arXiv subjects

Michael Yang

Publications and source records attributed to Michael Yang.

At least 19 recordsLinked to original sources

arXiv2026

Harbor Adapters and Harbor-Index: Infrastructure and a Curated Meta-Dataset for Large-Scale Agentic Evaluation

Evaluating agents on the growing number of agentic benchmarks is challenging because they often require complex environments and agent integrations. We introduce Harbor Adapters, a unified evaluation infrastructure for agentic benchmarks. Our work makes three contributions. First, we develop benchmark adapters that port more than 80 benchmarks to evaluate arbitrary agents, and validate them through rigorous code review and parity experiments. Second, we conduct a large-scale evaluation of 8 models spanning capability tiers across 54 benchmarks; every model is run with Terminus-2 and with one of 3 native harnesses. This enables a broader analysis of agent capabilities and failure modes than was previously possible. Third, we introduce Harbor-Index, a curated set of 82 difficult, diverse, and high-quality tasks spanning 29 benchmarks, refined from the adapted suite through difficulty filtering, AI and human audit, and an audit-and-fix loop. Harbor-Index preserves the challenge and breadth of large-scale agentic evaluations while being affordable to run; no evaluated model-harness configuration exceeds 30% pass rate, and the strongest (GPT-5.5 with Codex) reaches 28.0%. We release the adapters, evaluation results, in-depth analysis, and Harbor-Index as open-source artifacts to support more reliable and comprehensive evaluation of language-model agents.

cs.AI↗

arXiv2026

DevOps-Gym: Benchmarking AI Agents in Software DevOps Cycle

Even though demonstrating extraordinary capabilities in code generation and software issue resolving, AI agents' capabilities in the full software DevOps cycle are still unknown. Different from pure code generation, handling the DevOps cycle in real-world software, including developing, deploying, and managing, requires analyzing large-scale projects, understanding dynamic program behaviors, leveraging domain-specific tools, and making sequential decisions. However, existing benchmarks focus on isolated problems and lack environments and tool interfaces for DevOps. We introduce DevOps-Gym, the first end-to-end benchmark for evaluating AI agents across core DevOps workflows: build and configuration, monitoring, issue resolving, and test generation. DevOps-Gym includes 700+ real-world tasks collected from 30+ projects in Java and Go. We develop a semi-automated data collection mechanism with rigorous and non-trivial expert efforts in ensuring the task coverage and quality. Our evaluation of state-of-the-art models and agents reveals fundamental limitations: they struggle with issue resolving and test generation in Java and Go, and remain unable to handle new tasks such as monitoring and build and configuration. These results highlight the need for essential research in automating the full DevOps cycle with AI agents.

cs.SE↗

arXiv2026

Terminal-Bench: Benchmarking Agents on Hard, Realistic Tasks in Command Line Interfaces

AI agents may soon become capable of autonomously completing valuable, long-horizon tasks in diverse domains. Current benchmarks either do not measure real-world tasks, or are not sufficiently difficult to meaningfully measure frontier models. To this end, we present Terminal-Bench 2.0: a carefully curated hard benchmark composed of 89 tasks in computer terminal environments inspired by problems from real workflows. Each task features a unique environment, human-written solution, and comprehensive tests for verification. We show that frontier models and agents score less than 65\% on the benchmark and conduct an error analysis to identify areas for model and agent improvement. We publish the dataset and evaluation harness to assist developers and researchers in future work at https://www.tbench.ai/ .

cs.SE↗

arXiv2025

Sell Data to AI Algorithms Without Revealing It: Secure Data Valuation and Sharing via Homomorphic Encryption

The rapid expansion of Artificial Intelligence is hindered by a fundamental friction in data markets: the value-privacy dilemma, where buyers cannot verify a dataset's utility without inspection, yet inspection may expose the data (Arrow's Information Paradox). We resolve this challenge by introducing the Trustworthy Influence Protocol (TIP), a privacy-preserving framework that enables prospective buyers to quantify the utility of external data without ever decrypting the raw assets. By integrating Homomorphic Encryption with gradient-based influence functions, our approach allows for the precise, blinded scoring of data points against a buyer's specific AI model. To ensure scalability for Large Language Models (LLMs), we employ low-rank gradient projections that reduce computational overhead while maintaining near-perfect fidelity to plaintext baselines, as demonstrated across BERT and GPT-2 architectures. Empirical simulations in healthcare and generative AI domains validate the framework's economic potential: we show that encrypted valuation signals achieve a high correlation with realized clinical utility and reveal a heavy-tailed distribution of data value in pre-training corpora where a minority of texts drive capability while the majority degrades it. These findings challenge prevailing flat-rate compensation models and offer a scalable technical foundation for a meritocratic, secure data economy.

cs.CR↗

arXiv2025

Explainable AI-Generated Image Detection RewardBench

Conventional, classification-based AI-generated image detection methods cannot explain why an image is considered real or AI-generated in a way a human expert would, which reduces the trustworthiness and persuasiveness of these detection tools for real-world applications. Leveraging Multimodal Large Language Models (MLLMs) has recently become a trending solution to this issue. Further, to evaluate the quality of generated explanations, a common approach is to adopt an "MLLM as a judge" methodology to evaluate explanations generated by other MLLMs. However, how well those MLLMs perform when judging explanations for AI-generated image detection generated by themselves or other MLLMs has not been well studied. We therefore propose \textbf{XAIGID-RewardBench}, the first benchmark designed to evaluate the ability of current MLLMs to judge the quality of explanations about whether an image is real or AI-generated. The benchmark consists of approximately 3,000 annotated triplets sourced from various image generation models and MLLMs as policy models (detectors) to assess the capabilities of current MLLMs as reward models (judges). Our results show that the current best reward model scored 88.76\% on this benchmark (while human inter-annotator agreement reaches 98.30\%), demonstrating that a visible gap remains between the reasoning abilities of today's MLLMs and human-level performance. In addition, we provide an analysis of common pitfalls that these models frequently encounter. Code and benchmark are available at https://github.com/RewardBench/XAIGID-RewardBench.

cs.CV↗

arXiv2025

ICEPool: Enhancing Graph Pooling Networks with Inter-cluster Connectivity

Hierarchical Pooling Models have demonstrated strong performance in classifying graph-structured data. While numerous innovative methods have been proposed to design cluster assignments and coarsening strategies, the relationships between clusters are often overlooked. In this paper, we introduce Inter-cluster Connectivity Enhancement Pooling (ICEPool), a novel hierarchical pooling framework designed to enhance model's understanding of inter-cluster connectivity and ability of preserving the structural integrity in the original graph. ICEPool is compatible with a wide range of pooling-based GNN models. The deployment of ICEPool as an enhancement to existing models effectively combines the strengths of the original model with ICEPool's capability to emphasize the integration of inter-cluster connectivity, resulting in a more comprehensive and robust graph-level representation. Moreover, we make theoretical analysis to ICEPool's ability of graph reconstruction to demonstrate its effectiveness in learning inter-cluster relationship that is overlooked by conventional models. Finally, the experimental results show the compatibility of ICEPool with wide varieties of models and its potential to boost the performance of existing graph neural network architectures.

cs.LG↗

arXiv2025

REIC: RAG-Enhanced Intent Classification at Scale

Accurate intent classification is critical for efficient routing in customer service, ensuring customers are connected with the most suitable agents while reducing handling times and operational costs. However, as companies expand their product lines, intent classification faces scalability challenges due to the increasing number of intents and variations in taxonomy across different verticals. In this paper, we introduce REIC, a Retrieval-augmented generation Enhanced Intent Classification approach, which addresses these challenges effectively. REIC leverages retrieval-augmented generation (RAG) to dynamically incorporate relevant knowledge, enabling precise classification without the need for frequent retraining. Through extensive experiments on real-world datasets, we demonstrate that REIC outperforms traditional fine-tuning, zero-shot, and few-shot methods in large-scale customer service settings. Our results highlight its effectiveness in both in-domain and out-of-domain scenarios, demonstrating its potential for real-world deployment in adaptive and large-scale intent classification systems.

cs.CL↗

arXiv2025

Co-PatcheR: Collaborative Software Patching with Component(s)-specific Small Reasoning Models

