Yue Fang
Author directoryOther people with similar names: Yue Fang (Peking University, ORCiD 8212)
Unverified author pages with similar names: Yue Fang
2026
AgenticRag-R1: Agentic Reinforcement Learning with Stack Memory for Multi-Step Reasoning, Retrieval and Memorizing
Xinke Jiang | Yue Fang | Zhibang Yang | Jiaran Gao | Zhixin Zhang | Tao Feng | Rihong Qiu | Wentao Zhang | Hongxin Ding | Ruizhe Zhang | Yongxin Xu | Yuheng Huang | Xu Chu | Junfeng Zhao | Yasha Wang
Findings of the Association for Computational Linguistics: EMNLP 2026
Xinke Jiang | Yue Fang | Zhibang Yang | Jiaran Gao | Zhixin Zhang | Tao Feng | Rihong Qiu | Wentao Zhang | Hongxin Ding | Ruizhe Zhang | Yongxin Xu | Yuheng Huang | Xu Chu | Junfeng Zhao | Yasha Wang
Findings of the Association for Computational Linguistics: EMNLP 2026
Retrieval-Augmented Generation (RAG) im- proves the factuality of large language models (LLMs), yet existing RAG systems often struggle with complex, multi-step reasoning that requires adaptive retrieval and continuous revision of intermediate contexts. Recent reinforcement learning (RL)-based agentic RAG methods partially alleviate this issue, but typically rely on coarse-grained action spaces and trajectory-level rewards, resulting in weak reward assignment and a bias toward short-horizon, stereotyped reasoning template. To address, we propose AGENTICRAG-R1, a RL framework that deeply integrates reasoning, retrieval, and memory via a memory stack and fine-grained action space, supported by hierarchical action-aware rewards and an information-aware trajectory rejection strategy to enable effective long-horizon learning. Experiments across a diverse set of multi-hop, open-domain, and agentic reasoning benchmarks, spanning multiple backbone model sizes, demonstrate that AGENTICRAG- R1 consistently outperforms strong baselines. Moreover, AGENTICRAG-R1 learns more robust, interpretable, and memory-aware reasoning behaviors, highlighting the effect of fine-grained action modeling and information- aware optimization for long-horizon reasoning. Our code is anonymous available at https: //github.com/jiangxinke/Harness-RL/ tree/AgenticRAG-R1-Whitebox.
EvoRubrics: Dynamic Rubrics as Rewards via Adversarial Co-Evolution for LLM Reinforcement Learning
Hongxin Ding | Baixiang Huang | Yue Fang | Weibin Liao | Zheng Li | Jinyang Zhang | Zhijing Wu | Junfeng Zhao | Yasha Wang
Findings of the Association for Computational Linguistics: EMNLP 2026
Hongxin Ding | Baixiang Huang | Yue Fang | Weibin Liao | Zheng Li | Jinyang Zhang | Zhijing Wu | Junfeng Zhao | Yasha Wang
Findings of the Association for Computational Linguistics: EMNLP 2026
Rubric-based rewards offer interpretable and fine-grained optimization signals for reinforcement learning in open-ended tasks where verifiable answers are unavailable. However, pre-constructed rubrics remain static throughout training, creating a fundamental mismatch with the evolving policy: fixed criteria gradually lose discriminative power as the model improves, leading to reward saturation and potential hacking. Recent dynamic rubric methods partially address this but rely on external frontier models or ground-truth answers, and update rubrics only at coarse granularity. We propose EvoRubrics, a co-evolutionary RL framework where a Policy LLM and a Rubric Generator jointly improve through adversarial interaction within each training step. As the policy improves under the rubric generator’s guidance, the rubric generator adapts its criteria to remain discriminative and informative, enabling evaluation to track the policy in real time and naturally inducing an automatic curriculum. Experiments show that EvoRubrics consistently outperforms static and dynamic rubric baselines across benchmarks. The learned Rubric Generator further generalizes as a transferable reward model. Notably, even a fully self-supervised variant without any external supervision achieves meaningful gains, suggesting that co-evolution between generation and evaluation alone can provide sufficiently rich learning signals. Our code is publicly available at https://github.com/huangbaixiang100/EvoRubrics.
