Jincheng Dai
Author directory2026
Towards Smart Exploration: Reinforcement Learning for LLM Agents Guided by Meta-Actions
Hanwen Tong | Zhengqi Zhang | Ruixuan Lu | Jincheng Dai | Bin Yang | Bo Zheng | Feng Wei
Findings of the Association for Computational Linguistics: IJCNLP-AACL 2026
Hanwen Tong | Zhengqi Zhang | Ruixuan Lu | Jincheng Dai | Bin Yang | Bo Zheng | Feng Wei
Findings of the Association for Computational Linguistics: IJCNLP-AACL 2026
Reinforcement Learning (RL) has empowered Large Language Model (LLM) agents to tackle long-horizon tasks through multi-step interactions with the environment. However, current LLM agents still rely on inefficient trial-and-error exploration, leading to frequent task failures and redundant actions. In this paper, we propose MetaAct, an RL framework that incorporates a set of high-level meta-actions to explicitly guide the agent towards promising trajectories and facilitate goal-aware exploration. Specifically, the agent is required to predict one of four meta-actions (FOCUS, GUESS, RESUME, UNDO) to constrain the direction of its subsequent actions to minimize unproductive trials. More importantly, we employ group-based RL with episode-level and step-level advantages to fine-tune the agent, enabling it to identify strategic directions more accurately and generate effective task-specific actions. Experimental results demonstrate that our method consistently outperforms the state-of-the-art approaches on ALFWorld and WebShop, achieving higher success rates with fewer steps. Our code and data are publicly available at https://github.com/HavenTong/MetaAct.
2024
Advancement in Graph Understanding: A Multimodal Benchmark and Fine-Tuning of Vision-Language Models
Qihang Ai | Jiafan Li | Jincheng Dai | Jianwu Zhou | Lemao Liu | Haiyun Jiang | Shuming Shi
Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Qihang Ai | Jiafan Li | Jincheng Dai | Jianwu Zhou | Lemao Liu | Haiyun Jiang | Shuming Shi
Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Graph data organizes complex relationships and interactions between objects, facilitating advanced analysis and decision-making across different fields. In this paper, we propose a new paradigm for interactive and instructional graph data understanding and reasoning.Instead of adopting complex graph neural models or heuristic graph-to-text instruction design, we leverage Vision-Language Models (VLMs) to encode the graph images with varying structures across different domains. This paper first evaluates the capabilities of public VLMs in graph learning from multiple aspects. Then it introduces a novel instruction-following dataset for multimodal graph understanding and reasoning in English and Chinese. Besides, by fine-tuning MiniGPT-4 and LLaVA on our dataset, we achieved an accuracy increase of 5%-15% compared to baseline models, with the best-performing model attaining scores comparable to Gemini in GPT-asissted Evaluation. This research not only showcases the potential of integrating VLMs with graph data but also opens new avenues for advancements in graph data understanding.
Search