Papers with modular architecture

20 papers
Unifying Language Agent Algorithms with Graph-based Orchestration Engine for Reproducible Agent Research (2025.acl-demo)

Copied to clipboard

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

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

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

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

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

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

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.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations