每天知道
你的领域
出了什么

Recent text-to-image generation models have demonstrated remarkable capabilities in synthesizing highly realistic images from text inputs alone. Although existing benchmarks can evaluate the generation capabilities of various models to some extent, they struggle to comprehensively and accurately measure performance across multiple dimensions, often failing to reveal the inherent deficiencies of models in specific categories. To address these limitations, we propose WeGenBench, a novel benchmark designed for the comprehensive, multi-perspective evaluation of text-to-image generation capabilities. Our benchmark comprises a total of 4,000 test prompts across two primary categories, meticulously balanced between Chinese and English to evaluate bilingual and cross-cultural generation capabilities. Beyond macroscopic scene classification, we annotate each prompt with multi-dimensional tags tailored to the distinct content and challenges of each language, thereby refining the generation tasks into more specific sub-categories. Through a cross-dimensional evaluation mechanism leveraging both scene classifications and multi-dimensional tags, WeGenBench can precisely pinpoint model shortcomings in specific generation categories. Furthermore, to measure generation quality more accurately, we design and validate several novel evaluation metrics by integrating Vision-Language Models (VLMs), which assess model performance on domain-specific tasks from three core aspects. Crucially, our approach yields both the assessment outcomes and the detailed reasoning trajectories, facilitating a rigorous verification of the accuracy and soundness of the evaluation results. Finally, we conduct systematic benchmarking on current state-of-the-art methods and provide an in-depth analysis of the limitations present in existing models.

This paper revisits the classical concept on N-version programming in the setting of contemporary AI coding agents. Revisiting the seminal Knight-Leveson experiment, we study whether diversity across agent systems, models, and implementation languages creates diverse failure modes. Using the Knight-Leveson's, Launch Interceptor Program Specification, we evaluate 48 agent-generated implementations on a shared oracle and a campaign of 1,000,000 randomized test inputs. The results show substantial common-mode failure, along the findings of Knight-Leveson. Further analysis that many of those co-occuring failures can be traced to where is specification is particularly hard or ambiguous. We also demonstrate that diversity from coding agents provides practical benefit: across majority voting three-version units, the mean failure count drops from 387.44 for single versions to 130.99 for triples, and 11,844 N-version units exhibit zero observed failures. Our original results is the strongest evidence to date that N-Version Programming with coding agents is a useful engineering strategy.

The rapid evolution of Quantum Development Kits (QDKs) introduces a specific form of technical debt that compromises code maintainability and hinders software reuse. In the specialized domain of Quantum Software Engineering (QSE), this challenge is intensified by the scarcity of high-quality training data and the high volatility of emerging frameworks, which often lead general-purpose Large Language Models (LLMs) to produce unreliable or hallucinated results. This paper proposes a hybrid approach integrating LLMs with Retrieval-Augmented Generation (RAG) to automate the migration of Qiskit code across versions. The proposed methodology enhances the precision and reliability of migration suggestions by leveraging an automatically generated taxonomy of migration scenarios as the structured, version-specific knowledge source to guide the models. The approach is implemented through an automated, extensible workflow evaluating LLMs (Google Gemini Flash-2.5 and OpenAI Gpt-oss-20b) under different retrieval schemes (unconstrained and restrictive). Results demonstrate that the taxonomy-based RAG architecture, particularly under the restrictive scheme, significantly reduces hallucinations and improves descriptive quality, with Google Gemini Flash-2.5 showing superior performance in detecting complex refactoring scenarios. These findings confirm the potential of this data-centric methodology to foster technological independence and provide robust, intelligent assistants that mitigate API obsolescence, ensuring the long-term availability of quantum algorithms within a rapidly shifting ecosystem and flattening the learning curve within Quantum Software Engineering (QSE).

