Fine-tuning large language models for code editing has typically relied on mining commits and pull requests. The working hypothesis has been that commit messages describe human intent in natural language, and patches to code describe the changes that implement that intent. However, much of the previously collected data is noisy: commit messages are terse, human-written commits commingle several unrelated edits, and many commits come from simple, rule-based bots. The recent adoption of software engineering agents changes this landscape. Code changes co-authored by humans and agents tend to be more narrowly scoped and focused on clearer goals. Their commit messages, generated by LLMs, articulate intent and rationale in much greater detail. Moreover, when these changes land in public repositories, they are implicitly filtered by humans: maintainers discard low-quality commits to their projects. We present AgentPack, a corpus of 1.3M code edits co-authored by Claude Code, OpenAI Codex, and Cursor Agent across public GitHub projects up to mid-August 2025. We describe the identification and curation pipeline, quantify adoption trends of these agents, and analyze the structural properties of the edits. Finally, we show that models fine-tuned on AgentPack can outperform models trained on prior human-only commit corpora, highlighting the potential of using public data from software engineering agents to train future code-editing models.

Learning to compute, the ability to model the functional behavior of a computational graph, is a fundamental challenge for graph representation learning. Yet, the dominant paradigm is architecturally mismatched for this task. This flawed assumption, central to mainstream message passing neural networks (MPNNs) and their conventional Transformer-based counterparts, prevents models from capturing the position-aware, hierarchical nature of computation. To resolve this, we introduce \textbf{TRACE}, a new paradigm built on an architecturally sound backbone and a principled learning objective. First, TRACE employs a Hierarchical Transformer that mirrors the step-by-step flow of computation, providing a faithful architectural backbone that replaces the flawed permutation-invariant aggregation. Second, we introduce \textbf{function shift learning}, a novel objective that decouples the learning problem. Instead of predicting the complex global function directly, our model is trained to predict only the \textit{function shift}, the discrepancy between the true global function and a simple local approximation that assumes input independence. We validate this paradigm on electronic circuits, one of the most complex and economically critical classes of computational graphs. Across a comprehensive suite of benchmarks, TRACE substantially outperforms all prior architectures. These results demonstrate that our architecturally-aligned backbone and decoupled learning objective form a more robust paradigm for the fundamental challenge of learning to compute on graphs.

Large language models (LLMs) have been widely adopted across various applications, leveraging customized system prompts for diverse tasks. Facing potential system prompt leakage risks, model developers have implemented strategies to prevent leakage, primarily by disabling LLMs from repeating their context when encountering known attack patterns. However, it remains vulnerable to new and unforeseen prompt-leaking techniques. In this paper, we first introduce a simple yet effective prompt leaking attack to reveal such risks. Our attack is capable of extracting system prompts from various LLM-based application, even from SOTA LLM models such as GPT-4o or Claude 3.5 Sonnet. Our findings further inspire us to search for a fundamental solution to the problems by having no system prompt in the context. To this end, we propose SysVec, a novel method that encodes system prompts as internal representation vectors rather than raw text. By doing so, SysVec minimizes the risk of unauthorized disclosure while preserving the LLM's core language capabilities. Remarkably, this approach not only enhances security but also improves the model's general instruction-following abilities. Experimental results demonstrate that SysVec effectively mitigates prompt leakage attacks, preserves the LLM's functional integrity, and helps alleviate the forgetting issue in long-context scenarios.

Reinforcement learning with verifiable rewards (RL VR) is a practical and scalable approach to enhancing large language models in areas such as math, code, and other structured tasks. Two questions motivate this paper: how much of the reported gains survive under strictly parity-controlled evaluation, and whether RL VR is cost-free or exacts a measurable tax. We argue that progress is real, but gains are often overstated due to three forces--an RL VR tax, evaluation pitfalls, and data contamination. Using a partial-prompt contamination audit and matched-budget reproductions across base and RL models, we show that several headline gaps shrink or vanish under clean, parity-controlled evaluation. We then propose a tax-aware training and evaluation protocol that co-optimizes accuracy, grounding, and calibrated abstention and standardizes budgeting and provenance checks. Our position is constructive: RL VR is valuable and industry-ready; we advocate keeping its practical benefits while prioritizing reliability, safety, and measurement. Reinforcement learning with verifiable rewards (RL VR) has become a leading post-training route for improving large language models on math, code, and other structured tasks (Luong et al., 2024; Wen et al., 2025a). By optimizing against automatically computable signals--unit tests for programs, exact numeric or string matches for math, or retrieval-grounded checks for citations--RL VR promises a scalable, label-efficient path to better reasoning. Recent results are striking: across multiple domains, RL VR systems often post large gains on standard benchmarks. Moreover, Figure 2 shows a rise in RL VR-tagged papers alongside improvements on AIME-24/25 through 2024-H1 2025, underscoring both the field's momentum and the need to separate genuine reasoning gains from measurement and budgeting artifacts. Parity-controlled studies show that base models can narrow or erase RL VR gaps when given matched sampling budgets--consistent with smarter search rather than capability expansion (Y ue et al., 2025; Wu et al., 2025a).

