Effective memory management is essential for large language model agents to navigate long-horizon tasks. Recent research has explored using Reinforcement Learning to develop specialized memory manager agents. However, existing approaches rely on final task performance as the primary reward, which results in severe reward sparsity and ineffective credit assignment, providing insufficient guidance for individual memory operations. To this end, we propose Fine-Mem, a unified framework designed for fine-grained feedback alignment. First, we introduce a Chunk-level Step Reward to provide immediate step-level supervision via auxiliary chunk-specific question answering tasks. Second, we devise Evidence-Anchored Reward Attribution to redistribute global rewards by anchoring credit to key memory operations, based on the specific memory items utilized as evidence in reasoning. Together, these components enable stable policy optimization and align local memory operations with the long-term utility of memory. Experiments on Memalpha and MemoryAgentBench demonstrate that Fine-Mem consistently outperforms strong baselines, achieving superior success rates across various sub-tasks. Further analysis reveals its adaptability and strong generalization capabilities across diverse model configurations and backbones

Games offer a compelling paradigm for developing general reasoning capabilities in language models, as they naturally demand strategic planning, probabilistic inference, and adaptive decision-making. However, existing self-play approaches rely solely on terminal game outcomes, providing no mechanism to distinguish transferable reasoning patterns from game-specific heuristics. We present STRATAGEM, which addresses two fundamental barriers to reasoning transfer: domain specificity, where learned patterns remain anchored in game semantics, and contextual stasis, where static game contexts fail to cultivate progressive reasoning. STRATAGEM selectively reinforces trajectories exhibiting abstract, domain-agnostic reasoning through a Reasoning Transferability Coefficient, while incentivizing adaptive reasoning development via a Reasoning Evolution Reward. Experiments across mathematical reasoning, general reasoning, and code generation benchmarks demonstrate substantial improvements, with particularly strong gains on competition-level mathematics where multi-step reasoning is critical. Ablation studies and human evaluation confirm that both components contribute to transferable reasoning.

Large vision-language models (LVLMs) have made substantial advances in reasoning tasks at the Olympiad level. Nevertheless, current Olympiad-level multimodal reasoning benchmarks for these models often emphasize single-image analysis and fail to exploit contextual information across multiple images. We present OMIBench, a benchmark designed to evaluate Olympiad-level reasoning when the required evidence is distributed over multiple images. It contains problems from biology, chemistry, mathematics, and physics Olympiads, together with manually annotated rationales and evaluation protocols for both exact and semantic answer matching. Across extensive experiments on OMIBench, we observe meaningful performance gaps in existing models. Even the strongest LVLMs, such as Gemini-3-Pro, attain only about 50% on the benchmark. These results position OMIBench as a focused resources for studying and improving multi-image reasoning in LVLMs.

Existing memory benchmarks for LLM agents evaluate explicit recall of facts, yet overlook implicit memory where experience becomes automated behavior without conscious retrieval. This gap is critical: effective assistants must automatically apply learned procedures or avoid failed actions without explicit reminders. We introduce ImplicitMemBench, the first systematic benchmark evaluating implicit memory through three cognitively grounded constructs drawn from standard cognitive-science accounts of non-declarative memory: Procedural Memory (one-shot skill acquisition after interference), Priming (theme-driven bias via paired experimental/control instances), and Classical Conditioning (Conditioned Stimulus–Unconditioned Stimulus (CS–US) associations shaping first decisions). Our 300-item suite employs a unified Learning/Priming-Interfere-Test protocol with first-attempt scoring. Evaluation of 17 models reveals severe limitations: no model exceeds 66% overall, with top performers DeepSeek-R1 (65.3%), Qwen3-32B (64.1%), and GPT-5 (63.0%) far below human baselines. Analysis uncovers dramatic asymmetries (inhibition 17.6% vs. preference 75.0%) and universal bottlenecks requiring architectural innovations beyond parameter scaling. ImplicitMemBench reframes evaluation from "what agents recall" to "what they automatically enact".

