arXiv subjects

Shuwen Zhang

Publications and source records attributed to Shuwen Zhang.

5 recordsLinked to original sources

arXiv2026

Tencent WorkBuddy Bench: A Multi-Domain Coding-Agent Benchmark with Contamination-Resistant Task Construction

We introduce Tencent WorkBuddy Bench, a multi-domain evaluation suite for coding agents; this report documents its construction methodology, scoring protocol, and a cross-model leaderboard. At its core is a unified evaluation framework for constructing and running distribution-informed coding-agent tasks across four work domains - Code, Web, Office, and Security. Rather than adapting public issue text, every task is reverse-engineered from a real commit, pull request, or business scenario and rewritten as a short, colloquial, role-played request, so that a task's prompt is not recoverable by web-searching the underlying issue, pull request, or commit thread. Because the dataset is released openly - task directories, environment images, evaluation harness, tests, and reference solutions - contamination resistance rests on this construction together with dataset versioning rather than on secrecy. The four subsets - repository-level engineering, front-end development, office and business workflows, and red-/blue-team security - probe complementary facets of real work, each with its own verification style. All are packaged in a uniform task-directory format and run, under a uniform and reproducible protocol, on two agent harnesses (CodeBuddy Code and Claude Code); the full open release makes the benchmark reproducible end to end and directly auditable, since any third party can re-run each task and inspect its content. Because each subset uses a different scoring instrument, scores are not comparable across subsets and the suite reports no suite-wide average. We report a cross-model leaderboard across several model families.

cs.CL↗

arXiv2025

Collab-Overcooked: Benchmarking and Evaluating Large Language Models as Collaborative Agents

Large Language Models (LLMs) based agent systems have made great strides in real-world applications beyond traditional NLP tasks. This paper proposes a new LLM-based Multi-Agent System (LLM-MAS) benchmark, Collab-Overcooked, built on the popular Overcooked-AI game with more applicable and challenging tasks in interactive environments. Collab-Overcooked extends existing benchmarks in two novel ways. First, it provides a multi-agent framework supporting diverse tasks and objectives and encourages collaboration through natural language communication. Second, it introduces a spectrum of process-oriented evaluation metrics to assess the fine-grained collaboration capabilities of different LLM agents, a dimension often overlooked in prior work. We conduct extensive experiments with 13 popular LLMs and show that, while the LLMs exhibit a strong ability in goal interpretation, there are significant shortcomings in active collaboration and continuous adaptation, which are critical for efficiently fulfilling complex tasks. Notably, we highlight the strengths and weaknesses of LLM-MAS and provide insights for improving and evaluating LLM-MAS on a unified and open-source benchmark. The environments, 30 open-ended tasks, and the evaluation package are publicly available at https://github.com/YusaeMeow/Collab-Overcooked.

cs.CL↗

arXiv2025

Efficient Stochastic Polar Decoder With Correlated Stochastic Computing

Polar codes have gained significant attention in channel coding for their ability to approach the capacity of binary input discrete memoryless channels (B-DMCs), thanks to their reliability and efficiency in transmission. However, existing decoders often struggle to balance hardware area and performance. Stochastic computing offers a way to simplify circuits, and previous work has implemented decoding using this approach. A common issue with these methods is performance degradation caused by the introduction of correlation. This paper presents an Efficient Correlated Stochastic Polar Decoder (ECS-PD) that fundamentally addresses the issue of the `hold-state', preventing it from increasing as correlation computation progresses. We propose two optimization strategies aimed at reducing iteration latency, increasing throughput, and simplifying the circuit to improve hardware efficiency. The optimization can reduce the number of iterations by 25.2% at $E_b/N_0$ = 3 dB. Compared to other efficient designs, the proposed ECS-PD achieves higher throughput and is 2.7 times more hardware-efficient than the min-sum decoder.

cs.IT↗

arXiv2025

Multi-Objective Large Language Model Unlearning

Machine unlearning in the domain of large language models (LLMs) has attracted great attention recently, which aims to effectively eliminate undesirable behaviors from LLMs without full retraining from scratch. In this paper, we explore the Gradient Ascent (GA) approach in LLM unlearning, which is a proactive way to decrease the prediction probability of the model on the target data in order to remove their influence. We analyze two challenges that render the process impractical: gradient explosion and catastrophic forgetting. To address these issues, we propose Multi-Objective Large Language Model Unlearning (MOLLM) algorithm. We first formulate LLM unlearning as a multi-objective optimization problem, in which the cross-entropy loss is modified to the unlearning version to overcome the gradient explosion issue. A common descent update direction is then calculated, which enables the model to forget the target data while preserving the utility of the LLM. Our empirical results verify that MoLLM outperforms the SOTA GA-based LLM unlearning methods in terms of unlearning effect and model utility preservation. The source code is available at https://github.com/zibinpan/MOLLM.

cs.CL↗

arXiv2021

Deep manifold learning reveals hidden dynamics of proteasome autoregulation

The 2.5-MDa 26S proteasome maintains proteostasis and regulates myriad cellular processes. How polyubiquitylated substrate interactions regulate proteasome activity is not understood. Here we introduce a deep manifold learning framework, named AlphaCryo4D, which enables atomic-level cryogenic electron microscopy (cryo-EM) reconstructions of nonequilibrium conformational continuum and reconstitutes hidden dynamics of proteasome autoregulation in the act of substrate degradation. AlphaCryo4D integrates 3D deep residual learning with manifold embedding of free-energy landscapes, which directs 3D clustering via an energy-based particle-voting algorithm. In blind assessments using simulated heterogeneous cryo-EM datasets, AlphaCryo4D achieved 3D classification accuracy three times that of conventional method and reconstructed continuous conformational changes of a 130-kDa protein at sub-3-angstrom resolution. By using AlphaCryo4D to analyze a single experimental cryo-EM dataset, we identified 64 conformers of the substrate-bound human 26S proteasome, revealing conformational entanglement of two regulatory particles in the doubly capped holoenzymes and their energetic differences with singly capped ones. Novel ubiquitin-binding sites are discovered on the RPN2, RPN10 and Alpha5 subunits to remodel polyubiquitin chains for deubiquitylation and recycle. Importantly, AlphaCryo4D choreographs single-nucleotide-exchange dynamics of proteasomal AAA-ATPase motor during translocation initiation, which upregulates proteolytic activity by allosterically promoting nucleophilic attack. Our systemic analysis illuminates a grand hierarchical allostery for proteasome autoregulation.

q-bio.QM↗