We propose ILP-CoT, a method that bridges Inductive Logic Programming (ILP) and Multimodal Large Language Models (MLLMs) for abductive logical rule induction. The task involves both discovering logical facts and inducing logical rules from a small number of unstructured textual or visual inputs, which still remain challenging when solely relying on ILP, due to the requirement of specified background knowledge and high computational cost, or MLLMs, due to the appearance of perceptual hallucinations. Based on the key observation that MLLMs could propose structure-correct rules even under hallucinations, our approach automatically builds ILP tasks with pruned search spaces based on the rule structure proposals from MLLMs, and utilizes ILP system to output rules built upon rectified logical facts and formal inductive reasoning. Its effectiveness is verified through challenging logical induction benchmarks, as well as a potential application of our approach, namely text-to-image customized generation with rule induction. Our code and data are released at https://github.com/future-item/ILP-CoT.

Multimodal large language models (MLLMs) are well suited to image aesthetic assessment, as they can capture high-level aesthetic features leveraging their cross-modal understanding capacity. However, the scarcity of multimodal aesthetic reasoning data and the inherently subjective nature of aesthetic judgment make it difficult for MLLMs to generate accurate aesthetic judgments with interpretable rationales. To this end, we propose Aes-R1, a comprehensive aesthetic reasoning framework with reinforcement learning (RL). Concretely, Aes-R1 integrates a pipeline, AesCoT, to construct and filter high-quality chain-of-thought aesthetic reasoning data used for cold-start. After teaching the model to generate structured explanations prior to scoring, we then employ the Relative-Absolute Policy Optimization (RAPO), a novel RL algorithm that jointly optimizes absolute score regression and relative ranking order, improving both per-image accuracy and cross-image preference judgments. Aes-R1 enables MLLMs to generate grounded explanations alongside faithful scores, thereby enhancing aesthetic scoring and reasoning in a unified framework. Extensive experiments demonstrate that Aes-R1 improves the backbone's average PLCC/SRCC by 47.9%/34.8%, surpassing state-of-the-art baselines of similar size. More ablation studies validate Aes-R1's robust generalization under limited supervision and in out-of-distribution scenarios.

Low-Rank Adaptation (LoRA) is a widely adopted parameter-efficient fine-tuning method for large language models. However, its linear nature limits expressiveness. We propose LoRAN, a non-linear extension of LoRA that applies lightweight transformations to the low-rank updates. We further introduce Sinter, a sine-based activation that adds structured perturbations without increasing parameter count. Experiments across summarization and classification tasks show that LoRAN consistently improves over QLoRA. Ablation studies reveal that Sinter outperforms standard activations such as Sigmoid, ReLU, and Tanh, highlighting the importance of activation design in lowrank tuning.

There is growing interest in using Large Language Models as agents (LLM agents) for social simulations to inform policy, yet real-world adoption remains limited. This paper addresses the question: How can LLM agent simulations be made genuinely useful for policy? We report on a year-long iterative design engagement with a university emergency preparedness team. Across multiple design iterations, we iteratively developed a system of 13,000 LLM agents that simulate crowd movement and communication during a large-scale gathering under various emergency scenarios. These simulations informed actual policy implementation, shaping volunteer training, evacuation protocols, and infrastructure planning. Analyzing this process, we identify three design implications: start with verifiable scenarios and build trust gradually, use preliminary simulations to elicit tacit knowledge, and treat simulation and policy development as evolving together. These implications highlight actionable pathways to making LLM agent simulations that are genuinely useful for policy.

Retrieval-Augmented Generation (RAG) is a framework for grounding Large Language Models (LLMs) in external, up-to-date information. However, recent advancements in context window size allow LLMs to process inputs of up to 128K tokens or more, offering an alternative strategy: supplying the full document context directly to the model, rather than relying on RAG to retrieve a subset of contexts. Nevertheless, this emerging alternative strategy has notable limitations: (i) it is token-inefficient to handle large and potentially redundant contexts; (ii) it exacerbates the `lost in the middle' phenomenon; and (iii) under limited model capacity, it amplifies distraction, ultimately degrading LLM output quality. In this paper, we propose LDAR (Learning Distraction-Aware Retrieval), an adaptive retriever that learns to retrieve contexts in a way that mitigates interference from distracting passages, thereby achieving significantly higher performance with reduced token usage compared to long-context approaches. Extensive experiments across diverse LLM architectures and six knowledge-intensive benchmarks demonstrate the effectiveness and robustness of our approach, highlighting the importance of balancing the trade-off between information coverage and distraction.

Multi-Turn Long-Form Question Answering (MT-LFQA) is a key application paradigm of Large Language Models (LLMs) in knowledge-intensive domains. However, existing benchmarks are limited to single-turn dialogue, while multi-turn dialogue benchmarks typically assess other orthogonal capabilities rather than knowledge-intensive factuality. To bridge this critical gap, we introduce \textbf{KnowMT-Bench}, the \textit{first-ever} benchmark designed to systematically evaluate MT-LFQA for LLMs across knowledge-intensive fields, including medicine, finance, and law. To faithfully assess the model's real-world performance, KnowMT-Bench employs a dynamic evaluation setting where models generate their own multi-turn dialogue histories given logically progressive question sequences. The factual capability and information delivery efficiency of the \textit{final-turn} answer are then evaluated using a human-validated automated pipeline. Our experiments reveal that multi-turn contexts degrade performance: factual capability declines due to the contextual noise from self-generated histories, while information efficiency drops as models become more verbose with increasing dialogue length. We then investigate mitigation strategies, demonstrating that retrieval-augmented generation (RAG) can effectively alleviate and even reverse this factual degradation. These findings underscore the importance of our benchmark in evaluating and enhancing the conversational factual capabilities of LLMs in real-world knowledge-intensive applications. Code is available at \href{https://github.com/hardenyu21/KnowMT-Bench}{\textcolor{cyan}{\texttt{KnowMT-Bench}}}.