Daoyu Wang

Jie Ouyang, Yucong Luo, Mingyue Cheng et al.

This paper presents the solution of our team APEX in the Meta KDD CUP 2024: CRAG Comprehensive RAG Benchmark Challenge. The CRAG benchmark addresses the limitations of existing QA benchmarks in evaluating the diverse and dynamic challenges faced by Retrieval-Augmented Generation (RAG) systems. It provides a more comprehensive assessment of RAG performance and contributes to advancing research in this field. We propose a routing-based domain and dynamic adaptive RAG pipeline, which performs specific processing for the diverse and dynamic nature of the question in all three stages: retrieval, augmentation, and generation. Our method achieved superior performance on CRAG and ranked 2nd for Task 2&3 on the final competition leaderboard. Our implementation is available at this link: https://github.com/USTCAGI/CRAG-in-KDD-Cup2024.

Shuo Yu, Mingyue Cheng, Qi Liu et al.

Retrieval-augmented generation (RAG) is increasingly recognized as an effective approach to mitigating the hallucination of large language models (LLMs) through the integration of external knowledge. While numerous efforts, most studies focus on a single type of external knowledge source. However, in real-world applications, most situations involve diverse knowledge from various sources, yet this area has been less explored. The main dilemma is the lack of a suitable dataset containing multiple knowledge sources and pre-exploration of the associated issues. To address these challenges, we standardize a benchmark dataset that combines structured and unstructured knowledge across diverse and complementary domains. Based on this dataset, we further develop a plug-and-play RAG framework, \textbf{PruningRAG}, whose main characteristic is the use of multi-granularity pruning strategies to optimize the integration of relevant information while minimizing misleading context. It consistently improves performance across various existing RAG variants, demonstrating its robustness and broad applicability. Building upon the standardized dataset and PruningRAG, we also report a series of experimental results, as well as insightful findings. Our dataset and code are publicly available\footnote{https://github.com/USTCAGI/PruningRAG}, with the aim of advancing future research in the RAG community.

Daoyu Wang, Qingchuan Li, Mingyue Cheng et al.

General agents have given rise to phenomenal applications such as OpenClaw and Claude Code. As these agent systems (a.k.a. Harnesses) strive for bolder goals, they demand increasingly stronger agentic capabilities from foundation Large Language Models (LLMs). Agentic Reinforcement Learning (RL) is emerging as a central post-training paradigm for empowering LLMs with these capabilities and is playing an increasingly pivotal role in agent training. Unlike single-turn token-level alignment or reasoning enhancement, as in RLHF and RLVR, Agentic RL targets multi-turn interactive settings, where the goal is to optimize core agentic capabilities such as decision making and tool use while addressing new challenges including delayed and sparse rewards, as well as long and variable context. As a result, the token-centric modeling and optimization paradigm inherited from traditional LLM RL is becoming increasingly inadequate for capturing real LLM agent behavior. In this paper, we present StepPO as a position on step-level Agentic RL. We argue that the conventional token-level Markov Decision Process (MDP) should be advanced to a step-level MDP formulation, and that the step, rather than the token, should be regarded as the proper action representation for LLM agents. We then propose step-level credit assignment as the natural optimization counterpart of this formulation, thereby aligning policy optimization and reward propagation with the granularity of agent decisions. Finally, we discuss the key systems designs required to realize step-level Agentic RL in practice and preliminary experiments provide initial evidence for the effectiveness of this perspective. We hope that the step-aligned, step-level paradigm embodied in StepPO offers the Agentic RL community a useful lens for understanding agent behavior and helps advance LLMs toward stronger general-agent capabilities.

Yaguo Liu, Mingyue Cheng, Daoyu Wang et al.

Time series forecasting can be viewed as a generative problem that requires both semantic understanding over contextual conditions and stochastic modeling of continuous temporal dynamics. Existing approaches typically rely on either autoregressive large language models (LLMs) for semantic context modeling or diffusion-like models for continuous probabilistic generation. However, neither method alone can adequately model both aspects simultaneously. In this work, we propose CoGenCast, a hybrid generative framework that couples pre-trained LLMs with flow-matching mechanism for effective time series forecasting. Specifically, we reconfigure pre-trained decoder-only LLMs into a native forecasting encoder-decoder backbone by modifying only the attention topology, enabling bidirectional context encoding and causal representation generation. Building on this, a flow-matching mechanism is further integrated to model temporal evolution, capturing continuous stochastic dynamics conditioned on the autoregressively generated representation. Notably, CoGenCast naturally supports multimodal forecasting and cross-domain unified training. Extensive experiments on multiple benchmarks show that CoGenCast consistently outperforms previous compared baselines. Code is available at https://github.com/liuyaguo/_CoGenCast.

Mingyue Cheng, Daoyu Wang, Qi Liu et al.

Synthesizing informative commercial reports from massive and noisy web sources is critical for high-stakes business decisions. Although current deep research agents achieve notable progress, their reports still remain limited in terms of quality, reliability, and coverage. In this work, we propose Mind2Report, a cognitive deep research agent that emulates the commercial analyst to synthesize expert-level reports. Specifically, it first probes fine-grained intent, then searches web sources and records distilled information on the fly, and subsequently iteratively synthesizes the report. We design Mind2Report as a training-free agentic workflow that augments general large language models (LLMs) with dynamic memory to support these long-form cognitive processes. To rigorously evaluate Mind2Report, we further construct QRC-Eval comprising 200 real-world commercial tasks and establish a holistic evaluation strategy to assess report quality, reliability, and coverage. Experiments demonstrate that Mind2Report outperforms leading baselines, including OpenAI and Gemini deep research agents. Although this is a preliminary study, we expect it to serve as a foundation for advancing the future design of commercial deep research agents. Our code and data are available at https://github.com/Melmaphother/Mind2Report.

Jintao Zhang, Mingyue Cheng, Xiaoyu Tao et al.

Time series forecasting models are becoming increasingly prevalent due to their critical role in decision-making across various domains. However, most existing approaches represent the coupled temporal patterns, often neglecting the distinction between their specific components. In particular, fluctuating patterns and smooth trends within time series exhibit distinct characteristics. In this work, to model complicated temporal patterns, we propose a Conditional Denoising Polynomial Modeling (CDPM) framework, where probabilistic diffusion models and deterministic linear models are trained end-to-end. Instead of modeling the coupled time series, CDPM decomposes it into trend and seasonal components for modeling them separately. To capture the fluctuating seasonal component, we employ a probabilistic diffusion model based on statistical properties from the historical window. For the smooth trend component, a module is proposed to enhance linear models by incorporating historical dependencies, thereby preserving underlying trends and mitigating noise distortion. Extensive experiments conducted on six benchmarks demonstrate the effectiveness of our framework, highlighting the potential of combining probabilistic and deterministic models. Our code is available at https://github.com/zjt-gpu/CDPM.

Daoyu Wang, Mingyue Cheng, Shuo Yu et al.

Understanding and reasoning on the web-scale scientific literature is a crucial touchstone for large language model (LLM) based agents designed to support complex knowledge-intensive tasks. However, existing works are mainly restricted to tool-free tasks within isolated papers, largely due to the lack of a benchmark for cross-paper reasoning and multi-tool orchestration in real research scenarios. In this work, we propose PaperArena, an evaluation benchmark for agents to address real-world research questions that typically require integrating information across multiple papers with the assistance of external tools. Given a research question, agents should integrate diverse formats across multiple papers through reasoning and interacting with appropriate tools, thereby producing a well-grounded answer. To support standardized evaluation, we provide a modular and extensible platform for agent execution, offering tools such as multimodal parsing, context retrieval, and programmatic computation. Experimental results reveal that even the most advanced LLM powering a well-established agent system achieves merely 38.78% average accuracy. On the hard subset, accuracy drops to only 18.47%, highlighting great potential for improvement. We also present several empirical findings, including that all agents tested exhibit inefficient tool usage, often invoking more tools than necessary to solve a task. We invite the community to adopt PaperArena to develop and evaluate more capable agents for scientific discovery. Our code and data are available https://github.com/Melmaphother/PaperArena.

Shuo Yu, Mingyue Cheng, Daoyu Wang et al.

