Papers with modular architecture
Unifying Language Agent Algorithms with Graph-based Orchestration Engine for Reproducible Agent Research (2025.acl-demo)
Copied to clipboard
Qianqian Zhang, Jiajia Liao, Heting Ying, Yibo Ma, Haozhan Shen, Jingcheng Li, Peng Liu, Lu Zhang, Chunxin Fang, Kyusong Lee, Ruochen Xu, Tiancheng Zhao
| Challenge: | Language agents powered by large language models (LLMs) have demonstrated remarkable capabilities in understanding, reasoning, and executing complex tasks. |
| Approach: | They propose a flexible framework that addresses engineering overhead and insufficient evaluation frameworks for fair comparison. |
| Outcome: | The proposed framework simplifies language agent development and establishes a foundation for reproducible agent research. |
LUCE: A Dynamic Framework and Interactive Dashboard for Opinionated Text Analysis (2025.coling-demos)
Copied to clipboard
| Challenge: | LUCE is an advanced dynamic framework for analysing opinionated text . it features computational modules for different elements of opinions, e.g., sentiment/emotion, suggestion, figurative language, hate/toxic speech, and topics. |
| Approach: | They introduce a dynamic framework with an interactive dashboard for analysing opinionated text . it features computational modules of text classification and extraction for different elements of opinions . |
| Outcome: | The framework is validated in a relevant environment and its capabilities and performance demonstrated . it features trained models, python-based APIs, and a user-friendly dashboard . |
MeetDot: Videoconferencing with Live Translation Captions (2021.emnlp-demo)
Copied to clipboard
Arkady Arkhangorodsky, Christopher Chu, Scot Fang, Yiqi Huang, Denglin Jiang, Ajay Nagesh, Boliang Zhang, Kevin Knight
| Challenge: | MeetDot is a videoconferencing system with live translation captions overlaid on screen . currently, the system supports speech and captions in 4 languages . |
| Approach: | They propose a videoconferencing system with live translation captions overlaid on screen . the system supports speech and captions in 4 languages and combines automatic speech recognition and machine translation in a cascade . |
| Outcome: | The proposed system supports speech and captions in 4 languages and has very tight latency requirements to have acceptable call quality. |
A Modular Tool for Automatic Summarization (P19-3)
Copied to clipboard
| Challenge: | Abstractive automatic summarization methods are supervized, but they require large corpora to perform tasks. |
| Approach: | They propose to use a modular tool for automatic summarization that is as simple as possible for end-users. |
| Outcome: | The proposed tool is open source and written in Java . it could be used as a baseline for future work and evaluate methods on different corpora. |
DataArc-SynData-Toolkit: A Unified Closed-Loop Framework for Multi-Path, Multimodal, and Multilingual Data Synthesis (2026.acl-demo)
Copied to clipboard
Zhichao Shi, Cehao Yang, Hao Zhou, Xiaojun Wu, Huajie Li, Xuhui Jiang, Chengjin Xu, Yuanzhuo Wang, Jian Guo
| Challenge: | Existing synthetic data tools are limited by convoluted workflows, fragmented data standards, and limited scalability across modalities. |
| Approach: | They develop an open-source framework that aims to reduce the technical barrier to synthetic data generation and subsequent model training. |
| Outcome: | The proposed framework achieves an optimal balance between generation efficiency and data quality. |
RedactOR: An LLM-Powered Framework for Automatic Clinical Data De-Identification (2025.acl-industry)
Copied to clipboard
Praphul Singh, Charlotte Dzialo, Jangwon Kim, Sumana Srivatsa, Irfan Bulu, Sri Gadde, Krishnaram Kenthapadi
| Challenge: | Existing de-identification methods suffer from recall errors, limited generalization, and inefficiencies, limiting their real-world applicability. |
| Approach: | They propose a multi-modal framework for de-identifying electronic health records using a retrieval-based entity relexicalization approach. |
| Outcome: | The proposed framework achieves competitive performance while optimizing token usage to reduce LLM costs. |
EvoAgentX: An Automated Framework for Evolving Agentic Workflows (2025.emnlp-demos)
Copied to clipboard
| Challenge: | Existing MAS frameworks often require manual workflow configuration and lack native support for dynamic evolution and performance optimization. |
| Approach: | They propose an open-source platform that automates generation, execution, and evolutionary optimization of multi-agent workflows. |
| Outcome: | The proposed platform automates generation, execution, and evolutionary optimization of multi-agent workflows. |
UltraEval-Audio: A Unified Framework for Comprehensive Evaluation of Audio Foundation Models (2026.acl-demo)
Copied to clipboard
Qundong Shi, Jie Zhou, Biyuan Lin, Junbo Cui, Guoyang Zeng, Yixuan Zhou, Ziyang Wang, Xin Liu, Zhen Luo, Yudong Wang, Zhiyuan Liu
| Challenge: | Existing evaluation frameworks for audio foundation models are heavily reliant on English, making it difficult to objectively assess models’ performance on Chinese. |
| Approach: | They propose a unified framework that supports 10 languages, 14 task categories, 24 models, and 36 benchmarks with one-command evaluation and real-time leaderboards. |
| Outcome: | The proposed framework supports 10 languages, 14 task categories, 24 models, and 36 benchmarks with one-command evaluation and real-time leaderboards. |
Goal-Driven Data Story, Narrations and Explanations (2025.naacl-industry)
Copied to clipboard
| Challenge: | Unlike existing tools, our system addresses the ambiguity of vague, multi-line queries, setting a new benchmark in data storytelling by tackling complexities no existing system comprehensively handles. |
| Approach: | They propose a system that processes and interprets vague, open-ended, and multi-line complex queries, transforming them into coherent, actionable data stories. |
| Outcome: | The proposed system processes and interprets vague, open-ended, and multi-line complex queries, transforming them into coherent, actionable data stories. |
Modular Networks for Compositional Instruction Following (2021.naacl-main)
Copied to clipboard
| Challenge: | Standard instruction following models struggle on novel compositions of subgoals observed during training. |
| Approach: | They propose a modular architecture that follows natural language instructions that describe sequences of diverse subgoals. |
| Outcome: | The proposed architecture improves generalization to novel subgoals and environments unseen in training. |
IPR: Intelligent Prompt Routing with User-Controlled Quality-Cost Trade-offs (2025.emnlp-industry)
Copied to clipboard
Aosong Feng, Balasubramaniam Srinivasan, Yun Zhou, Zhichao Xu, Kang Zhou, Sheng Guan, Yueyan Chen, Xian Wu, Ninad Kulkarni, Yi Zhang, Zhengyuan Shen, Dmitriy Bespalov, Soumya Smruti Mishra, Yifei Teng, Darren Yow-Bang Wang, Haibo Ding, Lin Lee Cheong
| Challenge: | Existing systems require users to manually select models or employ rigid routing rules that fail to capture the continuous spectrum of query complexity. |
| Approach: | They propose a quality-constrained intelligent prompt routing framework that automatically selects optimal models based on predicted response quality and user-specified tolerance levels. |
| Outcome: | The proposed framework achieves 43.9% cost reduction while maintaining quality parity with strongest model in the Claude family and processes requests with sub-150ms latency. |
Database reasoning over text (2021.acl-long)
Copied to clipboard
| Challenge: | Existing models cannot handle database queries such as “List/Count all female athletes who were born in 20th century”. |
| Approach: | They propose a modular architecture to answer database-style queries over multiple spans from text and aggregate them at scale. |
| Outcome: | The proposed architecture scales to databases containing thousands of facts whereas current models are limited by how many facts can be encoded. |
Unsupervised Statistical Machine Translation (D18-1)
Copied to clipboard
| Challenge: | Neural Machine Translation (NMT) systems can be trained from monolingual corpora without supervision. |
| Approach: | They propose a phrase-based approach that trains from monolingual corpora . their method is based on phrase-driven Statistical Machine Translation (SMT) they propose to train NMT systems without supervision from monolinguistic corpors . |
| Outcome: | The proposed approach improves on the existing supervised systems by combining a phrase table with an n-gram language model and fine-tuning hyperparameters through an unsupervised MERT variant. |
