Academic Intelligence · Curated Daily

探索全球前沿学术脉络

AcademicHub 汇聚顶级期刊与预印本平台的实时文献。定制您的专属科研雷达,利用大语言模型自动生成交叉领域文献分析简报。

01.
medRxiv (Medicine) 2026-06-19

A soluble bi-specific fusion protein for the improved expansion of human CD8+ CAR-T cells

The success of Chimeric Antigen Receptor (CAR) T cell therapy is heavily dependent on the quality of the final cellular product. Current expansion protocols often rely on reagents that require removal from cell culture media, posing logistical challenges in manufacturing, and can also lead to terminal differentiation. Here, we evaluate the use of a soluble, bead-free T cell activator, T cell expansion protein (T-CEP), as a streamlined alternative for generating potent CAR-T cells. Human T cells were activated with T-CEP or known T cell activators (Dynabeads and TransAct) and transduced with either CD19 or interleukin-13 (IL-13) mutein (tetravariant-13; TV-13)-based CAR lentiviral vectors. Our results demonstrate that T-CEP supports robust CAR-T cell expansion and achieves transduction efficiencies comparable to commercial reagents for both types of CAR-T cells. Notably, T-CEP significantly favored the expansion of CD8+ T cells, yielding an enhanced CD27+ phenotype and a lower CD4:CD8 ratio compared to TransAct. Cytotoxicity assays confirmed that T-CEP-expanded CAR-T cells possess cytolytic function equivalent to commercial reagents for both CARs, while exhibiting lower levels of inflammatory cytokine secretion. In summary, T-CEP represents a competitive alternative to existing expansion agents, as it does not require its removal during CAR-T manufacturing and generates a CD8+ dominant, less-differentiated phenotype without compromising efficacy.

02.
arXiv (CS.LG) 2026-06-17

On Randomized Algorithms in Online Strategic Classification

arXiv:2602.06257v2 Announce Type: replace Abstract: Online strategic classification studies settings in which agents strategically modify their features to obtain favorable predictions. For example, given a classifier that determines loan approval based on credit scores, applicants may open or close credit cards and bank accounts to obtain a positive prediction. The learning goal is to achieve low mistake or regret bounds despite such behavior. While randomized algorithms have the potential to offer advantages to the learner in strategic settings, they have been largely underexplored. In the realizable setting, no lower bound is known for randomized algorithms, and existing lower bound constructions for deterministic learners can be circumvented by randomization. In the agnostic setting, the best known regret upper bound is $O(T^{3/4}\log^{1/4}T|\mathcal H|)$, which is far from the standard online learning rate of $O(\sqrt{T\log|\mathcal H|})$. In this work, we provide refined bounds for online strategic classification in both settings; our bounds depend on the Littlestone dimension $\mathrm{Ldim}(\mathcal H)$ of the hypothesis class $\mathcal H$ and the maximum degree $\Delta$ of the manipulation graph. In the realizable setting, we extend, for $T > \mathrm{Ldim}(\mathcal H) \Delta^2$, the existing lower bound $\Omega(\mathrm{Ldim}(\mathcal H) \Delta)$ for deterministic learners to all learners. This yields the first lower bound that applies to randomized learners. We then provide the first randomized learner that improves the known (deterministic) upper bound of $O(\mathrm{Ldim}(\mathcal H) \cdot \Delta \log \Delta)$. In the agnostic setting, we give an improper randomized learner that improves the regret upper bound to $O(\sqrt{T\log|\mathcal H|})$, matching the standard online learning rate. We also show a larger lower bound for all proper learning rules, demonstrating that improperness is necessary to achieve the optimal rate.

03.
arXiv (math.PR) 2026-06-16

A 0-1 Law for Multifractal Spectra via the HGDS Scale Derivative

arXiv:2606.15850v1 Announce Type: new Abstract: We prove that the multifractal spectrum D(h,omega) of a stochastic process is almost surely deterministic under a scale decorrelation condition on the HGDS scale derivative. The key difficulty is that the pointwise Hölder exponent lives in the germ sigma-algebra, where classical 0-1 laws do not reach. We get around this by working with the geometry accumulation integral G_Lambda, which is a genuine Lebesgue integral over scales and concentrates almost surely. The boundary case – log-correlated fields – is sharp: the variance summability condition fails exactly there.

04.
arXiv (CS.CV) 2026-06-16

Understanding Cross-Modal Contributions in Continual Vision-Language Models: A Theoretical Perspective

Continual vision-language models are commonly addressed through sequential fine-tuning; however, although this paradigm enables adaptation to new environments (tasks), it inherently emphasizes the contribution of previously learned environments (tasks) at the expense of the stability required to preserve previously acquired knowledge. While existing approaches have adequately studied continual learning and catastrophic forgetting in vision-language models (VLMs), the theoretical understanding of modality-specific contributions across a sequence of environments remains largely unexplored. In this paper, we present a new theoretical perspective to understand the cross-modal (vision-language) contributions to consecutive environments. We empirically evaluate our theoretical findings on large VLMs and demonstrate their effectiveness in capturing environment-level cross-modal contributions. Our analysis provides deeper insights into continual VLMs, highlighting their contribution robustness to varying task orders and inter-task similarities, and their improved generalization performance.

05.
arXiv (CS.CV) 2026-06-12

V-JEPA 2.1: Unlocking Dense Features in Video Self-Supervised Learning

We present V-JEPA 2.1, a family of self-supervised models that learn dense, high-quality visual representations for both images and videos while retaining strong global scene understanding. The approach combines four key components. First, a dense predictive loss uses a masking-based objective in which both visible and masked tokens contribute to the training signal, encouraging explicit spatial and temporal grounding. Second, deep self-supervision applies the self-supervised objective hierarchically across multiple intermediate encoder layers to improve representation quality. Third, multi-modal tokenizers enable unified training across images and videos. Finally, the model benefits from effective scaling in both model capacity and training data. Together, these design choices produce representations that are spatially structured, semantically coherent, and temporally consistent. Empirically, V-JEPA 2.1 achieves state-of-the-art performance on several challenging benchmarks, including 7.71 mAP on Ego4D for short-term object-interaction anticipation and 40.8 Recall@5 on EPIC-KITCHENS for high-level action anticipation, as well as a 20-point improvement in real-robot grasping success rate over V-JEPA-2 AC. The model also demonstrates strong performance in robotic navigation (5.687 ATE on TartanDrive), depth estimation (0.307 RMSE on NYUv2 with a linear probe), and global recognition (77.7 on Something-Something-V2). These results show that V-JEPA 2.1 significantly advances the state of the art in dense visual understanding and world modeling.

06.
arXiv (math.PR) 2026-06-15

Upper tails for irregular graphs beyond the mean-field regime

arXiv:2606.14564v1 Announce Type: new Abstract: Let $G_{n,p}$ be the binomial random graph of density $p$ and let $X_H$ be the number of copies of a fixed graph $H$ in $G_{n,p}$. We prove asymptotically tight bounds on the logarithmic upper-tail probability of $X_H$ whenever $H$ is a connected, irregular graph with maximum degree $\Delta \ge 2$ and $p \ge n^{-1/\Delta - \varepsilon_H} (\log n)^{\omega(1)}$ for an explicit $\varepsilon_H >0$. These bounds are expressed in terms of a new variational problem that generalises the combinatorial optimisation problem arising from the naïve mean-field approximation. This new variational problem includes an entropy term that corresponds to the large number of embeddings of certain highly structured graphs in $K_n$. For a certain class of irregular graphs $H$ that we call stable, we show that this description of the upper-tail probability is valid in a range of densities that is optimal up to a poly($\log\log n$) factor. For a further subclass of stable graphs, which includes all irregular complete bipartite graphs, we show that this range of densities is optimal up to a multiplicative constant.

07.
arXiv (CS.AI) 2026-06-16

Semantics-Enhanced Retrieval-Augmented Time Series Forecasting

arXiv:2606.14941v1 Announce Type: new Abstract: Time series forecasting models often benefit from historical patterns. Inspired by Retrieval-Augmented Generation (RAG), recent research explored retrieving relevant historical time series segments to enhance forecasting. However, relying solely on time series similarity is often insufficient for retrieval under non-stationarity. To address this, we propose a multimodal approach: a Semantics-Enhanced Retrieval-Augmented Time Series Forecasting framework, SERAF. Unlike mainstream approaches that depend only on time series similarity, SERAF conducts dual retrieval over the time series and their self-generated textual descriptions. It retrieves two complementary sets of historical patterns and corresponding futures, which are selectively and jointly used to guide future predictions. Experiments across seven real-world datasets demonstrate the effectiveness of SERAF in bridging numerical and semantic views of time series compared with state-of-the-art baselines.

08.
arXiv (quant-ph) 2026-06-16

Cosmological Pseudo-Entropy

arXiv:2606.15227v1 Announce Type: cross Abstract: We study pseudo entropy $\mathcal{S}$, a recent generalization of entanglement entropy, for scalar cosmological perturbations in de Sitter space with sound speed $0.024 \leq c_s \leq 1$, and in expanding and contracting FLRW backgrounds with varying equation-of-state parameter $w$. In de Sitter space, $\mathrm{Re}(\mathcal{S})$ grows after horizon exit while $c_s$ controls its onset and saturates at late times. A similar saturation occurs in expanding-accelerating and contracting-decelerating backgrounds. In contrast, expanding-decelerating and contracting-accelerating backgrounds show large early-time $\mathrm{Re}(\mathcal{S})$ followed by oscillations after horizon re-entry. This happens because while the squeezing freezes, the squeezing angle doesn't. Unlike entanglement entropy, pseudo entropy possesses an imaginary part, $\mathrm{Im}(\mathcal{S})$, as well, which can encode the relative phase. $\mathrm{Im}(\mathcal{S})$ decays to zero in de Sitter and expanding-accelerating cases, but forms dense sub-Hubble oscillation bands in expanding-decelerating and contracting-accelerating backgrounds. Compared with entanglement entropy, Krylov complexity, and Nielsen circuit complexity, pseudo entropy captures otherwise hidden phase information; in the unsaturated regime, its slope is $\sqrt{2}$ times that of Nielsen complexity. Unlike circuit complexity, whose saturation bound is $w$-independent, pseudo entropy is sensitive to $w$ during the transition regime, making it a finer information theoretic diagnostic of cosmological dynamics.

09.
arXiv (CS.AI) 2026-06-12

ReSET: Accurate Latency-Critical NVFP4 Reasoning via Step-Aware Temperature Scaling

arXiv:2606.13233v1 Announce Type: cross Abstract: Large reasoning models (LRMs) improve complex problem-solving by generating long intermediate reasoning traces, but this substantially increases inference costs. NVFP4 inference offers a promising approach to reduce both computational and memory costs through hardware-supported low-precision execution. However, directly applying NVFP4 to LRMs introduces two practical limitations: reasoning accuracy degrades under quantization, and existing NVFP4 kernels do not fully realize latency benefits in small-batch autoregressive decoding. In this work, we analyze the effect of NVFP4 quantization on token-level uncertainty during reasoning. We show that quantization increases incorrect sampling at low-entropy symbolic tokens, while causing over-concentration on a small set of tokens in high-uncertainty reasoning steps. Based on this observation, we propose ReSET, a reasoning-step entropy-based temperature-scaling method that estimates step-level uncertainty online and adapts the decoding temperature using both token-level and step-level entropy signals. To address the latency gap, we further design a CUDA-core small-$M$ NVFP4 kernel for latency-critical autoregressive decoding. Across reasoning benchmarks and model scales, ReSET improves NVFP4 reasoning accuracy by up to $\sim\!$2 points over the NVFP4 baseline. Our CUDA-core small-$M$ kernel further improves latency-critical decoding, delivering up to $2.5\!\times$ kernel-level speedup over NVFP4 vLLM and approximately $2\!\times$ end-to-end decoding speedup over BF16. Code is available at https://github.com/aiha-lab/ReSET.