The primary form of user-internet engagement is shifting from leveraging implicit feedback signals, such as browsing and clicks, to harnessing the rich explicit feedback provided by textual interactive behaviors. This shift unlocks a rich source of user textual history, presenting a profound opportunity for a deeper form of personalization. However, prevailing approaches offer only a shallow form of personalization, as they treat user history as a flat list of texts for retrieval and fail to model the rich temporal and semantic structures reflecting dynamic nature of user interests. In this work, we propose \textbf{MemWeaver}, a framework that weaves the user's entire textual history into a hierarchical memory to power deeply personalized generation. The core innovation of our memory lies in its ability to capture both the temporal evolution of interests and the semantic relationships between different activities. To achieve this, MemWeaver builds two complementary memory components that both integrate temporal and semantic information, but at different levels of abstraction: behavioral memory, which captures specific user actions, and cognitive memory, which represents long-term preferences. This dual-component memory serves as a unified representation of the user, allowing large language models (LLMs) to reason over both concrete behaviors and abstracted traits. Experiments on the Language Model Personalization (LaMP) benchmark validate the efficacy of MemWeaver. Our code is available\footnote{https://github.com/fishsure/MemWeaver}.

Qingchuan Li, Mingyue Cheng, Zirui Liu et al.

Logical reasoning is a core challenge in natural language understanding and a fundamental capability of artificial intelligence, underpinning scientific discovery, mathematical theorem proving, and complex decision-making. Despite the remarkable progress of large language models (LLMs), most current approaches still rely on forward reasoning paradigms, generating step-by-step rationales from premises to conclusions. However, such methods often suffer from redundant inference paths, hallucinated steps, and semantic drift, resulting in inefficient and unreliable reasoning. In this paper, we propose a novel framework, Hypothesis-driven Backward Logical Reasoning (HBLR). The core idea is to integrate confidence-aware symbolic translation with hypothesis-driven backward reasoning. In the translation phase, only high-confidence spans are converted into logical form, such as First-Order Logic (FOL), while uncertain content remains in natural language. A translation reflection module further ensures semantic fidelity by evaluating symbolic outputs and reverting lossy ones back to text when necessary. In the reasoning phase, HBLR simulates human deductive thinking by assuming the conclusion is true and recursively verifying its premises. A reasoning reflection module further identifies and corrects flawed inference steps, enhancing logical coherence. Extensive experiments on five reasoning benchmarks demonstrate that HBLR consistently outperforms strong baselines in both accuracy and efficiency.

Mingyue Cheng, Yucong Luo, Jie Ouyang et al.

Retrieval-Augmented Generation (RAG) has gained significant attention in recent years for its potential to enhance natural language understanding and generation by combining large-scale retrieval systems with generative models. RAG leverages external knowledge sources, such as documents, databases, or structured data, to improve model performance and generate more accurate and contextually relevant outputs. This survey aims to provide a comprehensive overview of RAG by examining its fundamental components, including retrieval mechanisms, generation processes, and the integration between the two. We discuss the key characteristics of RAG, such as its ability to augment generative models with dynamic external knowledge, and the challenges associated with aligning retrieved information with generative objectives. We also present a taxonomy that categorizes RAG methods, ranging from basic retrieval-augmented approaches to more advanced models incorporating multi-modal data and reasoning capabilities. Additionally, we review the evaluation benchmarks and datasets commonly used to assess RAG systems, along with a detailed exploration of its applications in fields such as question answering, summarization, and information retrieval. Finally, we highlight emerging research directions and opportunities for improving RAG systems, such as enhanced retrieval efficiency, model interpretability, and domain-specific adaptations. This paper concludes by outlining the prospects for RAG in addressing real-world challenges and its potential to drive further advancements in natural language processing.

Yucong Luo, Yitong Zhou, Mingyue Cheng et al.

