# SEAL: Self-Evolving Agentic Learning for Conversational Question Answering over Knowledge Graphs Source: [SEAL: Self-Evolving Agentic Learning for Conversational Question Answering over Knowledge Graphs]() Collection index: [llms.txt]() Data updated: 2026-05-28T05:00:05.404Z Authors: Hao Wang, Jialun Zhong, Changcheng Wang, Zhujun Nie, Zheng Li, Shunyu Yao, Yanzeng Li, Xinchi Li Published: 2025-12-04T14:52:30.000Z ## Abstract Knowledge-based conversational question answering (KBCQA) confronts persistent challenges in resolving coreference, modeling contextual dependencies, and executing complex logical reasoning. Existing approaches often suffer from inaccuracies and prohibitive computational costs, particularly when processing intricate queries over large knowledge graphs. Specifically, large language models (LLMs) tend to generate syntactically invalid or semantically misaligned logical forms for complex multi-hop or aggregation queries, while conventional entity-relation linking methods face an exponentially growing candidate space. To address these limitations, we introduce SEAL, a novel two-stage semantic parsing framework grounded in self-evolving agentic learning. In the first stage, an LLM extracts a minimal S-expression core capturing the essential semantics, which is then refined by an agentic calibration module to correct syntactic inconsistencies and align entities and relations with the knowledge graph. The second stage employs template-based completion guided by question-type prediction to construct a fully executable S-expression. Crucially, SEAL incorporates a self-evolving mechanism integrating local and global memory with a reflection module, enabling continuous adaptation from dialog history and execution feedback without explicit retraining. Extensive experiments on the SPICE benchmark demonstrate that SEAL achieves state-of-the-art performance in multi-hop reasoning, comparison, and aggregation tasks, validating notable gains in both structural accuracy and computational efficiency. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Knowledge Base Question Answering on SPICE (test)](): Knowledge Base Question Answering; SPICE (test); m-F1 (Logical Reasoning): 73.08. ## Original sources and implementation [Original paper]() [PDF]()