10.
arXiv (CS.CL) 2026-06-19

Multi-Agent Transactive Memory

The decentralized deployment of LLM agents with diverse capabilities across diverse tasks motivates infrastructure for knowledge sharing across heterogeneous agent populations. Just as search engines index human-generated artifacts to support human problem solving, retrieval systems can organize agent-generated artifacts for reuse across agent populations. We extend retrieval-augmented generation - which demonstrates the value of human-authored artifacts to individual agents - to retrieval of agent-generated artifacts supporting a population of agents. In particular, agent trajectories encode reusable procedural knowledge, yet these artifacts are typically discarded after a single use or retained only by the producing agent, forcing newly instantiated agents to repeatedly rediscover existing solutions. We propose Multi-Agent Transactive Memory (MATM), a framework for population-level storage and retrieval of agent-generated trajectories, where producer agents contribute trajectories to a shared repository and consumer agents retrieve them to improve task execution. We focus on interactive environments (ALFWorld and WebArena), where trajectories are long and encode especially rich procedural structure. Our experiments demonstrate that retrieving trajectories from MATM improves downstream task performance and reduces interaction steps without coordination or joint training. These results position MATM as a design pattern for population-level experience sharing in open agent ecosystems.

11.
arXiv (CS.CV) 2026-06-12

Navigating Gigapixel Pathology Images with Large Multimodal Models

Recent advances in large multimodal models have allowed for the development of interactive chat models that can converse and reason about pathology whole-slide images (WSIs). However, existing slide-level chat systems are often highly specialized, typically compressing WSIs into fixed slide-level embeddings or relying on multi-component pipelines, which can lose multi-scale detail and limit generalizability beyond the target task. We present GIANT (Gigapixel Image Agent for Navigating Tissue), a simple, training-free approach that lets general-purpose multimodal models navigate WSIs on their own, iteratively selecting multi-magnification crops and aggregating evidence over time. To evaluate generalizability in WSI question answering and to promote reproducibility, we introduce MultiPathQA, a benchmark suite spanning five clinical challenges and 934 questions over 868 unique WSIs. This includes a new set of 128 pathologist-authored multiple-choice questions designed to mirror real diagnostic search and multi-scale reasoning. Using GPT-5, GIANT outperforms models specialized for pathology question answering, achieving state-of-the-art performance on four out of five benchmarks.

12.
medRxiv (Medicine) 2026-06-11

Allostatic Load in Endometrial Cancer Disparities

Background: Endometrial cancer incidence and mortality are increasing, particularly among Black women and for aggressive subtypes. Allostatic load (AL), a composite measure of physiologic dysregulation across metabolic, cardiovascular, and immune systems, varies by racial category and tumor subtype in other cancers. Endometrial cancer is strongly associated with obesity, and it is unknown whether AL scores maintain sufficient heterogeneity to evaluate differences across subgroups or with clinical outcomes. Objective: To describe the performance of AL scoring in endometrial cancer patients and examine associations with tumor characteristics (grade/histology) and survival outcomes. Methods: We evaluated AL among 398 participants newly diagnosed with endometrial cancer. AL score was calculated by assigning 1 point for each ''high-risk'' value (by clinical reference range or distribution-based) for 15 biologic variables for vital signs, anthropometrics, blood-based biomarkers, and medical comorbidities. Results: Distribution-based thresholds for variables were used to preserve heterogeneity in this obesity-dominant context. Overall, 68.7% of Black women had high AL compared to White (56.7%), Hispanic (56.7%), and other race (32.3%) women. Decision tree analyses revealed grade-dependent associations between AL and survival. For women with low-grade tumors, higher AL was associated with poorer overall survival. For high-grade tumors, intermediate AL ([≥]4,

13.
arXiv (CS.AI) 2026-06-19

Sensorimotor World Models: Perception for Action via Inverse Dynamics

arXiv:2606.20104v1 Announce Type: cross Abstract: Perception for action suggests that representations of the world should be shaped not by visual fidelity alone, but by their relevance for actions. At the same time, latent JEPA-style world models advocate learning compact predictive states from high-dimensional observations to facilitate the prediction of future states, but end-to-end training of these models is nontrivial because representations may collapse if our only goal is to construct a latent state that is easy to predict. We introduce a sensorimotor world model (SMWM): a latent world model trained end-to-end with inverse dynamics regularization. This single regularizer addresses both issues: it prevents representation collapse and induces action-aligned representations. By forcing latent states to preserve information about the action underlying a transition, it biases the model toward the controllable degrees of freedom of the environment while discarding uncontrollable distractors. This yields stable latent world models trained from offline, reward-free trajectories, without frozen encoders, exponential moving averages, or complex latent regularizers. Empirically, SMWM learns compact, interpretable latent spaces and enables competitive planning performance across simple 2D and 3D control tasks.

