This work formalizes Agentic ER as a decision-theoretic problem, proposes a reference architecture, identifies core research challenges, and outlines new evaluation dimensions tailored to agentic behavior.
Abstract
Entity Resolution (ER) is a fundamental problem in data management, playing a critical role in tasks like data cleaning and knowledge graph construction. The existing ER approaches range from traditional rule-based to deep learning techniques and LLM-based methods, but typically operate under a ``passive paradigm'', as duplicates are detected through static, one-shot similarity computations. Such approaches fail to capture the inherently uncertain and context-dependent nature of real-world ER tasks, especially in data lakes with streaming content in heterogeneous formats such as CSV files, JSON files, RDF dumps, and free text. In such settings, resolving ambiguity often requires iterative evidence gathering, reasoning across multiple sources, even selective human involvement. To cover this gap, we advocate a paradigm shift from passive to Agentic ER, which frames ER as a sequential decision-making process that is performed by autonomous agents. These agents actively plan ER strategies, acquire external evidence, decide when to query additional sources or humans, and optimize trade-offs between accuracy, cost, and latency. We formalize Agentic ER as a decision-theoretic problem, we propose a reference architecture, we identify core research challenges, and outline new evaluation dimensions tailored to agentic behavior. By introducing Agentic ER, we aim to establish a new research direction at the intersection of data management and intelligent agents.
A hybrid knowledge graph generation pipeline that grounds a Large Language Model in the Wikidata multilingual Knowledge Graph while employing an agentic reflexion pattern to synthesize emerging concepts and their associated metadata to generate a comprehensive skills knowledge graph.
Emma Jouffroy, Warren Jouanneau, Marc Palyart· 0 citations
In product entity resolution, relationship definitions constantly evolve with business needs, yet adapting to each change traditionally requires slow, costly human annotation that is often noisy and carries no reasoning. Large vision-language models (VLMs) prompted zero-shot can adapt to a new definition immediately and supply the reasoning that human labels lack, but their cost and latency are prohibitive at production scale. We present MERGED, a distillation framework that transfers not just labels but structured reasoning from large teacher VLMs into a compact 7B-parameter student, requiring no human annotation. Multiple teachers label each product pair and articulate the reasoning behind their decision: agreement pairs supply supervised fine-tuning, while disagreements are resolved by a meta-judge into preference pairs for Direct Preference Optimization. Evaluated against human-labeled ground truth on a multilingual e-commerce dataset, the resulting student improves PR-AUC by 13.79% over the same backbone trained on human labels and surpasses the larger Qwen2.5-32B-VL baseline by 6.32% at 6x lower cost, while also yielding tighter label-reasoning alignment (over 10% above Qwen2.5-32B-VL). Moreover, re-applying MERGED from an existing checkpoint adapts to a new relationship definition with only 10K samples, improving PR-AUC by 6.97% over zero-shot and outperforming from-scratch training. MERGED enables rapid adaptation to evolving relationship definitions, supporting a new one in days rather than months, at a cost and latency suitable for large-scale industrial deployment.
You Chen, Kyoungjun Park, Bin Xu et al.· 0 citations
Knowledge Graph Construction (KGC) is essential for transforming unstructured text into structured knowledge representations. Despite advances in Large Language Models, existing methods treat KGC as a single-pass generation task, conflating extraction, normalization, and validation within a single forward pass. This leads to hallucinated facts, polysemous conflation, and fragmented triples, particularly in open-domain settings where predefined schemas are unavailable. In this work, we propose AgentsKG, a hierarchical multi-agent framework that decouples semantic perception from structural integration. In the Semantic Perception Layer, a multi-role Verification Committee filters hallucinated and invalid assertions through majority voting, while a Contextual Profiler resolves polysemous ambiguities by enriching mentions with context-dependent semantic descriptors. In the Structural Integration Layer, a Knowledge Linker merges redundant entities and relations based on semantic profiles, and an Ontological Logic Auditor enforces logical consistency across the graph. Extensive experiments demonstrate that AgentsKG outperforms state-of-the-art training-free baselines in both extraction accuracy and structural quality, offering a robust approach to open-domain knowledge graph construction without additional training. Source code is available at https://doi.org/10.5281/zenodo.20484211
Shilong Liu, Yongqiang Liu, Jiye Liu et al.· Proceedings of the 32nd ACM...· 0 citations
This work introduces SearchOS, a system-level multi-agent framework that turns fragile, implicit search progress into explicit, persistent, and shared state, and introduces a Search Tool Middleware Harness that intercepts model and tool interactions to record grounded evidence and react to stalls or budget exhaustion.
This work proposes agentic data cracking, a method that structures unstructured data adaptively and speculatively as a byproduct of reasoning itself, a first step toward next-generation data infrastructure for agentic reasoning over unstructured data.
Scientific discovery in data-rich domains is currently constrained by human bandwidth: the growth in the volume and complexity of real-world data far outpaces the rate at which researchers can read, reason, and synthesize. Recent LLM-based multi-agent systems have begun to automate portions of the research cycle, but they target hypothesis generation in settings where validation cannot itself be automated, and each run is one-shot, with no mechanism for findings to accumulate or steer subsequent inquiry. This paper introduces AutoKD, a multi-agent framework for autonomous knowledge discovery that is both computational and cumulative, allowing validated findings to persist and inform subsequent inquiry. Six coordinated LLM agents collaborate in an open-ended discovery loop, where accepted findings are stored in a persistent insight graph that serves as both long-term memory and an exploration-steering mechanism. We evaluate AutoKD on three diverse datasets from two perspectives: Open-ended Quality against published findings, and Conditioned Quality via literature-derived queries. Across both evaluation perspectives, AutoKD covers known findings and surfaces substantive discoveries that complement human-driven research. Our code is available at https://github.com/GeQinwen/AutoKD.
Qinwen Ge, Bo Ni, Haowei Fu et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