Large Language Models (LLMs) and Large Vision-Language Models (LVLMs) demonstrate strong reasoning capabilities, yet their performance in English significantly outperforms that in low-resource languages, raising fairness concerns in multilingual applications. Existing approaches either rely on costly multilingual training or employ prompting with external translation tools, both of which are resource-intensive and sensitive to translation quality. To address these limitations, we propose a training-free inference-time method to enhance Multilingual Reasoning capabilities via Representation Engineering (MRRE) without using any additional training data or tools. MRRE sequentially injects two precomputed vectors at specific layers during inference processing: cross-lingual reasoning enhancement vectors, which steer non-English reasoning representations toward English space to unlock multilingual reasoning, and target-language output anchoring vectors, which restore the distribution of the target language to preserve input–output language consistency. Comprehensive experiments across six advanced LLMs and LVLMs on four reasoning benchmarks demonstrate that MRRE consistently enhances non-English reasoning by an average gain of 5.48% and up to 7.54% in low-resource languages (e.g., Thai and Swahili), while improving input-output language consistency by 3.78%.

Research is a fundamental process driving the advancement of human civilization, yet it demands substantial time and effort from researchers. In recent years, the rapid development of artificial intelligence (AI) technologies has inspired researchers to explore how AI can accelerate and enhance research. To monitor relevant advancements, this paper presents a systematic review of the progress in this domain. Specifically, we organize the relevant studies into three main categories: hypothesis formulation, hypothesis validation, and manuscript publication. Hypothesis formulation involves knowledge synthesis and hypothesis generation. Hypothesis validation includes the verification of scientific claims, theorem proving, and experiment validation. Manuscript publication encompasses manuscript writing and the peer review process. Furthermore, we identify and discuss the current challenges faced in these areas, as well as potential future directions for research. Finally, we also offer a comprehensive overview of existing benchmarks and tools across various domains that support the integration of AI into the research process. We hope this paper serves as an introduction for beginners and fosters future research.

The application of role-playing large language models (LLMs) is rapidly expanding in both academic and commercial domains, driving an increasing demand for high-precision role-playing models. Simultaneously, the rapid advancement of reasoning techniques has continuously pushed the performance boundaries of LLMs. This intersection of practical role-playing demands and evolving reasoning capabilities raises an important research question: Can reasoning techniques enhance the role-playing capabilities of LLMs?” To address this, we conduct a comprehensive study using 6 role-playing benchmarks, 24 LLMs, and 3 distinct role-playing strategies, comparing the effectiveness of direct zero-shot role-playing, role-playing with Chain-of-Thought (CoT), and role-playing using reasoning-optimized LLMs. Our findings reveal that CoT may reduce role-playing performance, reasoning-optimized LLMs are unsuitable for role-playing, reasoning ability disrupts the role-playing scaling law, and large models still lack proficiency in advanced role-playing. Furthermore, based on extensive experimental results, we propose two promising future research directions: Role-aware Chain-of-Thought for improving role-playing LLMs and Reinforcement Learning for role-playing LLMs, aiming to enhance the adaptability, consistency, and effectiveness of role-playing LLMs for both research and real-world applications.

Code debugging is a crucial task in software engineering, which attracts increasing attention. While remarkable success has been made in the era of large language models (LLMs), current research still focuses on the simple no-library or single-library setting, ignoring the complex multi-library scenario in real-world applications. To address this limitation, we make the first attempt to introduce MLDebugging (Multi-Library Debugging), a comprehensive benchmark designed to assess debugging challenges within multi-library Python code. Specifically, MLDebugging encompasses 126 distinct Python libraries, covering a wide range of multi-library code issues, categorized into seven distinct types. Furthermore, we conduct a thorough evaluation of MLDebugging using both mainstream open-source and closed-source LLMs and highlight that current LLMs still struggle to correctly perform code debugging across multi-library scenarios. We hope this work can uncover the potential of LLMs in multi-library debugging scenario and offer insights for future research.