Automated skin cancer classification from dermoscopic images remains challenging due to heterogeneous lesion structure, strong intra-class variability, and subtle visual differences between benign and malignant cases. Existing CNN/ViT pipelines typically rely on global or patch-level features and often combine patient metadata via late fusion, which limits spatially grounded multimodal reasoning. We present a novel region-based graph learning framework that explicitly models lesions as graphs of spatially coherent superpixel regions represented as frozen CNN features. To capture fine-grained lesion arrangements, we encode inter-regional geometry as edge attributes and introduce a dedicated metadata context node connected to all regions, providing structured integration of demographic/clinical variables within the same relational space. Node representations are updated using our edge-aware graph transformer followed by attention-driven propagation, and a final graph-level embedding for benign-malignant classification. Experiments on four public benchmarks demonstrate that explicit region-level relational modeling and graph-native multimodal fusion yield consistent gains over the state-of-the-art. Consequently, we establish a new graph-centric perspective in which CNN features are modeled as relational nodes and improved through contextual integration, yielding more expressive and robust classifications.

Malware analysts often inspect compiled binaries through decompiled pseudo-C, when source code is unavailable. Recent work suggests that large language models (LLMs) can assist this process by classifying decompiled code as benign or malicious, but existing pipelines typically rely on a single decompiler view. We argue that this assumption is fragile: decompilers are lossy heuristic tools, and different decompilers can expose different artefacts of the same binary. We curate a benchmark of benign utilities and malicious programs spanning a range of threat behaviors. Each sample is compiled and decompiled with both Ghidra and RetDec, yielding matched pseudo-C views. Across a range of LLMs from major model families, we find that providing both decompiler views improves malicious-class F1, mainly by increasing recall on malicious samples. Agreement analyses further show that Ghidra and RetDec make partially different errors, supporting the view that decompiler outputs provide complementary evidence. Our results suggest that multi-decompiler prompting is a simple, training-free way to improve LLM-based malware triage in practical settings.

We study how to train visually grounded vision-language models (VLMs) for radiology without manual spatial annotations. We introduce RefRad2D, a large-scale bilingual (German/English) dataset of 1.2M CT and MR image-text pairs derived from clinical practice, with task-specific VQA and spatial grounding subsets generated automatically via LLM-based curation and automated segmentation. Trained on this data, our model RadGrounder jointly performs report generation, visual question answering, and spatial grounding via bounding-box detection or segmentation. On external VQA benchmarks (Slake, VQA-RAD), RadGrounder achieves competitive results with specialized medical VLMs. Adding our clinical data to the training mixture improves open-ended VQA over fine-tuning on the downstream datasets alone, showing the transferability of our dataset. Crucially, adding grounding supervision does not degrade language quality, enabling spatially verifiable outputs at no cost to VQA performance.

Whether LLMs scoring well on vulnerability benchmarks genuinely reason about security or merely pattern-match on contaminated data remains unresolved. We present CWE-Trace, a framework for LLM vulnerability detection built from 834 manually curated Linux kernel samples spanning 74 CWEs. The framework enforces a strict temporal split (pre-2025 historical set / post-cutoff leakage-free set), preserves context-aware vulnerable--patched pairs, and introduces two diagnostic metrics: the Directional Failure Index (DFI) and Hierarchical Distance and Direction (HDD). We evaluate eight vanilla LLMs and 15 LoRA fine-tuned variants across non-targeted detection, targeted detection, and CWE classification. Our analysis yields two key results. First, data contamination provides no measurable advantage. Function-level analysis shows that 84% of nominally contaminated samples carry no usable memorization signal: vulnerable functions are absent or cross-mapped across datasets, and ~31% of contaminated samples carry CWE misclassification. Second, backbone directional priors dominate fine-tuning. Models exhibit stable, systematic failure modes (DFI ranging from -85.5 to +94.8 pp) that persist from historical to post-cutoff data and resist correction. Fine-tuning shifts the output threshold without changing the decision policy. This is calibration without comprehension: output distributions adapt to training data while the underlying security reasoning remains absent. The weakest backbone at binary detection (DeepSeek-R1) gains the most in coarse CWE classification, revealing that detection and understanding are decoupled capabilities. The best detection score reaches only 52.1% (+2.1 pp above chance); exact CWE ranking remains below 1.3% Top-1 accuracy, confirming that current LLMs lack reliable security reasoning for systems software, regardless of fine-tuning strategy.

