arXiv subjects

Wenli Song

Publications and source records attributed to Wenli Song.

4 recordsLinked to original sources

arXiv2026

DuMate-DeepResearch: An Auditable Multi-Agent System with Recursive Search and Rubric-Grounded Reasoning

Deep Research (DR) has emerged as a new agentic paradigm to tackle complex, open-ended research tasks, demanding systems that can iteratively frame problems, acquire evidence, verify sources, and synthesize long-form reports. In practice, however, current DR systems are constrained by four interrelated limitations: long-horizon planning over an underspecified scope, the bottleneck of decomposing and scheduling such tasks within a single agent, hallucination risk in long-form synthesis, and limited process auditability. This technical report presents DuMate-DeepResearch, a multi-agent DR framework built on the Qianfan Agent Foundry. The framework decouples the Agent Core, which handles task understanding, planning, and scheduling, from an extensible Tool Ecosystem for retrieval, evidence acquisition, and report rendering, making every intermediate decision and tool invocation explicitly traceable. Building on this infrastructure, DuMate-DeepResearch further introduces three mechanisms: (i) a graph-based dynamic planning strategy expands the research roadmap coarse-to-fine and continuously revises it through reflection, re-planning, backtracking, and parallel branching; (ii) a recursive two-level execution design delegates each complex search sub-task to an inner Search Agent that runs its own planning loop, isolating noisy retrieval and stabilizing long-horizon execution; (iii) a rubric-based test-time optimization mechanism dynamically generates task-specific quality criteria and uses them as live reasoning scaffolds for evidence-grounded synthesis and adaptive stopping. Across two deep research benchmarks, DuMate-DeepResearch establishes new state-of-the-art results: the best overall score (58.03%) on DeepResearch Bench, and the best overall score (61.95%) on DeepResearch Bench II while ranking first in information recall and analysis.

cs.AI↗

arXiv2023

LiSum: Open Source Software License Summarization with Multi-Task Learning

Open source software (OSS) licenses regulate the conditions under which users can reuse, modify, and distribute the software legally. However, there exist various OSS licenses in the community, written in a formal language, which are typically long and complicated to understand. In this paper, we conducted a 661-participants online survey to investigate the perspectives and practices of developers towards OSS licenses. The user study revealed an indeed need for an automated tool to facilitate license understanding. Motivated by the user study and the fast growth of licenses in the community, we propose the first study towards automated license summarization. Specifically, we released the first high quality text summarization dataset and designed two tasks, i.e., license text summarization (LTS), aiming at generating a relatively short summary for an arbitrary license, and license term classification (LTC), focusing on the attitude inference towards a predefined set of key license terms (e.g., Distribute). Aiming at the two tasks, we present LiSum, a multi-task learning method to help developers overcome the obstacles of understanding OSS licenses. Comprehensive experiments demonstrated that the proposed jointly training objective boosted the performance on both tasks, surpassing state-of-the-art baselines with gains of at least 5 points w.r.t. F1 scores of four summarization metrics and achieving 95.13% micro average F1 score for classification simultaneously. We released all the datasets, the replication package, and the questionnaires for the community.

cs.SE↗

arXiv2021

Ultrasensitive barocaloric material for room-temperature solid-state refrigeration

Solid-state refrigeration based on caloric effects is an energetically efficient and environmentally friendly technology, which is deemed as a potential alternative to the conventional vapor-compression technology. One of the greatest obstacles to the real application is the huge driving fields. Here, we report a giant barocaloric effect in inorganic NH4I with maximum entropy changes of ΔS_BCE^max ~89 J K-1 kg-1 around room temperature, associated with the orientationally order-disorder phase transition. The phase transition temperature, Tt, varies dramatically with pressure in a rate of dTt/dP ~0.81 K MPa-1, which leads to a very much small saturation driving pressure of ΔP ~20 MPa, an unprecedentedly large caloric strength of |ΔS_BCE^max/ΔP| ~4.45 J K-1 kg-1 MPa-1, as well as a broad temperature window of ~68 K under an 80 MPa driving pressure. Comprehensive characterization of the crystal structure and dynamics by neutron scattering measurements reveals a strong reorientation-vibration coupling that is responsible for the large pressure sensitivity of Tt. This work is expected to advance the practical application of barocaloric refrigeration.

cond-mat.mtrl-sci↗

arXiv2021

Layer-wise Customized Weak Segmentation Block and AIoU Loss for Accurate Object Detection

The anchor-based detectors handle the problem of scale variation by building the feature pyramid and directly setting different scales of anchors on each cell in different layers. However, it is difficult for box-wise anchors to guide the adaptive learning of scale-specific features in each layer because there is no one-to-one correspondence between box-wise anchors and pixel-level features. In order to alleviate the problem, in this paper, we propose a scale-customized weak segmentation (SCWS) block at the pixel level for scale customized object feature learning in each layer. By integrating the SCWS blocks into the single-shot detector, a scale-aware object detector (SCOD) is constructed to detect objects of different sizes naturally and accurately. Furthermore, the standard location loss neglects the fact that the hard and easy samples may be seriously imbalanced. A forthcoming problem is that it is unable to get more accurate bounding boxes due to the imbalance. To address this problem, an adaptive IoU (AIoU) loss via a simple yet effective squeeze operation is specified in our SCOD. Extensive experiments on PASCAL VOC and MS COCO demonstrate the superiority of our SCOD.

cs.CV↗