Jinyu Guo

Xiang Li, Jiwei Wei, Ke Liu et al.

While Large Language Models (LLMs) achieve impressive performance on multi-step reasoning tasks, their reliability is persistently hindered by critical limitations such as unconstrained hallucinations and poor numerical computation. Fundamentally, these issues arise because standard models treat reasoning as a transient, one-off generation process rather than retaining and refining successful procedural logic. To address these challenges, we propose eMoT (evolving Memory-of-Thought), a unified framework that stabilizes multi-step reasoning by treating reasoning trajectories as dynamic, evolving memories rather than static templates. The framework primarily consists of three interconnected modules: (i) a memory corrosion mechanism that reinforces high-utility reasoning structures while gradually decaying less frequent ones; (ii) a symbolic anchoring engine that utilizes Python for deterministic computation, much like a human uses a calculator; and (iii) a consistency-driven refinement process that aligns neural inference with symbolic outcomes, reducing the accumulation of logical discrepancies. Across multiple reasoning benchmarks, eMoT improves accuracy and solution consistency over standard Chain-of-Thought and structured reasoning baselines.On the traditional task Game of 24, eMoT achieves 100% accuracy, surpassing the baseline by up to 17.6%. Evaluations on mathematical task GSM8K, ASDiv, SVAMP, and MGSM further show consistent gains in multi-step mathematical reasoning. In our evaluation, we achieve superior performance despite utilizing a lightweight backbone model with constrained baseline capabilities. Compared to alternative methods that rely on massively scaled models, our results demonstrate that the performance gains are fundamentally driven by the eMoT framework's reasoning control rather than sheer model size.

Jinyu Guo, Kai Shuang, Jijie Li et al.

In dialogue state tracking, dialogue history is a crucial material, and its utilization varies between different models. However, no matter how the dialogue history is used, each existing model uses its own consistent dialogue history during the entire state tracking process, regardless of which slot is updated. Apparently, it requires different dialogue history to update different slots in different turns. Therefore, using consistent dialogue contents may lead to insufficient or redundant information for different slots, which affects the overall performance. To address this problem, we devise DiCoS-DST to dynamically select the relevant dialogue contents corresponding to each slot for state updating. Specifically, it first retrieves turn-level utterances of dialogue history and evaluates their relevance to the slot from a combination of three perspectives: (1) its explicit connection to the slot name; (2) its relevance to the current turn dialogue; (3) Implicit Mention Oriented Reasoning. Then these perspectives are combined to yield a decision, and only the selected dialogue contents are fed into State Generator, which explicitly minimizes the distracting information passed to the downstream state prediction. Experimental results show that our approach achieves new state-of-the-art performance on MultiWOZ 2.1 and MultiWOZ 2.2, and achieves superior performance on multiple mainstream benchmark datasets (including Sim-M, Sim-R, and DSTC2).

Xunlei Chen, Jinyu Guo, Yuang Li et al.

Large language models (LLMs) have advanced to encompass extensive knowledge across diverse domains. Yet controlling what a LLMs should not know is important for ensuring alignment and thus safe use. However, effective unlearning in LLMs is difficult due to the fuzzy boundary between knowledge retention and forgetting. This challenge is exacerbated by entangled parameter spaces from continuous multi-domain training, often resulting in collateral damage, especially under aggressive unlearning strategies. Furthermore, the computational overhead required to optimize State-of-the-Art (SOTA) models with billions of parameters poses an additional barrier. In this work, we present ALTER, a lightweight unlearning framework for LLMs to address both the challenges of knowledge entanglement and unlearning efficiency. ALTER operates through two phases: (I) high entropy tokens are captured and learned via the shared A matrix in LoRA, followed by (II) an asymmetric LoRA architecture that achieves a specified forgetting objective by parameter isolation and unlearning tokens within the target subdomains. Serving as a new research direction for achieving unlearning via token-level isolation in the asymmetric framework. ALTER achieves SOTA performance on TOFU, WMDP, and MUSE benchmarks with over 95% forget quality and shows minimal side effects through preserving foundational tokens. By decoupling unlearning from LLMs' billion-scale parameters, this framework delivers excellent efficiency while preserving over 90% of model utility, exceeding baseline preservation rates of 47.8-83.6%.

HuaDong Jian, Chenghao Li, Haoyu Wang et al.