14.
arXiv (CS.LG) 2026-06-17

AIMER: Calibration-Free Task-Agnostic MoE Expert Pruning

arXiv:2603.18492v3 Announce Type: replace Abstract: Mixture-of-Experts (MoE) language models increase parameter capacity without proportional per-token computation, yet deployment still requires storing the full expert pool, making expert pruning important for reducing memory and serving overhead. Existing task-agnostic expert-pruning methods are typically calibration-dependent: they estimate expert importance from routing or activation statistics on a calibration set, making pruning decisions sensitive to calibration-data variation while introducing substantial preprocessing cost. We propose AIMER (Absolute mean over root mean square IMportance for Expert Ranking), a simple calibration-free criterion that identifies more distinct experts by capturing the concentration pattern of expert weights, making it well suited for task-agnostic expert pruning. Across 7B to 47B MoE language models with distinct architectures and 16 diverse benchmarks, AIMER consistently delivers stronger capability balance across diverse tasks than existing calibration-free methods. Surprisingly, AIMER also achieves better balance than strong calibration-based expert-pruning baselines calibrated on the widely used task-agnostic C4 corpus, while requiring only 0.22–2.06 seconds to score all experts.

15.
medRxiv (Medicine) 2026-06-12

The Acceptability of Three Co-Created Peer Support Interventions for People Living with Leprosy Reactions in Indonesia: A Mixed-Methods Pilot Study

Background: Leprosy reactions (LR) are immune-mediated complications associated with disability, emotional distress, and social isolation. We identified a gap in affected-individual-informed interventions that aim to improve the management of LR in healthcare settings. To address this gap, we assessed the acceptability of three peer-support interventions co-created with people affected by LR in Indonesia. Methods: Using an interactive learning and action approach, we co-created peer counselling, telesupport groups, and participatory video interventions which were piloted in an urban hospital and 13 rural community clinics. A mixed-methods design was applied with interviews, focus group discussions, and pre-post assessments involving four participant groups. Data were analyzed thematically using an acceptability framework. Results: One hundred participants were enrolled, and 92 completed the pilot intervention between November 2022 and July 2023. Qualitative findings showed that all interventions were acceptable. Peer counselling provided emotional reassurance through shared experiences and was perceived as trustworthy and supportive. Perceived burdens differed by setting, with time constraints in urban facilities and geographical barriers in rural clinics. Knowledge improved significantly among participants of peer counselling and telesupport groups in rural settings. Telesupport groups facilitated connection, information exchange, and continuity of care. Digital access and literacy limited participation for some, particularly in rural areas. The participatory video was perceived as reassuring and informative. Improvements in knowledge, attitude, practices, and mental well-being domain scores were observed among urban participants, but responses in rural settings showed less change. Participants and co-implementers reported increased self-efficacy, participants confidence to perform required behaviors within peer support interventions, with effects shaped by intervention and setting. Conclusions: The three co-created peer-support interventions were acceptable for individuals with LR in diverse healthcare settings. These outcomes highlight the importance and effectiveness of selective, and context-sensitive implementation of one or more peer-support modalities.

16.
arXiv (CS.CV) 2026-06-15

ClinHallu: A Benchmark for Diagnosing Stage-Wise Hallucinations in Medical MLLM Reasoning

Building trustworthy medical multimodal large language models (MLLMs) is critical for reliable clinical decision support. Existing medical hallucination benchmarks mainly focus on data collection, but often ignore where hallucinations originate within the reasoning process. We find that hallucination sources vary across samples: errors may arise from visual misrecognition, incorrect medical knowledge recall, or flawed reasoning integration. To enable source-level hallucination diagnosis, we introduce ClinHallu, a benchmark for stage-wise hallucination diagnosis in medical MLLM reasoning. ClinHallu contains 7,031 validated instances, where each instance is augmented with a structured reasoning trace decomposed into Visual Recognition, Knowledge Recall, and Reasoning Integration. We also use stage-replacement interventions to measure how correcting specific stages affects the final answer. Beyond evaluation, we show that trace-supervised fine-tuning reduces stage-wise hallucinations. ClinHallu provides a fine-grained hallucination testbed for diagnosing and mitigating reasoning failures in medical MLLMs. The benchmark is publicly available at https://github.com/alibaba-damo-academy/ClinHallu.