Motivated by the success of general-purpose large language models (LLMs) in software patching, recent works started to train specialized patching models. Most works trained one model to handle the end-to-end patching pipeline (including issue localization, patch generation, and patch validation). However, it is hard for a small model to handle all tasks, as different sub-tasks have different workflows and require different expertise. As such, by using a 70 billion model, SOTA methods can only reach up to 41% resolved rate on SWE-bench-Verified. Motivated by the collaborative nature, we propose Co-PatcheR, the first collaborative patching system with small and specialized reasoning models for individual components. Our key technique novelties are the specific task designs and training recipes. First, we train a model for localization and patch generation. Our localization pinpoints the suspicious lines through a two-step procedure, and our generation combines patch generation and critique. We then propose a hybrid patch validation that includes two models for crafting issue-reproducing test cases with and without assertions and judging patch correctness, followed by a majority vote-based patch selection. Through extensive evaluation, we show that Co-PatcheR achieves 46% resolved rate on SWE-bench-Verified with only 3 x 14B models. This makes Co-PatcheR the best patcher with specialized models, requiring the least training resources and the smallest models. We conduct a comprehensive ablation study to validate our recipes, as well as our choice of training data number, model size, and testing-phase scaling strategy.

cs.AI↗

arXiv2025

DeepEyes: Incentivizing "Thinking with Images" via Reinforcement Learning

Large Vision-Language Models excel at multimodal understanding but struggle to deeply integrate visual information into their predominantly text-based reasoning processes, a key challenge in mirroring human cognition. To address this, we introduce DeepEyes, a model that learns to "think with images", trained end-to-end with reinforcement learning without requiring pre-collected reasoning data for cold-start supervised fine-tuning (SFT). Notably, this ability emerges natively, leveraging the model's own grounding capability as an intrinsic function rather than relying on external specialized models or APIs. We enable this capability through active perception, where the model learns to strategically ground its reasoning in visual information, guided by a tailored data selection and reward strategy. DeepEyes achieves significant performance gains on general perception and reasoning benchmarks and also demonstrates improvement in grounding, hallucination, and mathematical reasoning tasks. Interestingly, we observe the distinct evolution of active perception from initial exploration to efficient and accurate exploitation, and diverse thinking patterns that closely mirror human visual reasoning processes. Code is available at https://github.com/Visual-Agent/DeepEyes.

cs.CV↗

arXiv2024

Stack-Sorting with Dotted-Pattern-Avoiding Stacks

In this paper, we introduce the dotted pattern-avoiding map $s_{\dot{\tau}}$, which avoids the dotted pattern $\dot{\tau}$ instead of descents as West's stack-sorting map $s$ does. We also extend the pattern-avoiding machine, which is composed of a $\sigma$ avoiding map and West's stack-sorting map $s$, to the dotted pattern-avoiding machine. In this paper, we prove the analogs of the classical results on West's stack sorting map for the length $2$ dotted pattern-avoiding maps. We end with several conjectures.

math.CO↗

arXiv2024

Contact Complexity in Customer Service

Customers who reach out for customer service support may face a range of issues that vary in complexity. Routing high-complexity contacts to junior agents can lead to multiple transfers or repeated contacts, while directing low-complexity contacts to senior agents can strain their capacity to assist customers who need professional help. To tackle this, a machine learning model that accurately predicts the complexity of customer issues is highly desirable. However, defining the complexity of a contact is a difficult task as it is a highly abstract concept. While consensus-based data annotation by experienced agents is a possible solution, it is time-consuming and costly. To overcome these challenges, we have developed a novel machine learning approach to define contact complexity. Instead of relying on human annotation, we trained an AI expert model to mimic the behavior of agents and evaluate each contact's complexity based on how the AI expert responds. If the AI expert is uncertain or lacks the skills to comprehend the contact transcript, it is considered a high-complexity contact. Our method has proven to be reliable, scalable, and cost-effective based on the collected data.

cs.LG↗

arXiv2024

Teacher-Student Learning on Complexity in Intelligent Routing

Customer service is often the most time-consuming aspect for e-commerce websites, with each contact typically taking 10-15 minutes. Effectively routing customers to appropriate agents without transfers is therefore crucial for e-commerce success. To this end, we have developed a machine learning framework that predicts the complexity of customer contacts and routes them to appropriate agents accordingly. The framework consists of two parts. First, we train a teacher model to score the complexity of a contact based on the post-contact transcripts. Then, we use the teacher model as a data annotator to provide labels to train a student model that predicts the complexity based on pre-contact data only. Our experiments show that such a framework is successful and can significantly improve customer experience. We also propose a useful metric called complexity AUC that evaluates the effectiveness of customer service at a statistical level.

