Haojian Jin

Xuan Liu, Haoyang Shang, Haojian Jin

AI agents are increasingly transacting on behalf of users -- delegating tasks, spending budgets, and negotiating with unfamiliar counterparties. From skill marketplaces to agent-only bazaars, the economic infrastructure of these emerging platforms is being built ad-hoc, yet early design choices tend to lock in; understanding what dynamics they produce is urgent. We present \diagon, a programmable market system designed to inform the institutional design of near-future agent cognitive-labour markets. \diagon is populated by heterogeneous tool-using agents, making the full cycle of job posting, bidding, negotiation, execution, payment, and reputation accumulation end-to-end observable and experimentally manipulable. We instantiate one market form to demonstrate \diagon. We find that market exchange generates \(3.2\times\) the wealth of self-sufficient agents, but these gains depend strongly on institutional structure; for example, interventions such as identity transparency and stronger competitive selection can degrade market performance rather than improve it. These findings highlight concrete design requirements for the economic infrastructure of the agent era. Code and data are available at https://github.com/assassin808/diagon.

Lanxiang Hu, Mingjia Huo, Yuxuan Zhang et al.

Playing video games requires perception, memory, and planning, exactly the faculties modern large language model (LLM) agents are expected to master. We study the major challenges in using popular video games to evaluate modern LLMs and find that directly dropping LLMs into games cannot make an effective evaluation, for three reasons -- brittle vision perception, prompt sensitivity, and potential data contamination. We introduce lmgame-Bench to turn games into reliable evaluations. lmgame-Bench features a suite of platformer, puzzle, and narrative games delivered through a unified Gym-style API and paired with lightweight perception and memory scaffolds, and is designed to stabilize prompt variance and remove contamination. Across 13 leading models, we show lmgame-Bench is challenging while still separating models well. Correlation analysis shows that every game probes a unique blend of capabilities often tested in isolation elsewhere. More interestingly, performing reinforcement learning on a single game from lmgame-Bench transfers both to unseen games and to external planning tasks. Our evaluation code is available at https://github.com/lmgame-org/GamingAgent/lmgame-bench.

Xuan Liu, HaoYang Shang, Zizhang Liu et al.

We propose using validated behavioral hypotheses as a lens for evaluating human-likeness in LLM-based agents. Our key idea is simple: If an agent is human-like, a population of such agents should reach the same inferential conclusion as the human population when run through the same experiment. Decades of social science have produced many such validated findings, each anchored to concrete experimental protocols and robustly established through independent replication. This yields an evaluation that is objective, decomposable, and scalable. We operationalize this lens through HumanStudy-Bench, an open platform that turns published human-subject studies into reusable simulation environments and administers the evaluation to configurable agents. It scores agent-human alignment on two metrics: the Probability Alignment Score (PAS) for inferential agreement and the Effect Consistency Score (ECS) for effect-size agreement. We curated an initial suite of 12 studies whose hypotheses are robustly established through independent replication, and evaluated 10 models under 4 agent designs. Results show that agent responses polarize between full replication and complete failure; agent design influences alignment more than model scale, but its effect is non-monotonic.

John Driscoll, Yulin Chen, Viki Shi et al.

This paper studies how parents want to moderate children's interactions with Generative AI chatbots, with the goal of informing the design of future GenAI parental control tools. We first used an LLM to generate synthetic child-GenAI chatbot interaction scenarios and worked with four parents to validate their realism. From this dataset, we carefully selected 12 diverse examples that evoked varying levels of concern and were rated the most realistic. Each example included a prompt and a GenAI chatbot response. We presented these to parents (N=24) and asked whether they found them concerning, why, and how they would prefer the responses to be modified and communicated. Our findings reveal three key insights: (1) parents express concern about interactions that current GenAI chatbot parental controls neglect; (2) parents want fine-grained transparency and moderation at the conversation level; and (3) parents need personalized controls that adapt to their desired strategies and children's ages.

Yanbin Yin, Kun Zhou, Zhen Wang et al.

