arXiv subjects

Xiaolong Jia

Publications and source records attributed to Xiaolong Jia.

5 recordsLinked to original sources

arXiv2026

Self-Correcting RAG: Enhancing Faithfulness via MMKP Context Selection and NLI-Guided MCTS

Retrieval-augmented generation (RAG) substantially extends the knowledge boundary of large language models. However, it still faces two major challenges when handling complex reasoning tasks: low context utilization and frequent hallucinations. To address these issues, we propose Self-Correcting RAG, a unified framework that reformulates retrieval and generation as constrained optimization and path planning. On the input side, we move beyond traditional greedy retrieval and, for the first time, formalize context selection as a multi-dimensional multiple-choice knapsack problem (MMKP), thereby maximizing information density and removing redundancy under a strict token budget. On the output side, we introduce a natural language inference (NLI)-guided Monte Carlo Tree Search (MCTS) mechanism, which leverages test-time compute to dynamically explore reasoning trajectories and validate the faithfulness of generated answers. Experiments on six multi-hop question answering and fact-checking datasets demonstrate that our method significantly improves reasoning accuracy on complex queries while effectively reducing hallucinations, outperforming strong existing baselines.Our code is available at https://github.com/xjiacs/Self-Correcting-RAG .

cs.CL↗

arXiv2026

RCBSF: A Multi-Agent Framework for Automated Contract Revision via Stackelberg Game

Despite the widespread adoption of Large Language Models (LLMs) in Legal AI, their utility for automated contract revision remains impeded by hallucinated safety and a lack of rigorous behavioral constraints. To address these limitations, we propose the Risk-Constrained Bilevel Stackelberg Framework (RCBSF), which formulates revision as a non-cooperative Stackelberg game. RCBSF establishes a hierarchical Leader Follower structure where a Global Prescriptive Agent (GPA) imposes risk budgets upon a follower system constituted by a Constrained Revision Agent (CRA) and a Local Verification Agent (LVA) to iteratively optimize output. We provide theoretical guarantees that this bilevel formulation converges to an equilibrium yielding strictly superior utility over unguided configurations. Empirical validation on a unified benchmark demonstrates that RCBSF achieves state-of-the-art performance, surpassing iterative baselines with an average Risk Resolution Rate (RRR) of 84.21\% while enhancing token efficiency. Our code is available at https://github.com/xjiacs/RCBSF .

cs.CL↗

arXiv2026

Small Target Detection Based on Mask-Enhanced Attention Fusion of Visible and Infrared Remote Sensing Images

Targets in remote sensing images are usually small, weakly textured, and easily disturbed by complex backgrounds, challenging high-precision detection with general algorithms. Building on our earlier ESM-YOLO, this work presents ESM-YOLO+ as a lightweight visible infrared fusion network. To enhance detection, ESM-YOLO+ includes two key innovations. (1) A Mask-Enhanced Attention Fusion (MEAF) module fuses features at the pixel level via learnable spatial masks and spatial attention, effectively aligning RGB and infrared features, enhancing small-target representation, and alleviating cross-modal misalignment and scale heterogeneity. (2) Training-time Structural Representation (SR) enhancement provides auxiliary supervision to preserve fine-grained spatial structures during training, boosting feature discriminability without extra inference cost. Extensive experiments on the VEDAI and DroneVehicle datasets validate ESM-YOLO+'s superiority. The model achieves 84.71\% mAP on VEDAI and 74.0\% mAP on DroneVehicle, while greatly reducing model complexity, with 93.6\% fewer parameters and 68.0\% lower GFLOPs than the baseline. These results confirm that ESM-YOLO+ integrates strong performance with practicality for real-time deployment, providing an effective solution for high-performance small-target detection in complex remote sensing scenes.

cs.CV↗

arXiv2025

On Architectures for Combining Reinforcement Learning and Model Predictive Control with Runtime Improvements

Model Predictive Control (MPC) faces computational demands and performance degradation from model inaccuracies. We propose two architectures combining Neural Network-approximated MPC (NNMPC) with Reinforcement Learning (RL). The first, Warm Start RL, initializes the RL actor with pre-trained NNMPC weights. The second, RLMPC, uses RL to generate corrective residuals for NNMPC outputs. We introduce a downsampling method reducing NNMPC input dimensions while maintaining performance. Evaluated on a rotary inverted pendulum, both architectures demonstrate runtime reductions exceeding 99% compared to traditional MPC while improving tracking performance under model uncertainties, with RL+MPC achieving 11-40% cost reduction depending on reference amplitude.

eess.SY↗

arXiv2024

Maxima of the $Q$-index of 2 leaves-free graphs with given size

The $Q$-index of graph $G$ is the largest eigenvalue of the signless Laplacian matrix of $G$. Wang [Discrete Appl. Math. 356(2024)] proved the sharp upper bounds on the $Q$-index of leaf-free graphs with given size and characterized the corresponding extremal graphs. A graph is $2$ leaves-free if it has no two pendent vertices. In this paper, we give sharp upper bounds on the $Q$-index of 2 leaves-free graphs with given size and characterize the corresponding extremal graphs.

math.CO↗