arXiv subjects

Weibin Lin

Publications and source records attributed to Weibin Lin.

4 recordsLinked to original sources

arXiv2026

Verication-driven closed-loop multi-agent large language modelframework for code-compliant structural design

Multi-agent large language model(LLM)systems are applied to structural design,yet most use one-shot generation and cannot verify their output,leaving themill-suited to safety-critical tasks.Rather than trusting LLM self-correction,thisframework injects feedback from an external physics-based verier into a closedrepair loop.The framework couples a three-layernite-element verication systemwith a dual-node loop.Node 1 turns code violations into hard repair constraints,Node 2 turns a four-dimensional quality score into safety-rst soft constraints,and a retrieval-augmented code base makes every violation traceable to a clause.Overve structure types and 44 cases,code compliance rises from 56.8%to 98.6%and the composite score from 63.8 to 71.4(p<0.000001),using about 5.8%lessmaterial.Removing either node degrades performance,and compliance does notchange detectably across the two backbone LLMs tested,indicating that it ishere attributed to the external verier rather than the model.The framework,the 44-case benchmark and all experiment scripts are released as open source forreplicability.

cs.SE↗

arXiv2026

Failure-Based Testing for Deep Reinforcement Learning Agents

Deep Reinforcement Learning (DRL) agents have been widely adopted across diverse domains to address challenging decision-making problems, such as autonomous driving and robotic control. Given that many of these applications are safety- and security-critical, rigorous testing of DRL agents is indispensable. Existing testing methods are typically guided by reward signals to detect failures. However, for well-trained agents, whose performance approaches optimal levels in standard operating conditions, reward signals remain generally high, making current methods ineffective at uncovering critical failures. To address these challenges, we propose a novel failure-based method that leverages task-induced failure insights to enhance failure detection capability while reducing the number of tests required. Since DRL agents are inherently designed with human-defined tasks, they provide valuable cues about task difficulty. Intuitively, a DRL agent is more likely to fail when confronted with a more difficult task; therefore, PRT prioritizes these tasks. Building on this foundation, we propose Prior Random Testing, a black-box failure-based testing method that enables targeted prioritization while preserving the diversity of generated test cases. Guided by task-induced failure insights, PRT prioritizes failure-prone regions of the input domain, thereby facilitating efficient failure detection. PRT is evaluated on four widely used benchmarks and compared with different state-of-the-art methods including fuzzing, search-based and generative-based methods. PRT ranks among the top performers in terms of both the cost of finding the first failure and the diversity of test cases. Notably, compared to random testing, PRT achieves better diversity and reduces the testing cost by over 50%.

cs.SE↗

arXiv2026

LGMT: Logic-Grounded Metamorphic Testing for Evaluating the Reasoning Reliability of LLMs

Large Language Models (LLMs) achieve strong performance on logical reasoning benchmarks, yet their reliability remains uncertain. Existing evaluations rely on static benchmarks, which fail to assess robustness under logically equivalent transformations and often overestimate reasoning capability. We propose LGMT (Logic-Grounded Metamorphic Testing), an oracle-free framework that leverages first-order logic (FOL) to evaluate LLM reasoning. By deriving metamorphic relations from formal logical equivalences, LGMT constructs semantically invariant test cases and detects reasoning defects through cross-case consistency checking. Experiments on six state-of-the-art LLMs show that LGMT exposes substantial hidden defects missed by traditional reference-based evaluations. We further find that models are particularly sensitive to symbol-level and conclusion-level variations, and that advanced prompting such as Few-shot CoT only partially mitigates these issues. These results suggest that LLM evaluation should move beyond isolated correctness toward robustness under logical invariance. LGMT provides a principled and scalable approach for diagnosing reasoning failures.

cs.AI↗

arXiv2019

An Item Recommendation Approach by Fusing Images based on Neural Networks

There are rich formats of information in the network, such as rating, text, image, and so on, which represent different aspects of user preferences. In the field of recommendation, how to use those data effectively has become a difficult subject. With the rapid development of neural network, researching on multi-modal method for recommendation has become one of the major directions. In the existing recommender systems, numerical rating, item description and review are main information to be considered by researchers. However, the characteristics of the item may affect the user's preferences, which are rarely used for recommendation models. In this work, we propose a novel model to incorporate visual factors into predictors of people's preferences, namely MF-VMLP, based on the recent developments of neural collaborative filtering (NCF). Firstly, we get visual presentation via a pre-trained convolutional neural network (CNN) model. To obtain the nonlinearities interaction of latent vectors and visual vectors, we propose to leverage a multi-layer perceptron (MLP) to learn. Moreover, the combination of MF and MLP has achieved collaborative filtering recommendation between users and items. Our experiments conduct Amazon's public dataset for experimental validation and root-mean-square error (RMSE) as evaluation metrics. To some extent, experimental result on a real-world data set demonstrates that our model can boost the recommendation performance.

cs.IR↗