ScaffoldAgent: Utility-Guided Dynamic Outline Optimization for Open-Ended Deep Research
Zhibang Yang | Xinke Jiang | Yuzhen Xiao | Ruizhe Zhang | Yue Fang | Xinfei Wan | Zhengxing Song | Yuxuan Liu | Yuheng Huang | Junfeng Zhao | Yasha Wang | Xu Chu
Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing
Zhibang Yang | Xinke Jiang | Yuzhen Xiao | Ruizhe Zhang | Yue Fang | Xinfei Wan | Zhengxing Song | Yuxuan Liu | Yuheng Huang | Junfeng Zhao | Yasha Wang | Xu Chu
Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing
Open-ended deep research (OEDR) requires systems to acquire knowledge through multi-round retrieval and generate coherent long-form reports. The outline plays a central role as a structural scaffold that coordinates retrieval, evidence organization, and generation. However, existing methods either fix the outline before writing or refine it with local heuristics, leading to scaffold drift under continuous information accumulation and delayed feedback for evaluating outline modifications. We propose ScaffoldAgent, a utility-guided dynamic outline optimization framework for OEDR. ScaffoldAgent models outline evolution as a structured decision process with three operations: Expansion, Contraction, and Revision, enabling controlled updates to the report scaffold. It further introduces a utility-guided feedback mechanism that estimates the downstream value of each outline operation from retrieval gain, structural coherence, and trial-generation quality. The resulting utility signal guides node selection, operation scheduling, and termination during inference. Experiments on DeepResearch Bench and DeepResearch Gym show that ScaffoldAgent consistently improves long-form report generation and factual grounding over existing deep research agents.
The Weakest Link Tells It All: Outcome-Supervised Process Reward Modeling via Learnable Credit Assignment
Tianyu Jia | Yue Fang | Hongxin Ding | Rihong Qiu | Zhibang Yang | Zhijing Wu | Junfeng Zhao | Yasha Wang | Xu Chu
Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing
Tianyu Jia | Yue Fang | Hongxin Ding | Rihong Qiu | Zhibang Yang | Zhijing Wu | Junfeng Zhao | Yasha Wang | Xu Chu
Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing
Process reward models (PRMs) enhance the reasoning capabilities of large language models (LLMs) by providing fine-grained feedback, yet training PRMs typically requires expensive stepwise annotations. Outcome-supervised PRMs offer a scalable alternative by learning from final-answer correctness alone, but this introduces a fundamental credit assignment challenge, i.e., attributing outcomes to responsible reasoning steps. Existing approaches rely on either uniform or causal assignment, both of which fail to anchor credit in step correctness and thus hinder process error identification.
In this work, we propose Outcome-Supervised Process Reward Modeling via Learnable Credit Assignment (LCA), an outcome-supervised PRM framework that jointly learns credit assignment and reward modeling under the principle of Weakest Link Assignment: a reasoning chain is as strong as its weakest link. To address mutual dependence between credit assignment and reward modeling, we formalize outcome-supervised PRM as a Multiple Instance Learning (MIL) problem and introduce Softmax-Weighted-Sum (SWS) pooling, an MIL pooling technique tailored for strong dependence and redundancy among reasoning states. We establish instance-level Bayes consistency of the resulting learning objective under mild assumptions. Extensive experiments demonstrate that LCA outperforms state-of-the-art outcome-supervised PRMs across multiple tasks and backbones. Code is available at https://github.com/JiaTianyu20031016/MIL.git.
In this work, we propose Outcome-Supervised Process Reward Modeling via Learnable Credit Assignment (LCA), an outcome-supervised PRM framework that jointly learns credit assignment and reward modeling under the principle of Weakest Link Assignment: a reasoning chain is as strong as its weakest link. To address mutual dependence between credit assignment and reward modeling, we formalize outcome-supervised PRM as a Multiple Instance Learning (MIL) problem and introduce Softmax-Weighted-Sum (SWS) pooling, an MIL pooling technique tailored for strong dependence and redundancy among reasoning states. We establish instance-level Bayes consistency of the resulting learning objective under mild assumptions. Extensive experiments demonstrate that LCA outperforms state-of-the-art outcome-supervised PRMs across multiple tasks and backbones. Code is available at https://github.com/JiaTianyu20031016/MIL.git.
