Retrieval-augmented generation (RAG) systems improve large language model outputs by incorporating external knowledge, enabling more informed and context-aware responses. However, the effectiveness and trustworthiness of these systems critically depends on how they are evaluated, particularly on whether the evaluation process captures real-world constraints like protecting sensitive information. While current evaluation efforts for RAG systems have primarily focused on the development of performance metrics, far less attention has been given to the design and quality of the underlying evaluation datasets, despite their pivotal role in enabling meaningful, reliable assessments. In this work, we introduce a novel multi-agent framework for generating synthetic QA datasets for RAG evaluation that prioritize semantic diversity and privacy preservation. Our approach involves: (1) a Diversity agent leveraging clustering techniques to maximize topical coverage and semantic variability, (2) a Privacy Agent that detects and mask sensitive information across multiple domains and (3) a QA curation agent that synthesizes private and diverse QA pairs suitable as ground truth for RAG evaluation. Extensive experiments demonstrate that our evaluation sets outperform baseline methods in diversity and achieve robust privacy masking on domain-specific datasets. This work offers a practical and ethically aligned pathway toward safer, more comprehensive RAG system evaluation, laying the foundation for future enhancements aligned with evolving AI regulations and compliance standards.

Autoformalization is one of the central tasks in formal verification, while its advancement remains hindered due to the data scarcity and the absence efficient methods. In this work we propose \textbf{FormaRL}, a simple yet efficient reinforcement learning framework for autoformalization which only requires a small amount of unlabeled data. FormaRL integrates syntax check from Lean compiler and consistency check from large language model to calculate the reward, and adopts GRPO algorithm to update the formalizer. We also curated a proof problem dataset from undergraduate-level math materials, named \textbf{uproof}, in the hope to facilitate the exploration of autoformalization and theorem proving in advanced math. Experiments show that FormaRL can increase the pass@1 autoformalization accuracy of Qwen2.5-Coder-7B-Instruct by 4 $\sim$ 6x (4.04\% $\to$ 26.15\% on ProofNet and 2.4\% $\to$ 9.6\% on uproof) with merely 859 unlabeled data. And on uproof our method also achieved a strong improvement in out-of-distribution performance compared to existing open-source state-of-the-art autoformalizers on both pass@1 accuracy (6.2\% $\to$ 9.6\%) and pass@16 accuracy (24.4\% $\to$ 33.6\%). Training code of FormaRL is open-sourced at https://github.com/THUNLP-MT/FormaRL.

Standard single-turn, static benchmarks fall short in evaluating the nuanced capabilities of Large Language Models (LLMs) on complex tasks such as software engineering. In this work, we propose a novel interactive evaluation framework that assesses LLMs on multi-requirement programming tasks through structured, feedback-driven dialogue. Each task is modeled as a requirement dependency graph, and an ``interviewer'' LLM, aware of the ground-truth solution, provides minimal, targeted hints to an ``interviewee'' model to help correct errors and fulfill target constraints. This dynamic protocol enables fine-grained diagnostic insights into model behavior, uncovering strengths and systematic weaknesses that static benchmarks fail to measure. We build on DevAI, a benchmark of 55 curated programming tasks, by adding ground-truth solutions and evaluating the relevance and utility of interviewer hints through expert annotation. Our results highlight the importance of dynamic evaluation in advancing the development of collaborative code-generating agents.

Exploration is essential in modern learning, from reinforcement learning environments with small neural policies to large language models (LLMs). Existing work, such as DPO, leverages full sequence log-likelihoods to capture an entire trajectory of the model's decisions, while methods like GRPO aggregate per-token ratios into a trajectory-level update. However, both often limit exploration on long-horizon tasks. We introduce History-Aggregated Exploratory Policy Optimization (HAEPO), a history-aware exploratory loss to combat these shortcomings. HAEPO compresses each trajectory into the sum of its logarithmic probabilities (a cumulative logarithmic likelihood), and applies a Plackett-Luce softmax across trajectories to obtain normalized weights proportional to their returns, thus encouraging broader exploration. We add entropy regularization to stabilize the aggressive updates to prevent premature collapse and a soft KL penalty relative to a frozen copy of the previous (reference) policy. Empirically, HAEPO converges fast, explores thoroughly, aligns closely with true rewards, and demonstrates robust learning behavior better or at par with PPO, GRPO, and DPO across diverse tasks. Thus, HAEPO provides a stable and interpretable framework by explicitly leveraging full-trajectory history while balancing exploration and stability.

Vector similarity search plays a pivotal role in modern information retrieval systems, especially when powered by transformer-based embeddings. However, the scalability and efficiency of such systems are often hindered by the high dimensionality of latent representations. In this paper, we propose a novel game-theoretic framework for optimizing latent-space compression to enhance both the efficiency and semantic utility of vector search. By modeling the compression strategy as a zero-sum game between retrieval accuracy and storage efficiency, we derive a latent transformation that preserves semantic similarity while reducing redundancy. We benchmark our method against FAISS, a widely-used vector search library, and demonstrate that our approach achieves a significantly higher average similarity (0.9981 vs. 0.5517) and utility (0.8873 vs. 0.5194), albeit with a modest increase in query time. This trade-off highlights the practical value of game-theoretic latent compression in high-utility, transformer-based search applications. The proposed system can be seamlessly integrated into existing LLM pipelines to yield more semantically accurate and computationally efficient retrieval.

