Bolun Zhang

Lingyue Fu, Hao Guan, Bolun Zhang et al.

As Large Language Models (LLMs) demonstrate increasingly sophisticated code processing capabilities, evaluating their performance on engineering-level code remains challenging. Existing repository-level benchmarks primarily focus on single scenarios, such as code generation or bug fixing, without adequately capturing the diversity and complexity of real-world software or project engineering workflows. Furthermore, these benchmarks suffer from limited controllability in question positioning and reliability issues in their generated test cases. To address these limitations, we present CorePipe, a fully automated pipeline that converts repositories into comprehensive test cases, and introduce CoreCodeBench, a configurable multi-scenario repository-level benchmark. To simulate real engineering scenarios, CorePipe generates three types of atomic questions (Development, BugFix, and Test-Driven Development) specifically targeting core code segments. These atomic questions are further combined into three types of composite questions, with difficulty levels flexibly adjusted through hyperparameter tuning. CoreCodeBench provides a comprehensive and extensive repository-level benchmark to investigate the applicability of LLMs in real-world engineering projects. Experiments with 16 LLMs across diverse scenarios reveal varying capabilities and offer multi-dimensional insights into LLM performance in engineering contexts. The code for CorePipe is available at https://github.com/AGI-Eval-Official/CoreCodeBench, and the data for CoreCodeBench can be accessed at https://huggingface.co/collections/tubehhh/corecodebench-68256d2faabf4b1610a08caa.

Xianghe Pang, Shuo Tang, Rui Ye et al.

Aligning large language models (LLMs) with human values is imperative to mitigate potential adverse effects resulting from their misuse. Drawing from the sociological insight that acknowledging all parties' concerns is a key factor in shaping human values, this paper proposes a novel direction to align LLMs by themselves: social scene simulation. To achieve this, we present MATRIX, a novel social scene simulator that emulates realistic scenes around a user's input query, enabling the LLM to take social consequences into account before responding. MATRIX serves as a virtual rehearsal space, akin to a Monopolylogue, where the LLM performs diverse roles related to the query and practice by itself. To inject this alignment, we fine-tune the LLM with MATRIX-simulated data, ensuring adherence to human values without compromising inference speed. We theoretically show that the LLM with MATRIX outperforms Constitutional AI under mild assumptions. Finally, extensive experiments validate that our method outperforms over 10 baselines across 4 benchmarks. As evidenced by 875 user ratings, our tuned 13B-size LLM exceeds GPT-4 in aligning with human values. See our project page at https://shuotang123.github.io/MATRIX.

Junkun Jiao, Tong Liu, Ke Li et al.

The escalating data scale in High-Energy Physics (HEP) fuels a growing aspiration for higher analytical efficiency. While Large Language Models (LLMs) offer a path toward automation via agentic AI, they struggle with complex scientific workflows that require deep domain knowledge and are tightly coupled to experiment-specific codebases. To address this, we introduce a methodology centered on HepScript, a dual-use Domain-Specific Language (DSL) for HEP data analysis workflows. HepScript serves as a shared formal interface, abstracting HEP analysis logic into a constrained syntax that is both intuitive for human experts and reliably generable by AI agents. First developed for the Beijing Spectrometer III (BESIII) experiment, HepScript hides the complexity of the underlying software stack, translating high-level analysis intent into low-level, production-ready code. In our case studies, this abstraction reduces the required human-written code by 93\%. Crucially, HepScript's constrained grammar defines a tractable action space, enabling AI agents to autonomously generate executable specifications for core analysis stages directly from published literature with a 95\% success rate. Our work demonstrates a scalable pathway toward human-AI collaborative systems, where a formally specified DSL acts as an unambiguous translation layer between human expertise, AI automation, and production environment, rendering previously intractable automation problems solvable.

Nguyen Van Huynh, Bolun Zhang, Dinh-Hieu Tran et al.

Spectrum access is an essential problem in device-to-device (D2D) communications. However, with the recent growth in the number of mobile devices, the wireless spectrum is becoming scarce, resulting in low spectral efficiency for D2D communications. To address this problem, this paper aims to integrate the ambient backscatter communication technology into D2D devices to allow them to backscatter ambient RF signals to transmit their data when the shared spectrum is occupied by mobile users. To obtain the optimal spectrum access policy, i.e., stay idle or access the shared spectrum and perform active transmissions or backscattering ambient RF signals for transmissions, to maximize the average throughput for D2D users, deep reinforcement learning (DRL) can be adopted. However, DRL-based solutions may require long training time due to the curse of dimensionality issue as well as complex deep neural network architectures. For that, we develop a novel quantum reinforcement learning (RL) algorithm that can achieve a faster convergence rate with fewer training parameters compared to DRL thanks to the quantum superposition and quantum entanglement principles. Specifically, instead of using conventional deep neural networks, the proposed quantum RL algorithm uses a parametrized quantum circuit to approximate an optimal policy. Extensive simulations then demonstrate that the proposed solution not only can significantly improve the average throughput of D2D devices when the shared spectrum is busy but also can achieve much better performance in terms of convergence rate and learning complexity compared to existing DRL-based methods.