17.
arXiv (CS.AI) 2026-06-16

AC-ODM: Actor–Critic Online Data Mixing for Sample-Efficient LLM Pretraining

arXiv:2505.23878v2 Announce Type: replace-cross Abstract: Optimizing pretraining data composition is pivotal for LLM generalization. While dynamic mixing outperforms static strategies by capturing evolving training dynamics, current methods fail to reconcile computational efficiency with sample efficiency and structural flexibility for diverse pipelines.We introduce Actor–Critic Online Data Mixing (AC-ODM), which approaches data mixing from a reinforcement learning perspective with a parameterized policy that we theoretically prove to act as a dynamic linear surrogate maximizing the constructive interference of gradients. To enhance practical flexibility, AC-ODM supports two operational modes: (i) a proxy mode for fixed, pre-prepared corpora, where a policy learned on a small model is transferred to a larger target; and (ii) a non-proxy mode for direct end-to-end training from scratch without priors. Empirically, AC-ODM significantly outperforms prior methods in convergence speed and downstream accuracy across various architectures. On Pythia-1B, it reaches optimal validation perplexity using up to 66% fewer training steps than competitive baselines, delivering a 27.5% relative improvement in MMLU accuracy and a 2.23 x higher pass@1 on HumanEval, all while incurring a virtually negligible (0.4%) per-step wall-clock increase and only 2% additional memory overhead. Code is available at https://github.com/DANG-ai/AC-ODM.

18.
arXiv (CS.CL) 2026-06-15

GitOfThoughts: Version-Controlled Reasoning and Agent Memory You Can Replay, Diff, and Merge

Large language model (LLM) reasoning is ephemeral: chains of thought vanish with the context window, pruned search branches leave no record, and memory buffers cannot be diffed, merged, or audited. Every other complex software process (code, infrastructure, data, experiments) is version-controlled; reasoning is not. We introduce GitOfThoughts, which stores an agent's reasoning tree as a git repository: every scored thought is a commit, scores are notes, outcomes are tags, and retrieval is "git log" over the agent's own history. This makes reasoning replayable, auditable, and mergeable across agents at near-zero engineering cost. We then ask the harder question: does memory, in any substrate, actually improve accuracy? Across five substrates (none, markdown, vector, graph, git), two benchmarks, two model scales, and pre-registered replications, the answer for novel problems is no. No memory format reliably helps, and a promising early result collapsed under its own pre-registered replication. Memory pays only above what we call the copyability threshold: when the retrieved case is a near-duplicate of the current problem (similarity >~ 0.8), accuracy jumps sharply; below it, nothing. The gain is answer retrieval, not method transfer: a 4.5x larger model doubles the near-duplicate payoff yet still cannot extract a transferable method from a worked example. The only general lever we find is test-time sampling. The case for git-as-substrate is therefore auditability, provenance, and mergeability at accuracy parity. We document a retracted result and a refuted hypothesis to model the evaluation standard we hold ourselves to.

19.
arXiv (CS.AI) 2026-06-18

Code-Augur: Agentic Vulnerability Detection via Specification Inference

arXiv:2606.18619v1 Announce Type: cross Abstract: The advent of agentic vulnerability detection is already becoming a watershed moment for software security. Audits conducted entirely by autonomous LLM agents are uncovering critical vulnerabilities in fundamental software underpinning digital society. Many of these vulnerabilities remained masked for years, surfacing only now with AI agents. Yet the reasoning behind these discoveries remains alarmingly opaque and unvalidated. What assumptions did the agent make about a function's inputs when it deemed that function to be secure? Failures in reasoning and incorrect assumptions can lead to missed vulnerabilities and reduce trust in agentic analysis. We propose a security-specification-first paradigm that (1) exposes the agent's tacit assumptions explicitly as security specifications and (2) continuously refines those specifications via runtime falsification. We realize our approach in Code-Augur, a novel harness for agentic vulnerability detection. Given a codebase, Code-Augur analyzes each component of the system for vulnerable code. When it deems a component to be secure, it commits the local invariants behind that judgment as in-source assertions. In parallel, Code-Augur leverages a guided fuzzer to attempt to falsify those assumptions. When the fuzzer triggers an assertion, this either reveals a genuine vulnerability or a flawed specification to refine. In both cases, this process grounds the agent's understanding, aligning its view of code intent with how the code actually behaves. On real-world subjects, Code-Augur effectively leverages security specifications to detect more vulnerabilities than other state-of-the-art agents. Additionally, Code-Augur found 22 new vulnerabilities in key open-source projects. Compared to curated specialized models like Claude Mythos, Code-Augur offers effective agentic vulnerability detection built on widely available LLMs like Sonnet and DeepSeek.