To advance time series forecasting (TSF), various methods have been proposed to improve prediction accuracy, evolving from statistical techniques to data-driven deep learning architectures. Despite their effectiveness, most existing methods still adhere to a fast thinking paradigm-relying on extracting historical patterns and mapping them to future values as their core modeling philosophy, lacking an explicit thinking process that incorporates intermediate time series reasoning. Meanwhile, emerging slow-thinking LLMs (e.g., OpenAI-o1) have shown remarkable multi-step reasoning capabilities, offering an alternative way to overcome these issues. However, prompt engineering alone presents several limitations - including high computational cost, privacy risks, and limited capacity for in-depth domain-specific time series reasoning. To address these limitations, a more promising approach is to train LLMs to develop slow thinking capabilities and acquire strong time series reasoning skills. For this purpose, we propose Time-R1, a two-stage reinforcement fine-tuning framework designed to enhance multi-step reasoning ability of LLMs for time series forecasting. Specifically, the first stage conducts supervised fine-tuning for warmup adaptation, while the second stage employs reinforcement learning to improve the model's generalization ability. Particularly, we design a fine-grained multi-objective reward specifically for time series forecasting, and then introduce GRIP (group-based relative importance for policy optimization), which leverages non-uniform sampling to further encourage and optimize the model's exploration of effective reasoning paths. Experiments demonstrate that Time-R1 significantly improves forecast performance across diverse datasets.

Jiahao Wang, Mingyue Cheng, Qingyang Mao et al.

Large language models (LLMs) have demonstrated their effectiveness in multivariate time series classification (MTSC). Effective adaptation of LLMs for MTSC necessitates informative data representations. Existing LLM-based methods directly encode embeddings for time series within the latent space of LLMs from scratch to align with semantic space of LLMs. Despite their effectiveness, we reveal that these methods conceal three inherent bottlenecks: (1) they struggle to encode temporal and channel-specific information in a lossless manner, both of which are critical components of multivariate time series; (2) it is much difficult to align the learned representation space with the semantic space of the LLMs; (3) they require task-specific retraining, which is both computationally expensive and labor-intensive. To bridge these gaps, we propose TableTime, which reformulates MTSC as a table understanding task. Specifically, TableTime introduces the following strategies: (1) convert multivariate time series into a tabular form, thus minimizing information loss to the greatest extent; (2) represent tabular time series in text format to achieve natural alignment with the semantic space of LLMs; (3) design a reasoning framework that integrates contextual text information, neighborhood assistance, multi-path inference and problem decomposition to enhance the reasoning ability of LLMs and realize zero-shot classification. Extensive experiments performed on 10 publicly representative datasets from UEA archive verify the superiorities of the TableTime.

Xiaoyu Tao, Shilong Zhang, Mingyue Cheng et al.

Time series forecasting plays a vital role in supporting decision-making across a wide range of critical applications, including energy, healthcare, and finance. Despite recent advances, forecasting accuracy remains limited due to the challenge of integrating historical numerical sequences with contextual features, which often comprise unstructured textual data. To address this challenge, we propose TokenCast, an LLM-driven framework that leverages language-based symbolic representations as a unified intermediary for context-aware time series forecasting. Specifically, TokenCast employs a discrete tokenizer to transform continuous numerical sequences into temporal tokens, enabling structural alignment with language-based inputs. To bridge the semantic gap between modalities, both temporal and contextual tokens are embedded into a shared representation space via a pre-trained large language model (LLM), further optimized with autoregressive generative objectives. Building upon this unified semantic space, the aligned LLM is subsequently fine-tuned in a supervised manner to predict future temporal tokens, which are then decoded back into the original numerical space. Extensive experiments on diverse real-world datasets enriched with contextual features demonstrate the effectiveness and generalizability of TokenCast.

Mingyue Cheng, Jie Ouyang, Shuo Yu et al.

Large Language Models (LLMs) are increasingly being explored for building Agents capable of active environmental interaction (e.g., via tool use) to solve complex problems. Reinforcement Learning (RL) is considered a key technology with significant potential for training such Agents; however, the effective application of RL to LLM Agents is still in its nascent stages and faces considerable challenges. Currently, this emerging field lacks in-depth exploration into RL approaches specifically tailored for the LLM Agent context, alongside a scarcity of flexible and easily extensible training frameworks designed for this purpose. To help advance this area, this paper first revisits and clarifies Reinforcement Learning methodologies for LLM Agents by systematically extending the Markov Decision Process (MDP) framework to comprehensively define the key components of an LLM Agent. Secondly, we introduce Agent-R1, a modular, flexible, and user-friendly training framework for RL-based LLM Agents, designed for straightforward adaptation across diverse task scenarios and interactive environments. We conducted experiments on Multihop QA benchmark tasks, providing initial validation for the effectiveness of our proposed methods and framework.