KnowCoder-A1: Incentivizing Agentic Reasoning Capability with Outcome Supervision for KBQA

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Chen, Zhuo, Wang, Fei, Li, Zixuan, Zhang, Zhao, Ding, Weiwei, Yang, Chuanguang, Xu, Yongjun, Jin, Xiaolong, Guo, Jiafeng
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917088144130048
author Chen, Zhuo
Wang, Fei
Li, Zixuan
Zhang, Zhao
Ding, Weiwei
Yang, Chuanguang
Xu, Yongjun
Jin, Xiaolong
Guo, Jiafeng
author_facet Chen, Zhuo
Wang, Fei
Li, Zixuan
Zhang, Zhao
Ding, Weiwei
Yang, Chuanguang
Xu, Yongjun
Jin, Xiaolong
Guo, Jiafeng
contents Knowledge Base Question Answering (KBQA) aims to answer natural-language questions over a structured Knowledge Base (KB). Recent work improves KBQA by adopting an agentic reasoning paradigm, in which Large Language Models (LLMs) iteratively decompose a question, generate its corresponding logical queries, and interact with the KB to derive the answer. However, these methods typically fine-tune LLMs on reasoning trajectories synthesized via process supervision, which offers weak incentives for exploration and thus fails to strengthen the agentic reasoning ability. In this paper, we propose KnowCoder-A1, an LLM that can autonomously perform agentic reasoning on KBs to obtain answers. To incentivize autonomous exploration, KnowCoder-A1 trains the LLM under outcome-only supervision via a multi-stage curriculum reinforcement learning with an easy-to-hard curriculum. To establish foundational agentic capabilities, KnowCoder-A1 first fine-tunes the LLM on a small set of high-quality trajectories obtained through outcome-based rejection sampling. Then, to alleviate the reward sparsity inherent in outcome-only supervision, it applies multi-stage curriculum RL with reward schedules that progress from easy to hard. Trained with outcome-only supervision, KnowCoder-A1 exhibits powerful reasoning behaviors and consistently outperforms prior approaches across three mainstream datasets. Notably, on the zero-shot subset of GrailQA, KnowCoder-A1 achieves up to an 11.1% relative improvement while using only one-twelfth of the training data, demonstrating strong agentic reasoning capabilities.
format Preprint
id arxiv_https___arxiv_org_abs_2510_25101
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle KnowCoder-A1: Incentivizing Agentic Reasoning Capability with Outcome Supervision for KBQA
Chen, Zhuo
Wang, Fei
Li, Zixuan
Zhang, Zhao
Ding, Weiwei
Yang, Chuanguang
Xu, Yongjun
Jin, Xiaolong
Guo, Jiafeng
Artificial Intelligence
Computation and Language
Knowledge Base Question Answering (KBQA) aims to answer natural-language questions over a structured Knowledge Base (KB). Recent work improves KBQA by adopting an agentic reasoning paradigm, in which Large Language Models (LLMs) iteratively decompose a question, generate its corresponding logical queries, and interact with the KB to derive the answer. However, these methods typically fine-tune LLMs on reasoning trajectories synthesized via process supervision, which offers weak incentives for exploration and thus fails to strengthen the agentic reasoning ability. In this paper, we propose KnowCoder-A1, an LLM that can autonomously perform agentic reasoning on KBs to obtain answers. To incentivize autonomous exploration, KnowCoder-A1 trains the LLM under outcome-only supervision via a multi-stage curriculum reinforcement learning with an easy-to-hard curriculum. To establish foundational agentic capabilities, KnowCoder-A1 first fine-tunes the LLM on a small set of high-quality trajectories obtained through outcome-based rejection sampling. Then, to alleviate the reward sparsity inherent in outcome-only supervision, it applies multi-stage curriculum RL with reward schedules that progress from easy to hard. Trained with outcome-only supervision, KnowCoder-A1 exhibits powerful reasoning behaviors and consistently outperforms prior approaches across three mainstream datasets. Notably, on the zero-shot subset of GrailQA, KnowCoder-A1 achieves up to an 11.1% relative improvement while using only one-twelfth of the training data, demonstrating strong agentic reasoning capabilities.
title KnowCoder-A1: Incentivizing Agentic Reasoning Capability with Outcome Supervision for KBQA
topic Artificial Intelligence
Computation and Language
url https://arxiv.org/abs/2510.25101