20.
arXiv (CS.AI) 2026-06-16

Protein Design with Agent Rosetta: A Case Study for Specialized Scientific Agents

arXiv:2603.15952v2 Announce Type: replace Abstract: Large language models (LLMs) are capable of emulating reasoning and using tools, creating opportunities for autonomous agents that execute complex scientific tasks. Protein design provides a natural testbed: although machine learning (ML) methods achieve strong results, these are largely restricted to canonical amino acids and narrow objectives, leaving unfilled need for a generalist tool for broad design pipelines. We introduce Agent Rosetta, an LLM agent paired with a structured environment for operating Rosetta, the leading physics-based heteropolymer design software, capable of modeling non-canonical building blocks and geometries. Agent Rosetta iteratively refines designs to achieve user-defined objectives, combining LLM reasoning with Rosetta's generality. We evaluate Agent Rosetta on design with canonical amino acids, matching specialized models and expert baselines, and with non-canonical residues – where ML approaches fail – achieving comparable performance. Critically, prompt engineering alone often fails to generate Rosetta actions, demonstrating that environment design is essential for integrating LLM agents with specialized software. Our results show that properly designed environments enable LLM agents to make scientific software accessible while matching specialized tools and human experts.

21.
arXiv (CS.LG) 2026-06-11

Bergson: An Open Source Library for Data Attribution

arXiv:2606.11660v1 Announce Type: new Abstract: Data attribution is a promising field in interpretability that aims to explain model behavior through the influence of its training data, with applications including debugging undesirable model behavior and training dataset curation. However, significant engineering effort is required to perform it at scale, and many cutting edge techniques lack open-source tooling and support. Bergson is an open source library that aims to enable faster progress in the field by providing a host of techniques that scale to very large language models and pre-training datasets. The library natively supports on-disk gradient stores and multi-node distributed training, and provides quality of life tools for researchers. Finally, we introduce the first open-source implementations of three leading data attribution methods: MAGIC, SOURCE, and TrackStar. The library is available at https://github.com/EleutherAI/bergson .

22.
arXiv (CS.CL) 2026-06-19

Closing the Calibration Gap in Semantic Caching

Semantic caching cuts LLM inference costs by serving a cached response to semantically similar queries. Standard practice evaluates these systems using PR-AUC, a metric that only measures how well scores rank and ignores whether they are usable at a fixed threshold. We show this mismatch leads to systematically poor deployment choices, as models with the highest PR-AUC are often the worst in operation. We introduce Precision-Cache Hit Ratio (P-CHR) AUC, a cache-aware metric that measures precision across cache utilization levels, and Calibration Retention Rate (CRR), which captures how much offline ranking quality survives at deployment. We decompose the operational gap between offline and deployed quality into a recoverable calibration component and an irreducible structural component fixed by the dataset's positive rate. Our experiments show that the calibration gap is governed by the training objective rather than data scale, and post-hoc calibration only partially closes it. Ultimately, model selection for semantic caching is a calibration problem, not a ranking one, and measuring it is the first step to closing the gap.