Bolun Zhang, Linzhuo Li, Yunqi Chen et al.

Large language models (LLMs) are rapidly being integrated into computational social science research, yet their blackboxed training and designed stochastic elements in inference pose unique challenges for scientific inquiry. This article argues that applying LLMs to social scientific tasks requires explicit assessment of uncertainty-an expectation long established in both quantitative methodology in the social sciences and machine learning. We introduce a unified framework for evaluating LLM uncertainty along two dimensions: the task type (T), which distinguishes between classification, short-form, and long-form generation, and the validation type (V), which captures the availability of reference data or evaluative criteria. Drawing from both computer science and social science literature, we map existing uncertainty quantification (UQ) methods to this T-V typology and offer practical recommendations for researchers. Our framework provides both a methodological safeguard and a practical guide for integrating LLMs into rigorous social science research.

Lingyue Fu, Bolun Zhang, Hao Guan et al.

Recent advances in code agents have enabled automated software development at the project level, supported by large language models (LLMs) and widely adopted tools. However, existing benchmarks for code agent evaluation face two major limitations: high annotation cost and expertise requirements, and rigid evaluation metrics that rely primarily on unit tests. To address these challenges, we propose an agent-driven benchmark construction pipeline that leverages human supervision to efficiently generate diverse and challenging project-level tasks. Based on this approach, we introduce PRDBench, a novel benchmark comprising 50 real-world Python projects across 20 domains, each with structured Product Requirement Document (PRD) requirements, comprehensive evaluation criteria, and reference implementations. PRDBench features rich data sources, high task complexity, and flexible metrics. We further employ an Agent-as-a-Judge paradigm to score agent outputs, enabling the evaluation of various test types beyond unit tests. Extensive experiments on PRDBench demonstrate its effectiveness in assessing the capabilities of both code agents and evaluation agents, providing a scalable and robust framework for annotation and evaluation.

Siliang Qin, Fengrui Yang, Hao Wang et al.

Disassembly is a crucial yet challenging step in binary analysis. While emerging neural disassemblers show promise for efficiency and accuracy, they frequently generate outputs violating fundamental structural constraints, which significantly compromise their practical usability. To address this critical problem, we regularize the disassembly solution space by formalizing and applying key structural constraints based on post-dominance relations. This approach systematically detects widespread errors in existing neural disassemblers' outputs. These errors often originate from models' limited context modeling and instruction-level decoding that neglect global structural integrity. We introduce Tady, a novel neural disassembler featuring an improved model architecture and a dedicated post-processing algorithm, specifically engineered to address these deficiencies. Comprehensive evaluations on diverse binaries demonstrate that Tady effectively eliminates structural constraint violations and functions with high efficiency, while maintaining instruction-level accuracy.

Bolun Zhang, Nguyen Van Huynh

End-to-End (E2E) learning-based concept has been recently introduced to jointly optimize both the transmitter and the receiver in wireless communication systems. Unfortunately, this E2E learning architecture requires a prior differentiable channel model to jointly train the deep neural networks (DNNs) at the transceivers, which is hardly obtained in practice. This paper aims to solve this issue by developing a deep deterministic policy gradient (DDPG)-based framework. In particular, the proposed solution uses the loss value of the receiver DNN as the reward to train the transmitter DNN. The simulation results then show that our proposed solution can jointly train the transmitter and the receiver without requiring the prior channel model. In addition, we demonstrate that the proposed DDPG-based solution can achieve better detection performance compared to the state-of-the-art solutions.

Michael Hagenow, Bolun Zhang, Bilge Mutlu et al.

Manipulations of a constrained object often use a non-rigid grasp that allows the object to rotate relative to the end effector. This orientation slip strategy is often present in natural human demonstrations, yet it is generally overlooked in methods to identify constraints from such demonstrations. In this paper, we present a method to model and recognize prehensile orientation slip in human demonstrations of constrained interactions. Using only observations of an end effector, we can detect the type of constraint, parameters of the constraint, and orientation slip properties. Our method uses a novel hierarchical model selection method that is informed by multiple origins of physics-based evidence. A study with eight participants shows that orientation slip occurs in natural demonstrations and confirms that it can be detected by our method.