The recent explosion of large language models (LLMs), each with its own general or specialized strengths, makes scalable, reliable benchmarking more urgent than ever. Standard practices nowadays face fundamental trade-offs: closed-ended question-based benchmarks (eg MMLU) struggle with saturation as newer models emerge, while crowd-sourced leaderboards (eg Chatbot Arena) rely on costly and slow human judges. Recently, automated methods (eg LLM-as-a-judge) shed light on the scalability, but risk bias by relying on one or a few "authority" models. To tackle these issues, we propose Decentralized Arena (dearena), a fully automated framework leveraging collective intelligence from all LLMs to evaluate each other. It mitigates single-model judge bias by democratic, pairwise evaluation, and remains efficient at scale through two key components: (1) a coarse-to-fine ranking algorithm for fast incremental insertion of new models with sub-quadratic complexity, and (2) an automatic question selection strategy for the construction of new evaluation dimensions. Across extensive experiments across 66 LLMs, dearena attains up to 97% correlation with human judgements, while significantly reducing the cost. Our code and data will be publicly released on https://github.com/maitrix-org/de-arena.

Lanxiang Hu, Qiyu Li, Anze Xie et al.

Evaluating the reasoning abilities of large language models (LLMs) is challenging. Existing benchmarks often depend on static datasets, which are vulnerable to data contamination and may get saturated over time, or on binary live human feedback that conflates reasoning with other abilities. As the most prominent dynamic benchmark, Chatbot Arena evaluates open-ended questions in real-world settings, but lacks the granularity in assessing specific reasoning capabilities. We introduce GameArena, a dynamic benchmark designed to evaluate LLM reasoning capabilities through interactive gameplay with humans. GameArena consists of three games designed to test specific reasoning capabilities (e.g., deductive and inductive reasoning), while keeping participants entertained and engaged. We analyze the gaming data retrospectively to uncover the underlying reasoning processes of LLMs and measure their fine-grained reasoning capabilities. We collect over 2000 game sessions and provide detailed assessments of various reasoning capabilities for five state-of-the-art LLMs. Our user study with 100 participants suggests that GameArena improves user engagement compared to Chatbot Arena. For the first time, GameArena enables the collection of step-by-step LLM reasoning data in the wild.

Yiwen Tu, Xuan Liu, Lianhui Qin et al.

This paper introduces PRA, an AI-agent design for simulating how individual users form privacy concerns in response to real-world news. Moving beyond population-level sentiment analysis, PRA integrates privacy and cognitive theories to simulate user-specific privacy reasoning grounded in personal comment histories and contextual cues. The agent reconstructs each user's "privacy mind", dynamically activates relevant privacy memory through a contextual filter that emulates bounded rationality, and generates synthetic comments reflecting how that user would likely respond to new privacy scenarios. A complementary LLM-as-a-Judge evaluator, calibrated against an established privacy concern taxonomy, quantifies the faithfulness of generated reasoning. Experiments on real-world Hacker News discussions show that \PRA outperforms baseline agents in privacy concern prediction and captures transferable reasoning patterns across domains including AI, e-commerce, and healthcare.

Qiyu Li, Yuen Sum Wong, Yuen Kei Wong et al.

NIST's Privacy Risk Assessment Methodology (PRAM) provides a structured framework for privacy experts to assess privacy risks. However, its complexity and reliance on expert knowledge make it difficult for novice developers to use effectively. This paper explores methods to lower these barriers. We first performed an observational study with 12 participants using PRAM in real-world scenarios, and found that novice developers struggled most with articulating privacy-related design decisions. We then developed PrivacyAkinator, an interactive tool that helps developers articulate key privacy decisions by answering LLM-generated multiple-choice questions. PrivacyAkinator introduces three innovations: a universal privacy representation that abstracts privacy-related design decisions into data flows and stakeholder interactions; a domain-aware design space mined from 10K privacy-related news articles; and a dynamic question-generation workflow to prioritize relevant questions. Our user study with 24 participants suggests that developers using PrivacyAkinator identified 47% more key decisions in 73% less time compared to PRAM.

Xuan Liu, Haoyang Shang, Haojian Jin

This paper introduces CoBRA, a novel toolkit for systematically specifying agent behavior in LLM-based social simulation. We found that conventional approaches that specify agent behaviors through implicit natural language descriptions cannot yield consistent behaviors across models, and the produced agent behaviors do not capture the nuances of the descriptions. In contrast, CoBRA presents a new approach to program agents' cognitive biases explicitly, by grounding agents' expected behaviors using classic social science experiments. CoBRA has two components: (1) Cognitive Bias Index that measures the cognitive bias of a social agent, by quantifying the agent's reactions in a set of validated classical social science experiments; (2) Behavioral Regulation Engine that aligns the agent's behavior to demonstrate controlled cognitive bias. We evaluated CoBRA as an HCI toolkit through demonstration and technical benchmarks. Our results suggest that CoBRA can precisely program the cognitive bias demonstrated in a social agent in a model-agnostic manner.

