KnowCoder-A1: Incentivizing Agentic Reasoning Capability with Outcome Supervision for KBQA
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| 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 |