arXiv:2603.01875v2 Announce Type: replace-cross Abstract: Knowledge distillation (KD) is an essential technique to compress large language models (LLMs) into smaller ones. However, despite the distinct roles of the student model and the teacher model in KD, most existing frameworks still use a homogeneous training backend (e.g., FSDP and DeepSpeed) for both models, leading to suboptimal training efficiency. In this paper, we present a novel framework for LLM distillation, termed \textbf{KDFlow}, which features a decoupled architecture and employs SGLang for teacher inference. By bridging the training efficiency of FSDP2 and the inference efficiency of SGLang, KDFlow achieves full utilization of both advantages in a unified system. Moreover, instead of transferring full logits across different processes, our framework only transmits the teacher's hidden states using zero-copy data transfer and recomputes the logits on the student side, effectively balancing the communication cost and KD performance. Furthermore, our framework supports both off-policy and on-policy distillation and incorporates KD algorithms for cross-tokenizer KD through highly extensible and user-friendly APIs. Experiments show that KDFlow can achieve \textbf{1.44$\times$ to 6.36$\times$} speedup compared to current KD frameworks, enabling researchers to rapidly prototype and scale LLM distillation with minimal engineering overhead. Code is available at: https://github.com/songmzhang/KDFlow

Nature Biotechnology, Published online: 18 March 2026; doi:10.1038/s41587-026-03054-y

Solid tumors are sensitized to anti‑PD‑L1 immunotherapy by engineered E. coli to produce nitric oxide.

arXiv:2508.11360v2 Announce Type: replace Abstract: As autonomous agents become adept at understanding and interacting with graphical user interface (GUI) environments, a new era of automated task execution is emerging. Recent studies have demonstrated that Reinforcement Learning (RL) can effectively enhance agents' performance in dynamic interactive GUI environments. However, these methods face two key limitations: (1) they overlook the significant variation in difficulty across different GUI tasks by treating the entire training data as a uniform set, which hampers the agent's ability to adapt its learning process; and (2) most approaches collapse task-specific nuances into a single, coarse reward, leaving the agent with a uniform signal that yields inefficient policy updates. To address these limitations, we propose CRAFT-GUI, a curriculum learning framework based on Group Relative Policy Optimization (GRPO) that explicitly accounts for the varying difficulty across trajectories. To enable more fine-grained policy optimization, we design a reward function that combines simple rule-based signals with model-judged evaluation, providing richer and more nuanced feedback during training. Experimental results demonstrate that our method achieves significant improvements over previous state-of-the-art approaches, outperforming them by 5.6% on public benchmarks Android Control and 10.3% on our internal online benchmarks, respectively. These findings empirically validate the effectiveness of integrating reinforcement learning with curriculum learning in GUI interaction tasks.

arXiv:2603.05772v2 Announce Type: replace-cross Abstract: Currently, open-sourced large language models (OSLLMs) have demonstrated remarkable generative performance. However, as their structure and weights are made public, they are exposed to jailbreak attacks even after alignment. Existing attacks operate primarily at shallow levels, such as the prompt or embedding level, and often fail to expose vulnerabilities rooted in deeper model components, which creates a false sense of security for successful defense. In this paper, we propose \textbf{\underline{S}}afety \textbf{\underline{A}}ttention \textbf{\underline{H}}ead \textbf{\underline{A}}ttack (\textbf{SAHA}), an attention-head-level jailbreak framework that explores the vulnerability in deeper but insufficiently aligned attention heads. SAHA contains two novel designs. Firstly, we reveal that deeper attention layers introduce more vulnerability against jailbreak attacks. Based on this finding, \textbf{SAHA} introduces \textit{Ablation-Impact Ranking} head selection strategy to effectively locate the most vital layer for unsafe output. Secondly, we introduce a boundary-aware perturbation method, \textit{i.e. Layer-Wise Perturbation}, to probe the generation of unsafe content with minimal perturbation to the attention. This constrained perturbation guarantees higher semantic relevance with the target intent while ensuring evasion. Extensive experiments show the superiority of our method: SAHA improves ASR by 14\% over SOTA baselines, revealing the vulnerability of the attack surface on the attention head. Our code is available at https://anonymous.4open.science/r/SAHA.