SchemaToken: Tokenizing Database Schemas for Efficient and Robust Text-to-SQL Linking
Weibin Liao | Jingwen Liu | Rihong Qiu | Xin Gao | Xinyu Ma | Hongxin Ding | Yue Fang | Yifan Zhu | Yuheng Huang | Junfeng Zhao | Yasha Wang
Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing
Weibin Liao | Jingwen Liu | Rihong Qiu | Xin Gao | Xinyu Ma | Hongxin Ding | Yue Fang | Yifan Zhu | Yuheng Huang | Junfeng Zhao | Yasha Wang
Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing
Schema linking is a crucial step in Text-to-SQL systems, connecting natural language mentions to relevant database tables and columns. Despite recent advances in LLM-based Text-to-SQL models, current approaches face two fundamental limitations: (1) providing detailed column descriptions inflates the input context, often exceeding the model’s effective sequence length, and (2) predicting multi-token column names increases output complexity, making the task fragile to generation errors. To address these challenges, we propose SchemaToken, which represents each database column as a dedicated token in the LLM’s vocabulary. This design compresses column semantics into single embeddings, reducing context length and simplifying prediction. We introduce a two-stage training paradigm: (i) Semantic Alignment, which enables the LLM to understand the newly added schema tokens via structured embeddings, and (ii) Pseudo-task Alignment, which trains the LLM to generate these tokens as an unordered set using reinforcement learning with a Jaccard-based reward. Experiments on multiple benchmark datasets demonstrate that SchemaToken significantly improves schema linking performance, particularly for large and complex schemas, while maintaining computational efficiency. Our code is publicly available at https://github.com/MrBlankness/SchemaToken.
The Imitation Game: When LLMs Learn to Reason Like Programs via Code-Centric Reasoning Data Synthesis
Jinyang Zhang | Weibin Liao | Keqin Bao | Sihang Li | Shaobo Wang | Muyang Ye | Hongxin Ding | Yue Fang | Tianyi Tang | Fei Huang | Kexin Yang | Xingzhang Ren | Dayiheng Liu
Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing
Jinyang Zhang | Weibin Liao | Keqin Bao | Sihang Li | Shaobo Wang | Muyang Ye | Hongxin Ding | Yue Fang | Tianyi Tang | Fei Huang | Kexin Yang | Xingzhang Ren | Dayiheng Liu
Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing
Large Language Models (LLMs) excel at programming tasks but frequently fail at deterministic, fine-grained reasoning in natural language, relying heavily on semantic approximations rather than robust symbolic execution. To bridge this gap, we propose MIMIC, a framework that leverages executable code as a rigorous medium for reasoning data synthesis. MIMIC fundamentally transforms algorithms into verifiable reasoning trajectories through narrative fusion, code-guided test synthesis, and dynamic code instrumentation. Crucially, these explicit intermediate execution states naturally form a Code-Instrumented Reward (CIR), providing dense, high-fidelity process supervision for reinforcement learning without external reward models. Extensive evaluations reveal that models trained via SFT and GRPO on our synthesized dataset achieve substantial, consistent gains. Our method significantly elevates accuracy across general reasoning, complex mathematical benchmarks, and fine-grained deterministic tasks, demonstrating that the procedural rigor of executable code can effectively unlock and enhance the generalized reasoning capabilities of LLMs. Our code and data are available at https://github.com/zjy1298/MIMIC.
ProMed: Shapley Information Gain Guided Reinforcement Learning for Proactive Medical LLMs
Hongxin Ding | Baixiang Huang | Yue Fang | Weibin Liao | Xinke Jiang | Jinyang Zhang | Yinghao Zhu | Zheng Li | Liantao Ma | Junfeng Zhao | Yasha Wang
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Hongxin Ding | Baixiang Huang | Yue Fang | Weibin Liao | Xinke Jiang | Jinyang Zhang | Yinghao Zhu | Zheng Li | Liantao Ma | Junfeng Zhao | Yasha Wang
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Interactive medical questioning is essential in clinical consultations, where physicians must actively gather necessary patient information. Yet existing medical Large Language Models (LLMs) predominantly follow a reactive paradigm, risking diagnostic errors by answering before seeking sufficient details. To bridge this gap, we propose ProMed, a reinforcement learning framework that transitions LLMs toward a proactive paradigm, enabling them to ask clinically valuable questions before decision-making. Central to ProMed is the Shapley Information Gain (SIG) reward, which quantifies a question’s clinical utility as the amount of newly acquired information, while considering its contextual importance via Shapley values. We integrate SIG into a two-stage training pipeline: (1) SIG-Guided Model Initialization uses Monte Carlo Tree Search to construct high-reward interaction trajectories for supervision, and (2) SIG-Augmented Policy Optimization, with a novel SIG-guided Reward Distribution Mechanism that prioritizes informative questions for fine-grained optimization. Experiments on partial-information medical benchmarks show that ProMed significantly outperforms state-of-the-art methods by 6.29% on average and delivers a 54.45% gain over the reactive paradigm, and generalizes robustly to out-of-domain cases. Our codes are available at https://github.com/hxxding/ProMed.
DFAMS: Dynamic-flow guided Federated Alignment based Multi-prototype Search
Zhibang Yang | Xinke Jiang | Rihong Qiu | Ruiqing Li | Yihang Zhang | Yue Fang | Yongxin Xu | Hongxin Ding | Xu Chu | Junfeng Zhao | Yasha Wang
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Zhibang Yang | Xinke Jiang | Rihong Qiu | Ruiqing Li | Yihang Zhang | Yue Fang | Yongxin Xu | Hongxin Ding | Xu Chu | Junfeng Zhao | Yasha Wang
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Federated Retrieval (FR) routes queries across multiple external knowledge sources, to mitigate hallucinations of LLMs, when necessary external knowledge is distributed. However, existing methods struggle to retrieve high-quality and relevant documents for ambiguous queries, especially in cross-domain scenarios, which significantly limits their effectiveness in supporting downstream generation tasks. Inspired by Dynamic Information Flow (DIF), we propose DFAMS, a novel framework that leverages DIF to identify latent query intents and construct semantically aligned knowledge partitions for accurate retrieval across heterogeneous sources. Specifically, DFAMS probes the DIF in LLMs by leveraging gradient signals from a few annotated queries and employing Shapley value-based attribution to trace neuron activation paths associated with intent recognition and subdomain boundary detection. Then, DFAMS leverages DIF to train an alignment module via multi-prototype contrastive learning, enabling fine-grained intra-source modeling and inter-source semantic alignment across knowledge bases. Experimental results across five benchmarks show that DFAMS outperforms advanced FR methods by up to 14.37% in knowledge classification accuracy, 5.38% in retrieval recall, and 6.45% in downstream QA accuracy, demonstrating its effectiveness in complex FR scenarios. Our code is publicly available at https://github.com/Artessay/DFAMS.
2025
3DS: Medical Domain Adaptation of LLMs via Decomposed Difficulty-based Data Selection
Hongxin Ding | Yue Fang | Runchuan Zhu | Xinke Jiang | Jinyang Zhang | Yongxin Xu | Weibin Liao | Xu Chu | Junfeng Zhao | Yasha Wang
Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing
Hongxin Ding | Yue Fang | Runchuan Zhu | Xinke Jiang | Jinyang Zhang | Yongxin Xu | Weibin Liao | Xu Chu | Junfeng Zhao | Yasha Wang
Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing
Large Language Models (LLMs) excel in general language tasks, motivating their adaptation to specialized domains such as healthcare. Effective domain adaptation typically involves supervised fine-tuning (SFT) on carefully selected instruction-tuning data. Current data selection methods adopt a data-centric approach, relying on external annotations and heuristics to identify externally defined high-quality or challenging data. Our exploratory experiments highlight this approach fails to improve the model’s domain performance, due to misalignment between selected data and the model’s knowledge distribution. To tackle this, we propose Decomposed Difficulty-based Data Selection (3DS), a two-stage model-centric data selection framework that aligns data selection with the model’s distribution. 3DS employs Prompt-Driven Data Selection to filter out noise based on the model’s knowledge via explicit alignment in Stage#1, then adopts Decomposed Difficulty-based Data Selection to guide selection via three novel data difficulty metrics, including Instruction Understanding, Response Confidence, and Response Correctness in Stage#2, enhanced by an attention-based importance weighting mechanism for accurate calibration.Extensive experiments in the healthcare domain show 3DS outperforms existing methods by up to 2.97% accuracy, with additional validation in law and general domains, confirming its generalization ability. Our dataset and code are open-sourced at https://github.com/PuppyKnightUniversity/3DS.