Streaming Retrieval-Augmented Generation (Streaming RAG) hides tool latency by issuing retrieval queries in parallel with the user's still-arriving input, before the utterance is complete. Speculation can only help, though, when the correct query becomes determinable before the user stops speaking or typing — a property of the query, not the system. We name and measure this property, tool-intent stabilization: the point in the input stream at which a speculative query's retrieval converges on the answer-bearing result. On the CRAG benchmark (1371 validation questions) we (i) characterize how stabilization is distributed across queries; (ii) derive a model-agnostic bound H on the share of tool latency hideable behind the remaining input, given tool latency L and input cadence delta; (iii) validate it against a working streaming pipeline; and (iv) ask which query properties predict early versus late stabilization. Stabilization is typically early: at a realistic operating point a 73.9% streamable fraction of the benchmark admits latency hiding, and H acts as a conservative aggregate floor that realized savings meet or exceed — though it does not predict savings query by query. Question type yields a statistically significant but small early/late split. The study needs no model training and runs on commodity CPU hardware; a dense-retriever replication confirms the early-stabilization effect is not a BM25 lexical artifact.

Large language models (LLMs) are increasingly applied to computer-aided design (CAD) to generate design artifacts from textual instructions. In engineering practice, this requires more than creating new geometry, models must also understand existing scenes, edit them correctly, and preserve semantics and relations. However, many CAD benchmarks focus on creating new models rather than editing existing ones, and mostly evaluate geometric correctness. We introduce BIM-Edit, a benchmark for evaluating LLMs on natural-language editing of Building Information Models (BIM) represented in the Industry Foundation Classes (IFC) format. BIM provides a challenging testbed because building models encode geometry together with semantic and relational structure. BIM-Edit contains 324 editing tasks spanning 11 realistic building models and 36 synthetic scenes. Tasks are expressed using three instruction categories - direct, spatial, and topological - covering both explicit and scene-grounded edits. We evaluate outputs along three dimensions: geometric accuracy, semantic validity, and topological consistency. Across evaluated LLMs, the best-performing model achieves only 49.5% average score across the three metrics, and no model fully solves more than 3.4% of tasks. These results demonstrate a substantial gap between current LLM capabilities and the requirements of structured engineering design workflows.

Recent advances in Large Language Models (LLMs) have substantially transformed Automated Essay Scoring (AES), yet the internal mechanisms underlying LLM-based scoring remain poorly understood. In this work, we systematically analyze the hidden representations of eight LLMs across two English essay datasets (ASAP++, CSEE) and one Portuguese dataset (ENEM). Using linear probing, cross-prompt generalization, dimensionality reduction, and neuron-level analyses, we find consistent evidence that essay quality information is encoded in a linearly accessible form within LLM representations. These representations emerge progressively across layers, remain robust across prompting strategies, and partially transfer across essay prompts despite differences in scoring rubrics. In addition, nonlinear probes provide only marginal and inconsistent improvements over linear probes, suggesting that most essay quality information is already linearly decodable. We further identify individual ``essay scoring neurons'' whose activations strongly correlate with essay scores and whose behavior is sensitive to targeted intervention. Moreover, the layer-wise distribution of these neurons systematically shifts with essay length, with longer essays relying more heavily on deeper layers. Overall, our findings provide evidence that LLMs encode structured representations related to essay quality and offer new insights into the interpretability of LLM-based AES systems.

