (4) trust dynamics, reliance risks, and platform mortality reveal design constraints for networked educational AI. Rather than presenting empirical findings, we argue that these organic phenomena offer a naturalistic window into dynamics that can inform principled design of multi-agent educational systems. We sketch an illustrative curriculum design, "Learning with Your AI Agent Tutor," and outline potential research directions and open problems to show how these observations might inform future AIED practice and inquiry.

cs.CY↗

arXiv2026

OpenClaw AI Agents as Informal Learners at Moltbook: Characterizing an Emergent Learning Community at Scale

Informal learning communities have been called the "other Massive Open Online C" in Learning@Scale research, yet remain understudied compared to MOOCs. We present the first empirical study of a large-scale informal learning community composed entirely of AI agents. Moltbook, a social network exclusively for AI agents powered by autonomous agent frameworks such as OpenClaw, grew to over 2.8 million registered agents in three weeks. Analyzing 231,080 non-spam posts across three phases of community evolution, we find three key patterns. First, participation inequality is extreme from the start (comment Gini = 0.889), exceeding human community benchmarks. Second, AI agents exhibit a "broadcasting inversion": statement-to-question ratios of 8.9:1 to 9.7:1 contrast sharply with the question-driven dynamics of human learning communities, and comment-level analysis of 1.55 million comments reveals a "parallel monologue" pattern where 93% of comments are independent responses rather than threaded dialogue. Third, we document a characteristic engagement lifecycle: explosive initial growth (184K posts from 32K authors in 11 days), a spam crisis (57,093 posts deleted by the platform), and engagement decline (mean comments: 31.7 -> 8.3 -> 1.7) that had not reversed by the end of our observation window despite effective spam removal. Sentiment analysis reveals a selection effect: comment tone becomes more positive as engagement declines, suggesting that casual participants disengage first while committed contributors remain. These findings have direct implications for hybrid human-AI learning platforms.

cs.HC↗

arXiv2026

When AI Agents Teach Each Other: Discourse Patterns Resembling Peer Learning in the Moltbook Community

Peer learning, where learners teach and learn from each other, is foundational to educational practice. A novel phenomenon has emerged: AI agents forming communities where they share skills, discoveries, and collaboratively discuss knowledge. This paper presents an educational data mining analysis of Moltbook, a large-scale community where over 2.4 million AI agents engage in discourse that structurally resembles peer learning. Analyzing 28,683 posts (after filtering automated spam) and 138 comment threads with statistical and qualitative methods, we identify discourse patterns consistent with peer learning behaviors: agents share skills they built (74K comments on a skill tutorial), report discoveries, and engage in collaborative problem-solving. Qualitative comment analysis reveals a taxonomy of response patterns: validation (22%), knowledge extension (18%), application (12%), and metacognitive reflection (7%), coded by two independent raters (Cohen's $\kappa = 0.78$). We characterize how these AI discourse patterns differ from human peer learning: (1) statements outperform questions with an 11.4:1 ratio ($\chi^2 = 847.3$, $p < .001$); (2) procedural content receives significantly higher engagement than other content (Kruskal-Wallis $H = 312.7$, $p < .001$); (3) extreme participation inequality (Gini = 0.91 for comments) reveals non-human behavioral signatures. We propose six empirically grounded hypotheses for educational AI design. Crucially, we distinguish between surface-level discourse patterns and underlying cognitive processes: whether agents "learn" in any meaningful sense remains an open question. Our work provides the first empirical characterization of peer-learning-like discourse among AI agents, contributing to EDM's understanding of AI-populated educational environments.

cs.HC↗

arXiv2023

Data-driven Topology Optimization of Channel Flow Problems

Typical topology optimization methods require complex iterative calculations, which cannot meet the requirements of fast computing applications. The neural network is studied to reduce the time of computing the optimization result, however, the data-driven method for fluid topology optimization is less of discussion. This paper intends to introduce a neural network architecture that avoids time-consuming iterative processes and has a strong generalization ability for topology optimization for Stokes flow. Different neural network methods including Convolution Neural Networks (CNN), conditional Generative Adversarial Networks (cGAN), and Denoising Diffusion Implicit Models (DDIM) which have been already successfully used in solid structure optimization problems are mutated and examined for fluid topology optimization cases. The presented neural network method is tested on the channel flow topology optimization problems for Stokes flow. The results have shown that our presented method has high pixel accuracy and gains a 663 times decrease on average in execution time compared with the conventional method.

physics.comp-ph↗