In long-horizon open-world multi-agent systems, existing methods often treat local anomalies as automatic triggers for communication. This default design introduces coordination noise, interrupts local execution, and overuses public interaction in cases that could be resolved locally. To address this issue, we propose a partitioned information architecture for MLLM agents that explicitly separates private execution states from public coordination states. Building on this design, we introduce two key mechanisms. First, we develop an event-triggered working memory based on system-verified outcomes to maintain compact and low-noise local state representations. Second, we propose a cost-sensitive gated escalation mechanism that determines whether cross-region communication should be initiated by jointly considering node criticality, local recovery cost, and downstream task impact. In this way, communication is transformed from a default reaction into a selective decision. Experiments conducted on long-term construction tasks in open environments demonstrate that, compared to baseline models based on strong communication and planned structures, the introduction of gated communication and a partitioned information architecture results in superior performance in terms of blueprint completion quality and execution chain length. It also improves local self-recovery, reduces ineffective escalations, and increases the utility of public communication.

Zhaokun Wang, Jinyu Guo, Jingwen Pu et al.

Large language models (LLMs) trained on unfiltered corpora inherently risk retaining sensitive information, necessitating selective knowledge unlearning for regulatory compliance and ethical safety. However, existing parameter-modifying methods face fundamental limitations: high computational costs, uncontrollable forgetting boundaries, and strict dependency on model weight access. These constraints render them impractical for closed-source models, yet current non-invasive alternatives remain unsystematic and reliant on empirical experience. To address these challenges, we propose the Controllable Alignment Prompting for Unlearning (CAP) framework, an end-to-end prompt-driven unlearning paradigm. CAP decouples unlearning into a learnable prompt optimization process via reinforcement learning, where a prompt generator collaborates with the LLM to suppress target knowledge while preserving general capabilities selectively. This approach enables reversible knowledge restoration through prompt revocation. Extensive experiments demonstrate that CAP achieves precise, controllable unlearning without updating model parameters, establishing a dynamic alignment mechanism that overcomes the transferability limitations of prior methods.

Jinyu Guo, Zhihan Zhang, Yutong Li et al.

The quadratic computational complexity of the standard attention mechanism constitutes a fundamental bottleneck for large language models in long-context inference. While existing KV cache compression methods alleviate memory pressure, they often sacrifice generation quality and fail to address the high overhead of floating-point arithmetic. This paper introduces DASH-KV, an innovative acceleration framework that reformulates attention as approximate nearest-neighbor search via asymmetric deep hashing. Under this paradigm, we design an asymmetric encoding architecture that differentially maps queries and keys to account for their distinctions in precision and reuse characteristics. To balance efficiency and accuracy, we further introduce a dynamic mixed-precision mechanism that adaptively retains full-precision computation for critical tokens. Extensive experiments on LongBench demonstrate that DASH-KV significantly outperforms state-of-the-art baseline methods while matching the performance of full attention, all while reducing inference complexity from O(N^2) to linear O(N). The code is available at https://github.com/Zhihan-Zh/DASH-KV

Jiaquan Zhang, Qigan Sun, Chaoning Zhang et al.

Enhancing the reasoning capability of large language models (LLMs) remains a core challenge in natural language processing. The Chain-of-Thought (CoT) paradigm dominates practical applications for its single-round efficiency, yet its reasoning chains often exhibit logical gaps. While multi-round paradigms like Graph-of-Thoughts (GoT), Tree-of-Thoughts (ToT), and Atom of Thought (AoT) achieve strong performance and reveal effective reasoning structures, their high cost limits practical use. To address this problem, this paper proposes a topology-based method for optimizing reasoning chains. The framework embeds essential topological patterns of effective reasoning into the lightweight CoT paradigm. Using persistent homology, we map CoT, ToT, and GoT into a unified topological space to quantify their structural features. On this basis, we design a unified optimization system: a Topological Optimization Agent diagnoses deviations in CoT chains from desirable topological characteristics and simultaneously generates targeted strategies to repair these structural deficiencies. Compared with multi-round reasoning methods like ToT and GoT, experiments on multiple datasets show that our approach offers a superior balance between reasoning accuracy and efficiency, showcasing a practical solution to ``single-round generation with multi-round intelligence''.

Jie Ou, Jinyu Guo, Shiyao Guo et al.