Large language model unlearning has garnered increasing attention due to its potential to address security and privacy concerns, leading to extensive research in the field. However, existing studies have predominantly focused on instance-level unlearning, specifically targeting the removal of predefined instances containing sensitive content. This focus has left a gap in the exploration of removing an entire entity, which is critical in real-world scenarios such as copyright protection. To close this gap, we propose a novel task named Entity-level unlearning, which aims to erase entity-related knowledge from the target model completely. To investigate this task, we systematically evaluate popular unlearning algorithms, revealing that current methods struggle to achieve effective entity-level unlearning. Then, we further explore the factors that influence the performance of unlearning algorithms, identifying that the knowledge coverage of the forget set and its size play pivotal roles. Notably, our analysis also uncovers that entities introduced through fine-tuning are more vulnerable than pre-trained entities during unlearning. We hope these findings can inspire future improvements in entity-level unlearning for LLMs.

Current large language models (LLMs) often exhibit imbalanced multilingual capabilities due to their English-centric training corpora. To address this, existing fine-tuning approaches operating at the data-level (e.g., through data augmentation or distillation) typically introduce implicit cross-lingual alignment, overlooking the potential for more profound, latent-level cross-lingual interactions. In this work, we propose CC-Tuning, a novel multilingual fine-tuning paradigm that explicitly establishes a cross-lingual connection mechanism at the latent level. During training, CC-Tuning fuses the feed forward activations from both English and non-English inputs, enabling the model to benefit from both linguistic resources. This process is facilitated with a trainable Decision Maker that identifies beneficial activations. Furthermore, during inference, a Transform Matrix is utilized to simulate the cross-lingual connection under monolingual setting through representation transformation. Our experiments on six benchmarks covering 22 languages show that CC-Tuning outperforms vanilla SFT and offers a strong latent-level alternative to data-level augmentation methods. Further analysis also highlights the practicality of CC-Tuning and the potential of latent-level cross-lingual interactions in advancing the multilingual performance of LLMs.

Ensuring contextual faithfulness in retrieval-augmented large language models (LLMs) is crucial for building trustworthy information-seeking systems, particularly in long-form question-answering (LFQA) scenarios. In this work, we identify a salient correlation between LFQA faithfulness and retrieval heads, a set of attention heads responsible for retrieving contextual information. Leveraging this insight, we propose RHIO, a framework designed to teach LLMs to explicitly discriminate between faithful and unfaithful generations. RHIO first augments unfaithful samples that simulate realistic model-intrinsic errors by selectively masking retrieval heads. Then, these samples are incorporated into joint training, enabling the model to distinguish unfaithful outputs from faithful ones conditioned on control tokens. Furthermore, these control tokens are leveraged to self-induce contrastive outputs, amplifying their difference through contrastive decoding. Additionally, to facilitate the evaluation of contextual faithfulness, we also introduce GroundBench, a comprehensive benchmark compiled from five existing LFQA datasets. Extensive experimental results on GroundBench demonstrate that RHIO significantly improves faithfulness, even outperforming GPT-4o.

Large language models (LLMs) encode vast world knowledge but struggle to stay up-to-date, often leading to errors and hallucinations. Knowledge editing offers an efficient alternative to retraining, enabling targeted modifications by updating specific model parameters. However, existing methods primarily focus on individual models, posing challenges in efficiently updating multiple models and adapting to new models. To address this, we propose OnceEdit, a novel ensemble-based approach that employs a plug-in model as the editing module, enabling stable knowledge updates across multiple models. Building on the model ensemble, OnceEdit introduces two key mechanisms to enhance its effectiveness. First, we introduce a dynamic weight mechanism through a weight token for distinguishing between edit-related and non-edit-related instances, ensuring the appropriate utilization of knowledge from integrated models. Second, we incorporate an ensemble enhancement mechanism to mitigate the excessive reliance on the central model inherent in the model ensemble technique, making it more suitable for knowledge editing. Extensive experiments on diverse LLMs demonstrate that OnceEdit consistently outperforms existing methods while achieving superior editing efficiency. Further analysis confirms its adaptability and stability in multi-model editing scenarios.