23.
arXiv (CS.AI) 2026-06-16

Closing the Auto-Research Loop: An AI Co-Scientist for Production Search Ranking

arXiv:2603.22376v2 Announce Type: replace-cross Abstract: We present an AI Co-Scientist framework that closes the research loop for the production search-ranking system of a large online travel platform – pairing LLM agents with direct cloud-compute access so that idea generation, code implementation, GPU experimentation, and result analysis iterate end-to-end with a human scientist in the loop. The framework uses a hybrid agent architecture: single-LLM agents handle routine work, while multi-LLM consensus (GPT-5.2, Gemini Pro 3, Claude Opus 4.5) is invoked for higher-stakes decisions. On the production ranking task, a human-designed transformer baseline (V2) yielded $+0.118\%$ over a pre-transformer baseline (V1); the AI Co-Scientist's automated loop on top of V2 contributed an additional $+0.083\%$, for a combined $+0.201\%$ offline gain delivered in roughly one extra week of wall-clock time (single-run numbers; statistical limits discussed in the paper). The most useful AI proposals – unified long-sequence layouts, slot-type embeddings, and multi-phase learning-rate schedules – are standard practice in NLP and Vision but were absent from our production stack, suggesting that LLM agents can serve as cross-disciplinary connectors for ranking teams. We also report deployment context, negative results, and lessons learned.

24.
arXiv (CS.AI) 2026-06-11

Intelligent Automation for Embodied Benchmark Construction: Pipelines, Embodiments, Simulators, and Trends

arXiv:2606.12207v1 Announce Type: cross Abstract: Embodied intelligence now spans navigation, household assistance, manipulation, autonomous driving, aerial agents, and multimodal large-model control. This expansion has made benchmark construction a central bottleneck for reliable evaluation. Unlike static datasets, embodied benchmarks combine task specifications, environments, robot data, demonstrations, annotations, metrics, evaluation scripts, and release policies into a single evaluation system. This survey reviews the literature through a five-stage construction pipeline: requirement and task construction, data acquisition, data cleaning and annotation, benchmark suite generation and metric definition, and evaluation execution with diagnostic feedback. For each stage, the survey analyzes the transition from manual curation to traditional automation, foundation-model assistance, and agentic closed-loop workflows. It also compares qualitative construction costs across human labor, data and asset acquisition, compute and simulation, validation and debugging, governance and maintenance, and rework risk. The main conclusion is that automation does not simply reduce benchmark cost. Instead, it often shifts cost toward validation, auditability, version control, and long-term governance. Progress in embodied evaluation will therefore depend not only on larger benchmark suites, but also on construction pipelines that are diagnosable, auditable, and responsibly refreshable.

25.
bioRxiv (Bioinfo) 2026-06-18

Benchmarking gene expression reconstruction from single-cell latent representations

Single-cell transcriptomics is typically modeled in low-dimensional latent representations that improve the signal-to-noise ratio of the data. Such representations underpin data integration, cell state discovery, and perturbation prediction, with applications ranging from large-scale organ atlases to latent trajectory modeling. Recent virtual cell approaches further leverage these representations to predict cellular responses as distributional shifts in latent space. Each of these applications ultimately requires faithful gene expression reconstruction from latent spaces for biological interpretation, enabling gene-level analysis of predicted perturbed or batch-corrected cells. Yet representation choice is typically treated as an implementation detail rather than a primary modeling decision, with no systematic evaluation of how well latent representations support gene expression reconstruction. Here, we introduce ReconEval, a benchmark for evaluating gene expression reconstruction from single-cell latent spaces. We benchmark two classes of latent representations: end-to-end trained models such as PCA, autoencoders, and variational autoencoders, and pretrained single-cell foundation model embeddings coupled to newly trained decoders. Reconstruction is evaluated both directly and after latent-space perturbation prediction. Across perturbational and observational datasets totaling over 100 million cells, our metric suite quantifies statistical fidelity; biological signal preservation, including differential expression, coexpression, cell-cycle structure, cytokine response and pathway activity; and perturbation-specific effects. We find that autoencoders achieve the strongest stand-alone reconstruction at low dimensionality, while variational regularization does not improve generalization in reconstruction. Frozen foundation model embeddings retain recoverable gene-level information, with reconstruction quality depending strongly on decoder architecture and pretraining objective. In latent perturbation modeling, high-dimensional PCA matches foundation model embeddings, while low-dimensional AE embeddings are optimal for flow-based generative models. Overall, reconstruction depends critically on the interplay between representation and downstream model, and simpler representations can outperform complex alternatives given appropriate capacity. Our benchmark establishes reconstruction as a critical evaluation axis for single-cell foundation models. We envision it improving the biological interpretability of latent-space modeling, a prerequisite for future virtual cell models to be validated by domain experts and grounded in biology.