Large Language Models (LLMs) have made significant progress in reasoning, particularly in deductive reasoning, which is crucial for high-stakes decision-making. As models improve, evaluation benchmarks should evolve to keep pace. However, existing benchmarks lack fine-grained control over logical complexity and struggle to balance semantic diversity with logical consistency. To address these issues, we propose QMFOL, an automated framework for generating monadic first-order logic reasoning tasks with quantifiable and controllable complexity. It constructs formal logical structures using conjunction and disjunction patterns, enabling precise control over reasoning depth, width, label types, and distractors. These structures are then translated into natural language via LLMs, with logical consistency ensured through round-trip verification using an external prover. Based on our framework, we build QMFOLBench, a benchmark comprising 2880 instances with 960 configurations across diverse logical and semantic dimensions. Evaluations on six large reasoning models (LRMs) and two LLMs show that performance degrades and computational overhead increases with rising logical complexity. Models perform better on True-labeled tasks than on False or Unknown ones, and exhibit sensitivity to semantic variation. Overall, QMFOL offers a scalable and reliable approach for constructing deductive reasoning benchmarks with controllable complexity, enabling more precise evaluation of reasoning capabilities in modern language models.

Reinforcement learning with verifiable rewards (RLVR) has driven substantial progress in large language model reasoning, but relies on ground-truth supervision that is costly or infeasible, especially in coding tasks. Recent work addresses this by deriving rewards from a model's own signals, such as majority voting or confidence-based scores, achieving notable success on mathematical reasoning benchmarks. However, code generation poses distinct challenges: programs are structurally complex, semantically equivalent solutions may differ syntactically, and verification typically requires execution. Whether these intrinsic reward methods transfer effectively to code remains unexplored. In this work, we present a systematic empirical study of intrinsic reward methods for code generation. We conduct extensive experiments on LiveCodeBench, systematically evaluating representative certainty-based Reinforcement Learning from Internal Feedback (RLIF) approaches under different training scenarios and hyperparameter settings. Our experiments reveal that certainty-based methods yield early gains but inevitably collapse: models progressively shorten outputs and lose reasoning capability, with collapse speed sensitive to sample size and temperature. When used to initialize RLVR training, RLIF pre-training offers no significant improvement over training from scratch. We also provide actionable recommendations for using intrinsic rewards for training code reasoning models. Our study shows both the promise and limitations of intrinsic reward methods for code, informing future work on code models and agents.

As academic submissions grow, the traditional peer review process struggles to keep up, raising concerns about quality and fairness. A trend of using large language models (LLMs) for assistance has emerged. In this work, we take a critical step toward improving the quality of LLM-generated reviews. We propose the PeerCheck framework, which investigates LLM-human review differences (RQ1) and explores methods to improve LLM-generated review quality (RQ2). We first analyzed the human-written reviews with reviews generated by various LLMs and found that LLMs and humans focus on different terms, e.g., LLMs prioritize theory while humans emphasize methodology and experiments. We further adopt prompt engineering, such as Chain-of-Thought (CoT), and utilize retrieval-augmented generation (RAG) to enhance the LLM-generated reviews towards human-level quality. We find CoT significantly improves the quality of LLM reviews, while we discover an unexpected "RAG paradox," i.e., experiments with RAG produce different results for various LLMs and, in some cases, even reduce review quality. Our comprehensive analysis of LLM-generated academic reviews illustrates both possibilities and limitations, contributing to a more effective, human-aligned review system. Our dataset is available on https://github.com/TrustAIRLab/PeerCheck.