Large language models (LLMs) are known to suffer from severe hallucination issues. One of the main causes lies in the knowledge misalignment between the pre-training stage and the supervised fine-tuning stage. The unfamiliar knowledge encountered during fine-tuning may encourage LLMs to generate facts that are not grounded in parametric knowledge. To address this, we propose Seal, a novel training objective with an abstention mechanism, in which the model learns to selectively reject tokens that misalign with the desired knowledge distribution via a special [REJ] token. This allows the model the option of acknowledging the insufficiency of knowledge rather than blindly assigning high probability to all ground-truth answers. We further propose a regularized decoding objective that penalizes uncertain predictions during inference by using the [REJ] probability learned during training. Extensive experiments on six short-form and long-form QA datasets with three LLMs of different sizes demonstrate that our method effectively alleviates hallucinations caused by knowledge misalignment. Further analysis highlights the adaptations of our method in answer refusal scenarios and its ability to effectively maintain the model’s instruction-following capabilities.

Built upon the Transformer, large language models (LLMs) have captured worldwide attention due to their remarkable abilities. Nevertheless, all Transformer-based models including LLMs suffer from a preset length limit and can hardly generalize from short training sequences to longer inference ones, namely, they can not perform **length extrapolation** to handle long sequences. Thus, numerous methods have emerged to enhance the length extrapolation of Transformers. Despite the great research efforts, a systematic survey is still lacking. To fill this gap, we delve into these advances in a unified notation from the perspective of positional encoding (PE), as it has been considered the primary factor on length extrapolation. Specifically, we begin with extrapolatable PEs that have dominated this research field. Then, we dive into extrapolation methods based on them, covering position interpolation and randomized position methods. Finally, several challenges and future directions in this area are highlighted. Through this survey, We aim to enable the reader to gain a deep understanding of existing methods and provide stimuli for future research.

Despite the impressive performance on information-seeking tasks, large language models (LLMs) still struggle with hallucinations. Attributed LLMs, which augment generated text with in-line citations, demonstrate potential in mitigating hallucinations and improving verifiability. However, current approaches suffer from suboptimal citation quality due to their reliance on in-context learning. Furthermore, the practice of merely citing document identifiers complicates the process for users to pinpoint specific supporting evidence. In this work, we introduce FRONT, a training framework that teaches LLMs to generate Fine-grained grounded citations. By initially grounding fine-grained supporting quotes, which then guide the generation process, these quotes not only provide supervision signals to improve citation quality but also serve as fine-grained attributions. Experiments on the ALCE benchmark demonstrate the efficacy of FRONT in generating superior grounded responses and highly supportive citations. With LLaMA-2-7B, the framework significantly outperforms all the baselines, achieving an average of 14.21% improvement in citation quality across all datasets, even surpassing ChatGPT.

News summarization in today’s global scene can be daunting with its flood of multilingual content and varied viewpoints from different sources. However, current studies often neglect such real-world scenarios as they tend to focus solely on either single-language or single-document tasks. To bridge this gap, we aim to unify Multi-lingual, Cross-lingual and Multi-document Summarization into a novel task, i.e., MCMS, which encapsulates the real-world requirements all-in-one. Nevertheless, the lack of a benchmark inhibits researchers from adequately studying this invaluable problem. To tackle this, we have meticulously constructed the GLOBESUMM dataset by first collecting a wealth of multilingual news reports and restructuring them into event-centric format. Additionally, we introduce the method of protocol-guided prompting for high-quality and cost-effective reference annotation. In MCMS, we also highlight the challenge of conflicts between news reports, in addition to the issues of redundancies and omissions, further enhancing the complexity of GLOBESUMM. Through extensive experimental analysis, we validate the quality of our dataset and elucidate the inherent challenges of the task. We firmly believe that GLOBESUMM, given its challenging nature, will greatly contribute to the multilingual communities and the evaluation of LLMs.