Many-Shot In-Context Learning (ICL) has emerged as a promising paradigm, leveraging extensive examples to unlock the reasoning potential of Large Language Models (LLMs). However, existing methods typically rely on a predetermined, fixed number of shots. This static approach often fails to adapt to the varying difficulty of different queries, leading to either insufficient context or interference from noise. Furthermore, the prohibitive computational and memory costs of long contexts severely limit Many-Shot's feasibility. To address the above limitations, we propose AdapShot, which dynamically optimizes shot counts and leverages KV cache reuse for efficient inference. Specifically, we design a probe-based evaluation mechanism that utilizes output entropy to determine the optimal number of shots. To bypass the redundant prefilling computation during both the probing and inference phases, we incorporate a semantics-aware KV cache reuse strategy. Within this reuse strategy, to address positional encoding incompatibilities, we introduce a decoupling and re-encoding method that enables the flexible reordering of cached key-value pairs. Extensive experiments demonstrate that AdapShot achieves an average performance gain of around 10% and a 4.64x speedup compared to state-of-the-art DBSA.

Yitian Zhou, Chaoning Zhang, Jiaquan Zhang et al.

Long-context large language models remain computationally expensive to run and often fail to reliably process very long inputs, which makes context compression an important component of many systems. Existing compression approaches typically rely on trained compressors, dense retrieval-style selection, or heuristic trimming, and they often struggle to jointly preserve task relevance, topic coverage, and cross-sentence coherence under a strict token budget. To address this, we propose a training-free and model-agnostic compression framework that selects a compact set of sentences guided by structural graph priors. Our method constructs a sparse hybrid sentence graph that combines mutual k-NN semantic edges with short-range sequential edges, extracts a topic skeleton via clustering, and ranks sentences using an interpretable score that integrates task relevance, cluster representativeness, bridge centrality, and a cycle coverage cue. A budgeted greedy selection with redundancy suppression then produces a readable compressed context in original order. Experimental results on four datasets show that our approach is competitive with strong extractive and abstractive baselines, demonstrating larger gains on long-document benchmarks.

Jie Ou, Jinyu Guo, Shuaihong Jiang et al.

Retrieval-augmented generation (RAG) has emerged as a pivotal method for expanding the knowledge of large language models. To handle complex queries more effectively, researchers developed Adaptive-RAG (A-RAG) to enhance the generated quality through multiple interactions with external knowledge bases. Despite its effectiveness, A-RAG exacerbates the pre-existing efficiency challenges inherent in RAG, which are attributable to its reliance on multiple iterations of generation. Existing A-RAG approaches process all retrieved contents from scratch. However, they ignore the situation where there is a significant overlap in the content of the retrieval results across rounds. The overlapping content is redundantly represented, which leads to a large proportion of repeated computations, thus affecting the overall efficiency. To address this issue, this paper introduces a model-agnostic approach that can be generally applied to A-RAG methods, which is dedicated to reducing the redundant representation process caused by the overlapping of retrieval results. Specifically, we use cache access and parallel generation to speed up the prefilling and decoding stages respectively. Additionally, we also propose an instruction-driven module to further guide the model to more effectively attend to each part of the content in a more suitable way for LLMs. Experiments show that our approach achieves 2.79 and 2.33 times significant acceleration on average for prefilling and decoding respectively while maintaining equal generation quality.

Shaozhe Yin, Jinyu Guo, Kai Shuang et al.

Continual Relation Extraction (CRE) aims to continually learn new emerging relations while avoiding catastrophic forgetting. Existing CRE methods mainly use memory replay and contrastive learning to mitigate catastrophic forgetting. However, these methods do not attach importance to the error cases that can reveal the model's cognitive biases more effectively. To address this issue, we propose an instruction-based continual contrastive tuning approach for Large Language Models (LLMs) in CRE. Different from existing CRE methods that typically handle the training and memory data in a unified manner, this approach splits the training and memory data of each task into two parts respectively based on the correctness of the initial responses and treats them differently through dual-task fine-tuning. In addition, leveraging the advantages of LLM's instruction-following ability, we propose a novel instruction-based contrastive tuning strategy for LLM to continuously correct current cognitive biases with the guidance of previous data in an instruction-tuning manner, which mitigates the gap between old and new relations in a more suitable way for LLMs. We experimentally evaluate our model on TACRED and FewRel, and the results show that our model achieves new state-of-the-art CRE performance with significant improvements, demonstrating the importance of specializing in exploiting error cases.