arXiv:2603.05773v2 Announce Type: replace-cross Abstract: Safety alignment is often conceptualized as a monolithic process wherein harmfulness detection automatically triggers refusal. However, the persistence of jailbreak attacks suggests a fundamental mechanistic decoupling. We propose the \textbf{\underline{D}}isentangled \textbf{\underline{S}}afety \textbf{\underline{H}}ypothesis \textbf{(DSH)}, positing that safety computation operates on two distinct subspaces: a \textit{Recognition Axis} ($\mathbf{v}_H$, ``Knowing'') and an \textit{Execution Axis} ($\mathbf{v}_R$, ``Acting''). Our geometric analysis reveals a universal ``Reflex-to-Dissociation'' evolution, where these signals transition from antagonistic entanglement in early layers to structural independence in deep layers. To validate this, we introduce \textit{Double-Difference Extraction} and \textit{Adaptive Causal Steering}. Using our curated \textsc{AmbiguityBench}, we demonstrate a causal double dissociation, effectively creating a state of ``Knowing without Acting.'' Crucially, we leverage this disentanglement to propose the \textbf{Refusal Erasure Attack (REA)}, which achieves State-of-the-Art attack success rates by surgically lobotomizing the refusal mechanism. Furthermore, we uncover a critical architectural divergence, contrasting the \textit{Explicit Semantic Control} of Llama3.1 with the \textit{Latent Distributed Control} of Qwen2.5. The code and dataset are available at https://anonymous.4open.science/r/DSH.

arXiv:2602.19320v1 Announce Type: cross Abstract: Agentic memory systems enable large language model (LLM) agents to maintain state across long interactions, supporting long-horizon reasoning and personalization beyond fixed context windows. Despite rapid architectural development, the empirical foundations of these systems remain fragile: existing benchmarks are often underscaled, evaluation metrics are misaligned with semantic utility, performance varies significantly across backbone models, and system-level costs are frequently overlooked. This survey presents a structured analysis of agentic memory from both architectural and system perspectives. We first introduce a concise taxonomy of MAG systems based on four memory structures. Then, we analyze key pain points limiting current systems, including benchmark saturation effects, metric validity and judge sensitivity, backbone-dependent accuracy, and the latency and throughput overhead introduced by memory maintenance. By connecting the memory structure to empirical limitations, this survey clarifies why current agentic memory systems often underperform their theoretical promise and outlines directions for more reliable evaluation and scalable system design.

arXiv:2602.13971v1 Announce Type: cross Abstract: Recommendation systems are essential for personalizing e-commerce shopping experiences. Among these, Trigger-Induced Recommendation (TIR) has emerged as a key scenario, which utilizes a trigger item (explicitly represents a user's instantaneous interest), enabling precise, real-time recommendations. Although several trigger-based techniques have been proposed, most of them struggle to address the intent myopia issue, that is, a recommendation system overemphasizes the role of trigger items and narrowly focuses on suggesting commodities that are highly relevant to trigger items. Meanwhile, existing methods rely on collaborative behavior patterns between trigger and recommended items to identify the user's preferences, yet the sparsity of ID-based interaction restricts their effectiveness. To this end, we propose the Deep Adaptive Intent-Aware Network (DAIAN) that dynamically adapts to users' intent preferences. In general, we first extract the users' personalized intent representations by analyzing the correlation between a user's click and the trigger item, and accordingly retrieve the user's related historical behaviors to mine the user's diverse intent. Besides, sparse collaborative behaviors constrain the performance in capturing items associated with user intent. Hence, we reinforce similarity by leveraging a hybrid enhancer with ID and semantic information, followed by adaptive selection based on varying intents. Experimental results on public datasets and our industrial e-commerce datasets demonstrate the effectiveness of DAIAN.

arXiv:2511.14853v2 Announce Type: replace Abstract: Assuring the trustworthiness and safety of AI systems, e.g., autonomous vehicles (AV), depends critically on the data-related safety properties, e.g., representativeness, completeness, etc., of the datasets used for their training and testing. Among these properties, this paper focuses on representativeness-the extent to which the scenario-based data used for training and testing, reflect the operational conditions that the system is designed to operate safely in, i.e., Operational Design Domain (ODD) or expected to encounter, i.e., Target Operational Domain (TOD). We propose a probabilistic method that quantifies representativeness by comparing the statistical distribution of features encoded by the scenario suites with the corresponding distribution of features representing the TOD, acknowledging that the true TOD distribution is unknown, as it can only be inferred from limited data. We apply an imprecise Bayesian method to handle limited data and uncertain priors. The imprecise Bayesian formulation produces interval-valued, uncertainty-aware estimates of representativeness, rather than a single value. We present a numerical example comparing the distributions of the scenario suite and the inferred TOD across operational categories-weather, road type, time of day, etc., under dependencies and prior uncertainty. We estimate representativeness locally (between categories) and globally as an interval.