Large vision-language models (LVLMs) excel across diverse tasks involving concrete images from natural scenes. However, their ability to interpret abstract figures, such as geometry shapes and scientific plots, remains limited due to a scarcity of training datasets in scientific domains.To fill this gap, we introduce Multimodal ArXiv, consisting of ArXivCap and ArXivQA, for enhancing LVLMs scientific comprehension.ArXivCap is a figure-caption dataset comprising 6.4M images and 3.9M captions, sourced from 572K ArXiv papers spanning various scientific domains.Drawing from ArXivCap, we introduce ArXivQA, a question-answering dataset generated by prompting GPT-4V based on scientific figures. ArXivQA greatly enhances open-sourced LVLMs’ mathematical reasoning capabilities, achieving a 10.4% absolute accuracy gain on a multimodal mathematical reasoning benchmark.Furthermore, employing ArXivCap, we devise four vision-to-text tasks for benchmarking LVLMs.Evaluation results with state-of-the-art LVLMs underscore their struggle with the nuanced semantics of academic figures, while domain-specific training yields substantial performance gains.Our error analysis uncovers misinterpretations of visual context, recognition errors, and the production of overly simplified captions by current LVLMs, shedding light on future improvements.

Scientific literature review generation aims to extract and organize important information from an abundant collection of reference papers and produces corresponding reviews while lacking a clear and logical hierarchy. We observe that a high-quality catalogue-guided generation process can effectively alleviate this problem. Therefore, we present an atomic and challenging task named Hierarchical Catalogue Generation for Literature Review as the first step for review generation, which aims to produce a hierarchical catalogue of a review paper given various references. We construct a novel English Hierarchical Catalogues of Literature Reviews Dataset with 7.6k literature review catalogues and 389k reference papers. To accurately assess the model performance, we design two evaluation metrics for informativeness and similarity to ground truth from semantics and structure. Our extensive analyses verify the high quality of our dataset and the effectiveness of our evaluation metrics. We further benchmark diverse experiments on state-of-the-art summarization models like BART and large language models like ChatGPT to evaluate their capabilities. We further discuss potential directions for this task to motivate future research.

Dialogue summarization helps users capture salient information from various types of dialogues has received much attention recently. However, current works mainly focus on English dialogue summarization, leaving other languages less well explored. Therefore, we present a multi-lingual dialogue summarization dataset, namely MSAMSum, which covers dialogue-summary pairs in six languages. Specifically, we derive MSAMSum from the standard SAMSum using sophisticated translation techniques and further employ two methods to ensure the integral translation quality and summary factual consistency. Given the proposed MSAMum, we systematically set up five multi-lingual settings for this task, including a novel mix-lingual dialogue summarization setting. To illustrate the utility of our dataset, we benchmark various experiments with pre-trained models under different settings and report results in both supervised and zero-shot manners. We also discuss some future works towards this task to motivate future researches.

Current dialogue summarization systems usually encode the text with a number of general semantic features (e.g., keywords and topics) to gain more powerful dialogue modeling capabilities. However, these features are obtained via open-domain toolkits that are dialog-agnostic or heavily relied on human annotations. In this paper, we show how DialoGPT, a pre-trained model for conversational response generation, can be developed as an unsupervised dialogue annotator, which takes advantage of dialogue background knowledge encoded in DialoGPT. We apply DialoGPT to label three types of features on two dialogue summarization datasets, SAMSum and AMI, and employ pre-trained and non pre-trained models as our summarizers. Experimental results show that our proposed method can obtain remarkable improvements on both datasets and achieves new state-of-the-art performance on the SAMSum dataset.