Qian Liang, Yujia Wu, Kuncheng Li et al.

Multimodal Large Language Models (MLLMs) with unified architectures excel across a wide range of vision-language tasks, yet aligning them with personalized image generation remains a significant challenge. Existing methods for MLLMs are frequently subject-specific, demanding a data-intensive fine-tuning process for every new subject, which limits their scalability. In this paper, we introduce MM-R1, a framework that integrates a cross-modal Chain-of-Thought (X-CoT) reasoning strategy to unlock the inherent potential of unified MLLMs for personalized image generation. Specifically, we structure personalization as an integrated visual reasoning and generation process: (1) grounding subject concepts by interpreting and understanding user-provided images and contextual cues, and (2) generating personalized images conditioned on both the extracted subject representations and user prompts. To further enhance the reasoning capability, we adopt Grouped Reward Proximal Policy Optimization (GRPO) to explicitly align the generation. Experiments demonstrate that MM-R1 unleashes the personalization capability of unified MLLMs to generate images with high subject fidelity and strong text alignment in a zero-shot manner.

Runqing Wu, Fei Ye, Qihe Liu et al.

Continual Learning seeks to develop a model capable of incrementally assimilating new information while retaining prior knowledge. However, current research predominantly addresses a straightforward learning context, wherein all data samples originate from a singular data domain. This paper shifts focus to a more complex and realistic learning environment, characterized by data samples sourced from multiple distinct domains. We tackle this intricate learning challenge by introducing a novel methodology, termed the Multi-Source Dynamic Expansion Model (MSDEM), which leverages various pre-trained models as backbones and progressively establishes new experts based on them to adapt to emerging tasks. Additionally, we propose an innovative dynamic expandable attention mechanism designed to selectively harness knowledge from multiple backbones, thereby accelerating the new task learning. Moreover, we introduce a dynamic graph weight router that strategically reuses all previously acquired parameters and representations for new task learning, maximizing the positive knowledge transfer effect, which further improves generalization performance. We conduct a comprehensive series of experiments, and the empirical findings indicate that our proposed approach achieves state-of-the-art performance.

Zhaokun Wang, Jinyu Guo, Jingwen Pu et al.

Current parameter-efficient fine-tuning methods for adapting pre-trained language models to downstream tasks are susceptible to interference from noisy data. Conventional noise-handling approaches either rely on laborious data pre-processing or employ model architecture modifications prone to error accumulation. In contrast to existing noise-process paradigms, we propose a noise-robust adaptation method via asymmetric LoRA poisoning experts (LoPE), a novel framework that enhances model robustness to noise only with generated noisy data. Drawing inspiration from the mixture-of-experts architecture, LoPE strategically integrates a dedicated poisoning expert in an asymmetric LoRA configuration. Through a two-stage paradigm, LoPE performs noise injection on the poisoning expert during fine-tuning to enhance its noise discrimination and processing ability. During inference, we selectively mask the dedicated poisoning expert to leverage purified knowledge acquired by normal experts for noise-robust output. Extensive experiments demonstrate that LoPE achieves strong performance and robustness purely through the low-cost noise injection, which completely eliminates the requirement of data cleaning.

Jinyu Guo, Kai Shuang, Jijie Li et al.

The goal of dialogue state tracking (DST) is to predict the current dialogue state given all previous dialogue contexts. Existing approaches generally predict the dialogue state at every turn from scratch. However, the overwhelming majority of the slots in each turn should simply inherit the slot values from the previous turn. Therefore, the mechanism of treating slots equally in each turn not only is inefficient but also may lead to additional errors because of the redundant slot value generation. To address this problem, we devise the two-stage DSS-DST which consists of the Dual Slot Selector based on the current turn dialogue, and the Slot Value Generator based on the dialogue history. The Dual Slot Selector determines each slot whether to update slot value or to inherit the slot value from the previous turn from two aspects: (1) if there is a strong relationship between it and the current turn dialogue utterances; (2) if a slot value with high reliability can be obtained for it through the current turn dialogue. The slots selected to be updated are permitted to enter the Slot Value Generator to update values by a hybrid method, while the other slots directly inherit the values from the previous turn. Empirical results show that our method achieves 56.93%, 60.73%, and 58.04% joint accuracy on MultiWOZ 2.0, MultiWOZ 2.1, and MultiWOZ 2.2 datasets respectively and achieves a new state-of-the-art performance with significant improvements.