Computing education research (CER) is often instigated by practitioners wanting to improve both their own and the wider discipline's teaching practice. However, the latter is often difficult as many researchers lack the colleagues, resources, or capacity to conduct research that is generalisable or rigorous enough to advance the discipline. As a result, research methods that enable sense-making with larger volumes of qualitative data, while not increasing the burden on the researcher, have significant potential within CER. In this discussion paper, we propose such a method for conducting rigorous analysis on large volumes of textual data, namely a variation of LLM-assisted content analysis (LACA). This method combines content analysis with the use of large language models, empowering researchers to conduct larger-scale research which they would otherwise not be able to perform. Using a computing education dataset, we illustrate how LACA could be applied in a reproducible and rigorous manner. We believe this method has potential in CER, enabling more generalisable findings from a wider range of research. This, together with the development of similar methods, can help to advance both the practice and research quality of the CER discipline.

Autoprompting is the process of automatically selecting optimized prompts for language models, which has been gaining popularity with the rapid advancement of prompt engineering, driven by extensive research in the field of large language models (LLMs). This paper presents ReflectivePrompt - a novel autoprompting method based on evolutionary algorithms that employs a reflective evolution approach for more precise and comprehensive search of optimal prompts. ReflectivePrompt utilizes short-term and long-term reflection operations before crossover and elitist mutation to enhance the quality of the modifications they introduce. This method allows for the accumulation of knowledge obtained throughout the evolution process and updates it at each epoch based on the current population. ReflectivePrompt was tested on 33 datasets for classification and text generation tasks using open-access large language models: t-lite-instruct-0.1 and gemma3-27b-it. The method demonstrates, on average, a significant improvement (e.g., 28% on BBH compared to EvoPrompt) in metrics relative to current state-of-the-art approaches, thereby establishing itself as one of the most effective solutions in evolutionary algorithm-based autoprompting.

Large language model (LLM) decoding suffers from high latency due to fragmented execution across operators and heavy reliance on off-chip memory for data exchange and reduction. This execution model limits opportunities for fusion and incurs significant memory traffic and kernel launch overhead. While modern architectures such as NVIDIA Hopper provide distributed shared memory and low-latency intra-cluster interconnects, they expose only low-level data movement instructions, lacking structured abstractions for collective on-chip communication. To bridge this software-hardware gap, we introduce two cluster-level communication primitives, ClusterReduce and ClusterGather, which abstract common communication patterns and enable structured, high-speed data exchange and reduction between thread blocks within a cluster, allowing intermediate results to be on-chip without involving off-chip memory. Building on these abstractions, we design ClusterFusion, an execution framework that schedules communication and computation jointly to expand operator fusion scope by composing decoding stages such as QKV Projection, Attention, and Output Projection into a single fused kernels. Evaluations on H100 GPUs show that ClusterFusion outperforms state-of-the-art inference frameworks by 1.61x on average in end-to-end latency across different models and configurations. The source code is available at https://github.com/xinhao-luo/ClusterFusion.

Enhancing the mathematical reasoning of large language models (LLMs) demands high-quality training data, yet conventional methods face critical challenges in scalability, cost, and data reliability. To address these limitations, we propose a novel program-assisted synthesis framework that systematically generates a high-quality mathematical corpus with guaranteed diversity, complexity, and correctness. This framework integrates mathematical knowledge systems and domain-specific tools to create executable programs. These programs are then translated into natural language problem-solution pairs and vetted by a bilateral validation mechanism that verifies solution correctness against program outputs and ensures program-problem consistency. We have generated 12.3 million such problem-solving triples. Experiments demonstrate that models fine-tuned on our data significantly improve their inference capabilities, achieving state-of-the-art performance on several benchmark datasets and showcasing the effectiveness of our synthesis approach.

The proliferation of misinformation in the digital age has led to significant societal challenges. Existing approaches often struggle with capturing long-range dependencies, complex semantic relations, and the social dynamics influencing news dissemination. Furthermore, these methods require extensive labelled datasets, making their deployment resource-intensive. In this study, we propose a novel self-supervised misinformation detection framework that integrates both complex semantic relations using Abstract Meaning Representation (AMR) and news propagation dynamics. We introduce an LLM-based graph contrastive loss (LGCL) that utilizes negative anchor points generated by a Large Language Model (LLM) to enhance feature separability in a zero-shot manner. To incorporate social context, we employ a multi view graph masked autoencoder, which learns news propagation features from social context graph. By combining these semantic and propagation-based features, our approach effectively differentiates between fake and real news in a self-supervised manner. Extensive experiments demonstrate that our self-supervised framework achieves superior performance compared to other state-of-the-art methodologies, even with limited labelled datasets while improving generalizability.