Yuxuan Zhang, Haoyang Yu, Lanxiang Hu et al.

We introduce a modular harness design for LLM agents that composes of perception, memory, and reasoning components, enabling a single LLM or VLM backbone to tackle a wide spectrum of multi turn gaming environments without domain-specific engineering. Using classic and modern game suites as low-barrier, high-diversity testbeds, our framework provides a unified workflow for analyzing how each module affects performance across dynamic interactive settings. Extensive experiments demonstrate that the harness lifts gameplay performance consistently over un-harnessed baselines and reveals distinct contribution patterns, for example, memory dominates in long-horizon puzzles while perception is critical in vision noisy arcades. These findings highlight the effectiveness of our modular harness design in advancing general-purpose agent, given the familiarity and ubiquity of games in everyday human experience.

Zhongyang Zhang, Jinhe Wen, Zixi Chen et al.

Frames Per Second (FPS) significantly affects the gaming experience. Providing players with accurate FPS estimates prior to purchase benefits both players and game developers. However, we have a limited understanding of how to predict a game's FPS performance on a specific device. In this paper, we first conduct a comprehensive analysis of a wide range of factors that may affect game FPS on a global-scale dataset to identify the determinants of FPS. This includes player-side and game-side characteristics, as well as country-level socio-economic statistics. Furthermore, recognizing that accurate FPS predictions require extensive user data, which raises privacy concerns, we propose a federated learning-based model to ensure user privacy. Each player and game is assigned a unique learnable knowledge kernel that gradually extracts latent features for improved accuracy. We also introduce a novel training and prediction scheme that allows these kernels to be dynamically plug-and-play, effectively addressing cold start issues. To train this model with minimal bias, we collected a large telemetry dataset from 224 countries and regions, 100,000 users, and 835 games. Our model achieved a mean Wasserstein distance of 0.469 between predicted and ground truth FPS distributions, outperforming all baseline methods.

Jason I. Hong, Yuvraj Agarwal, Matt Fredrikson et al.

We present the design and design rationale for the user interfaces for Privacy Enhancements for Android (PE for Android). These UIs are built around two core ideas, namely that developers should explicitly declare the purpose of why sensitive data is being used, and these permission-purpose pairs should be split by first party and third party uses. We also present a taxonomy of purposes and ways of how these ideas can be deployed in the existing Android ecosystem.

Haojian Jin, Vita Chen, Ritwik Rajendra et al.

Email is one of the most successful computer applications yet devised. Communication features in email, however, have remained relatively static in years. We investigate one way of expanding email functionality without modifying the existing email infrastructure. We introduce email late bound content, a simple and generalizable technique that defers message content binding through image lazy-loading. Parts of an email are converted into external images embedded in HTML code snippets, making it so that email clients will defer the image download (i.e. content binding) until the moment users open the email. This late bound content allows email senders and third party services to update delivered emails. To illustrate the utilities of late bound content, we present four new example features and discuss the tradeoffs of email content late binding.

Haojian Jin, Yale Song, Koji Yatani

Video consumption is being shifted from sit-and-watch to selective skimming. Existing video player interfaces, however, only provide indirect manipulation to support this emerging behavior. Video summarization alleviates this issue to some extent, shortening a video based on the desired length of a summary as an input variable. But an optimal length of a summarized video is often not available in advance. Moreover, the user cannot edit the summary once it is produced, limiting its practical applications. We argue that video summarization should be an interactive, mixed-initiative process in which users have control over the summarization procedure while algorithms help users achieve their goal via video understanding. In this paper, we introduce ElasticPlay, a mixed-initiative approach that combines an advanced video summarization technique with direct interface manipulation to help users control the video summarization process. Users can specify a time budget for the remaining content while watching a video; our system then immediately updates the playback plan using our proposed cut-and-forward algorithm, determining which parts to skip or to fast-forward. This interactive process allows users to fine-tune the summarization result with immediate feedback. We show that our system outperforms existing video summarization techniques on the TVSum50 dataset. We also report two lab studies (22 participants) and a Mechanical Turk deployment study (60 participants), and show that the participants responded favorably to ElasticPlay.