cs.LG↗

arXiv2024

Uncovering Customer Issues through Topological Natural Language Analysis

E-commerce companies deal with a high volume of customer service requests daily. While a simple annotation system is often used to summarize the topics of customer contacts, thoroughly exploring each specific issue can be challenging. This presents a critical concern, especially during an emerging outbreak where companies must quickly identify and address specific issues. To tackle this challenge, we propose a novel machine learning algorithm that leverages natural language techniques and topological data analysis to monitor emerging and trending customer issues. Our approach involves an end-to-end deep learning framework that simultaneously tags the primary question sentence of each customer's transcript and generates sentence embedding vectors. We then whiten the embedding vectors and use them to construct an undirected graph. From there, we define trending and emerging issues based on the topological properties of each transcript. We have validated our results through various methods and found that they are highly consistent with news sources.

cs.CL↗

arXiv2023

Maximum Number of Quads

We study the maximum number of quads among $\ell$ cards from an EvenQuads deck of size $2^n$. This corresponds to enumerating quadruples of integers in the range $[0,\ell-1]$ such that their bitwise XOR is zero. In this paper, we conjecture a formula that calculates the maximum number of quads among $\ell$ cards.

math.CO↗

arXiv2023

EvenQuads Game and Error-Correcting Codes

EvenQuads is a new card game that is a generalization of the SET game, where each card is characterized by three attributes, each taking four possible values. Four cards form a quad when, for each attribute, the values are the same, all different, or half and half. Given $\ell$ cards from the deck of EvenQuads, we can build an error-correcting linear binary code of length $\ell$ and Hamming distance 4. The quads correspond to codewords of weight 4. Error-correcting codes help us calculate the possible number of quads when given up to 8 cards. We also estimate the number of cards that do not contain quads for decks of different sizes. In addition, we discuss properties of error-correcting codes built on semimagic, magic, and strongly magic quad squares.

math.CO↗

arXiv2023

Quad Squares

We study 4-by-4 squares formed by cards from the EvenQuads deck. EvenQuads is a card game with 64 cards where cards have 3 attributes with 4 values in each attribute. A quad is four cards with all attributes the same, all different, or half and half. We define Latin quad squares as squares where the cards in each row and column have different values for each attribute. We define semimagic quad squares as squares where each row and column form a quad. For magic quad squares, we add a requirement that the diagonals have to form a quad. We also define strongly magic quad squares. We analyze types of semimagic and strongly magic quad squares. We also calculate the number of semimagic, magic, and strongly magic quad squares for quad decks of any size. These squares can be described in terms of integers. Four integers form a quad when their bitwise XOR is zero.

math.HO↗

arXiv2023

Card Games Unveiled: Exploring the Underlying Linear Algebra

We discuss four famous card games that can help learn linear algebra. The games are: SET, Socks, Spot it!, and EvenQuads. We describe the game in the language of vector, affine, and projective spaces. We also show how these games are connected to each other. A separate section is devoted to playing Socks with the EvenQuads deck and vice versa.

math.HO↗

arXiv2023

Event Camera-based Visual Odometry for Dynamic Motion Tracking of a Legged Robot Using Adaptive Time Surface

Our paper proposes a direct sparse visual odometry method that combines event and RGB-D data to estimate the pose of agile-legged robots during dynamic locomotion and acrobatic behaviors. Event cameras offer high temporal resolution and dynamic range, which can eliminate the issue of blurred RGB images during fast movements. This unique strength holds a potential for accurate pose estimation of agile-legged robots, which has been a challenging problem to tackle. Our framework leverages the benefits of both RGB-D and event cameras to achieve robust and accurate pose estimation, even during dynamic maneuvers such as jumping and landing a quadruped robot, the Mini-Cheetah. Our major contributions are threefold: Firstly, we introduce an adaptive time surface (ATS) method that addresses the whiteout and blackout issue in conventional time surfaces by formulating pixel-wise decay rates based on scene complexity and motion speed. Secondly, we develop an effective pixel selection method that directly samples from event data and applies sample filtering through ATS, enabling us to pick pixels on distinct features. Lastly, we propose a nonlinear pose optimization formula that simultaneously performs 3D-2D alignment on both RGB-based and event-based maps and images, allowing the algorithm to fully exploit the benefits of both data streams. We extensively evaluate the performance of our framework on both public datasets and our own quadruped robot dataset, demonstrating its effectiveness in accurately estimating the pose of agile robots during dynamic movements.

cs.RO↗