HyKGE: A Hypothesis Knowledge Graph Enhanced RAG Framework for Accurate and Reliable Medical LLMs Responses
Xinke Jiang | Ruizhe Zhang | Yongxin Xu | Rihong Qiu | Yue Fang | Zhiyuan Wang | Jinyi Tang | Hongxin Ding | Xu Chu | Junfeng Zhao | Yasha Wang
Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Xinke Jiang | Ruizhe Zhang | Yongxin Xu | Rihong Qiu | Yue Fang | Zhiyuan Wang | Jinyi Tang | Hongxin Ding | Xu Chu | Junfeng Zhao | Yasha Wang
Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
In this paper, we investigate the retrieval-augmented generation (RAG) based on Knowledge Graphs (KGs) to improve the accuracy and reliability of Large Language Models (LLMs). Recent approaches suffer from insufficient and repetitive knowledge retrieval, tedious and time-consuming query parsing, and monotonous knowledge utilization. To this end, we develop a Hypothesis Knowledge Graph Enhanced (HyKGE) framework, which leverages LLMs’ powerful reasoning capacity to compensate for the incompleteness of user queries, optimizes the interaction process with LLMs, and provides diverse retrieved knowledge. Specifically, HyKGE explores the zero-shot capability and the rich knowledge of LLMs with Hypothesis Outputs to extend feasible exploration directions in the KGs, as well as the carefully curated prompt to enhance the density and efficiency of LLMs’ responses. Furthermore, we introduce the HO Fragment Granularity-aware Rerank Module to filter out noise while ensuring the balance between diversity and relevance in retrieved knowledge. Experiments on two Chinese medical multiple-choice question datasets and one Chinese open-domain medical Q&A dataset with two LLM turbos demonstrate the superiority of HyKGE in terms of accuracy and explainability. Code is available at https://github.com/Artessay/HyKGE.
TC–RAG: Turing–Complete RAG’s Case study on Medical LLM Systems
Xinke Jiang | Yue Fang | Rihong Qiu | Haoyu Zhang | Yongxin Xu | Hao Chen | Wentao Zhang | Ruizhe Zhang | Yuchen Fang | Xinyu Ma | Xu Chu | Junfeng Zhao | Yasha Wang
Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Xinke Jiang | Yue Fang | Rihong Qiu | Haoyu Zhang | Yongxin Xu | Hao Chen | Wentao Zhang | Ruizhe Zhang | Yuchen Fang | Xinyu Ma | Xu Chu | Junfeng Zhao | Yasha Wang
Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
In the pursuit of enhancing domain-specific Large Language Models (LLMs), Retrieval-Augmented Generation (RAG) emerges as a promising solution to mitigate issues such as hallucinations, outdated knowledge, and limited expertise in highly specialized queries. However, existing approaches to RAG fall short by neglecting system state variables, which are crucial for ensuring adaptive control, retrieval halting, and system convergence. In this paper, we introduce the Turing-Complete-RAG (TC-RAG) through rigorous proof, a novel framework that addresses these challenges by incorporating a Turing Complete System to manage state variables, thereby enabling more efficient and accurate knowledge retrieval. By leveraging a memory stack system with adaptive retrieval, reasoning, and planning capabilities, TC-RAG not only ensures the controlled halting of retrieval processes but also mitigates the accumulation of erroneous knowledge via Push and Pop actions. In the case study of the medical and general domain, our extensive experiments on seven real-world healthcare and general-domain datasets demonstrate the superiority of TC-RAG over existing methods in accuracy by over 7.20%. Our code, datasets and RAG resources have been available at https://github.com/Artessay/TC-RAG.
Search
Fix author
Co-authors
- Yasha Wang 10
- Junfeng Zhao 10
- Hongxin Ding 9
- Xu Chu 7
- Xinke Jiang 7
- Rihong Qiu 6
- Weibin Liao 5
- Yongxin Xu 5
- Zhibang Yang 4
- Jinyang Zhang 4
- Ruizhe Zhang 4
- Yuheng Huang 3
- Baixiang Huang 2
- Zheng Li 2
- Xinyu Ma 2
- Zhijing Wu 2
- Keqin Bao 1
- Hao Chen 1
- Yuchen Fang 1
- Tao Feng 1
- Jiaran Gao 1
- Xin Gao 1
- Fei Huang 1
- Tianyu Jia 1
- Ruiqing Li 1
- Sihang Li 1
- Dayiheng Liu 1
- Jingwen Liu 1
- Yuxuan Liu 1
- Liantao Ma 1
- Xingzhang Ren 1
- Zhengxing Song 1
- Jinyi Tang 1
- Tianyi Tang 1
- Xinfei Wan 1
- Shaobo Wang 1
- Zhiyuan Wang 1
- Yuzhen Xiao 1
- Kexin Yang 1
- Muyang Ye 1
- Haoyu Zhang 1
- Wentao Zhang 1
- Wentao Zhang 1
- Yihang Zhang 1
- Zhixin Zhang 1
- Runchuan Zhu 1
- Yifan Zhu 1
- Yinghao Zhu 1