On the Compositional Generalization in Versatile Open-domain Dialogue (2023.acl-long)
Copied to clipboard
| Challenge: | Existing approaches to multi-task learning suffer from interference among datasets or fail to effectively reuse knowledge and skills learned from other datasets. |
| Approach: | They propose a sparsely activated modular network with a well-rounded set of operators and instantiate each operator with an independent module. |
| Outcome: | The proposed model outperforms state-of-the-art supervised approaches on 4 datasets with only 10% training data thanks to the modular architecture and multi-task learning. |
A Web-based Collaborative Annotation and Consolidation Tool (2020.lrec-1)
Copied to clipboard
| Challenge: | Annotation tools have a rigid structure, closed back-end and front-end, and are built in a non-user-friendly way rendering them unusable for a large cohort. |
| Approach: | They propose a web-based collaborative annotation and consolidation tool (AWOCATo) that supports varied textual formats and allows users to easily adapt to the annotation task. |
| Outcome: | AWOCATo supports a range of tasks and domains, filling the gap left by the lack of tools that can be used by people with and without programming knowledge. |
Fintan - Flexible, Integrated Transformation and Annotation eNgineering (2020.lrec-1)
Copied to clipboard
| Challenge: | Fintan is a platform for converting heterogeneous linguistic resources to RDF. |
| Approach: | They introduce Fintan for converting heterogeneous linguistic resources to RDF with its modular architecture, workflow management and visualization features. |
| Outcome: | The Fintan platform is designed to transform linguistic resources to graphs and graphs. |
Reviving Cultural Heritage: A Novel Approach for Comprehensive Historical Document Restoration (2025.acl-long)
Copied to clipboard
Yuyi Zhang, Peirong Zhang, Zhenhua Yang, Pengyu Yan, Yongxin Shi, Pengwei Liu, Fengjun Guo, Lianwen Jin
| Challenge: | Existing methods for historical document restoration focus on single modality or limited-size restoration, failing to meet practical needs. |
| Approach: | They propose a full-page HDR dataset and an automated HDR solution to replace manual restoration methods. |
| Outcome: | The proposed solution improves OCR accuracy from 46.83% to 84.05% when processing severely damaged documents, with enhancement to 94.25% through human-machine collaboration. |
EVM-QuestBench: An Execution-Grounded Benchmark for Natural-Language Transaction Code Generation (2026.acl-long)
Copied to clipboard
| Challenge: | Existing evaluations of large language models overlook execution accuracy and safety. |
| Approach: | They propose an execution-grounded benchmark for natural-language transaction-script generation on EVM-compatible chains. |
| Outcome: | The proposed benchmark finds large performance gaps in the models with 5 independent rounds. |
Reasoning with Memory: Adaptive Information Management for Retrieval-Augmented Generation (2026.findings-acl)
Copied to clipboard
| Challenge: | Multi-hop reasoning remains a fundamental challenge for Retrieval-Augmented Generation systems. |
| Approach: | They propose a framework that provides a dynamic cognitive workspace for multi-hop reasoning . it uses an explicit working memory that persists across retrieval cycles and is continuously updated . |
| Outcome: | The proposed framework achieves state-of-the-art performance over existing systems on eight QA benchmarks. |
CANDICE: Agentic Causal Disentanglement with Class Conditional Knowledge Integration for Long Tailed Domain Generalization (2026.findings-acl)
Copied to clipboard
| Challenge: | Domain generalization and long-tailed (LT) learning models face two challenges . domain invariance often suppresses class-discriminative signals essential for long-tail recognition. |
| Approach: | They propose a framework that disentangles domain-invariant and class-discriminative features . they evaluate 10 diverse medical imaging datasets spanning four modalities . |
| Outcome: | The proposed framework achieves an average performance improvement of 10.3% across multi-domain and in-domain long-tailed tasks while preserving minority class performance. |