Continual adaptation is essential for multimodal large language models (MLLMs) deployed across evolving domains, but the state-of-the-art MR-LoRA method highly relies on the assumption that a MLLM-based router is necessary to process complex multimodal inputs. This paper revisits this claim on the MLLM-CL benchmark and argues for two claims. First, routing does not require an MLLM: a simple training-free, replay-free ptotypical routing method (\textsc{RePRo}), uses frozen pretrained features and task prototypes to match the MLLM-based router of MR-LoRA at far lower computational cost. Second, shared experts do not improve continual learning for MLLMs, despite their theoretical appeal. We show that these findings arise from two structural limitations of MLLM-CL: (1) its tasks are highly separable in representation space, and (2) its fixed task order makes conclusions sensitive to a single curriculum rather than robust across diverse continual-learning trajectories. As a result, the benchmark primarily rewards learning in isolation rather than genuine continual transfer. This motivates a new design for future benchmarks of continual MLLM learning, with overlapping task manifolds, multiple task orders, fine-grained domain shifts, and evaluation protocols that reward forward transfer as well as retention.

Head and neck cancers (HNC) represent a significant global health burden, with accurate tumor delineation being essential for effective radiotherapy planning. The complexity of the oropharyngeal anatomy, combined with the heterogeneous appearance of tumors on imaging, makes manual segmentation time-intensive and subject to inter-observer variability. Beyond segmentation, predicting long-term clinical outcomes, such as recurrence-free survival (RFS), and determining human papillomavirus (HPV) status from noninvasive imaging, remain challenging yet clinically valuable goals. The HECKTOR 2025 challenge addresses these needs by establishing a comprehensive benchmark for automated HNC analysis using multimodal PET/CT imaging and electronic health records. Building on previous editions (2020-2022), this challenge features an expanded multi-institutional dataset comprising over 1,100 patients from 10 centers worldwide. Participants were tasked with three complementary objectives: (1) segmenting primary gross tumor volumes (GTVp) and metastatic lymph nodes (GTVn), (2) predicting recurrence-free survival, and (3) classifying HPV status. The challenge attracted 35 registered teams, with 15 final submissions evaluated on a held-out test set. Top-performing algorithms achieved a mean Dice similarity coefficient of 0.75 for segmentation, a concordance index of 0.66 for survival prediction, and a balanced accuracy of 0.56 for HPV classification. This paper presents a comprehensive analysis of the submitted methodologies, evaluates their performance across different lesion characteristics, and discusses their implications for clinical translation in automated oncology workflows and decision support systems.

Imperfectly supervised video polyp segmentation (VPS) aims to learn dense, temporally consistent masks from inexpensive supervision, including weak annotations (points, scribbles) and semi-supervision with few densely labeled frames. This setting is clinically valuable but challenging due to weak contrast, ambiguous boundaries, motion blur, and specular highlights, compounded by sparse pixel-level guidance. While SAM2 can generate dense masks from sparse inputs, direct pseudo-labeling often yields geometry-degraded masks with boundary leakage, underutilizes temporal consistency, and ignores reliability. To address these issues, we propose ARTEMIS, a unified framework for imperfectly supervised VPS driven by agent-guided reliability-aware temporal mask evolution. ARTEMIS initializes coarse masks from available supervision: SAM2 converts points/scribbles, while dense labels serve as reliable anchors. A debate-and-judge vision-language agent selects reliable temporal anchors under weak supervision, which are propagated bidirectionally with SAM2 to refine unreliable or unlabeled frames. Finally, ARTEMIS trains the segmenter using temporal reliability-aware robust learning, incorporating reliability-guided reference selection, a Reference Prototype Transport Module, and reliability-aware robust loss. These components assess mask reliability, evolve anchors over time, transport target identity across frames, and down-weight noisy supervision instead of discarding difficult samples. Experiments on SUN-SEG and CVC-ClinicDB-612 under scribble, point, and limited-label settings demonstrate that ARTEMIS achieves state-of-the-art performance. Code will be released at https://github.com/wangtong627/ARTEMIS.

Achieving dexterous robotic manipulation in the real world heavily relies on human supervision and algorithm engineering, which becomes a central bottleneck in the pursuit of general physical intelligence. Although emerging coding agents can generate code to automate algorithm search, their successes remain largely confined in digital environments. We conjecture that the missing abstraction to automate robotics research is a repeatable feedback loop for real-world policy improvement: reset the scene, execute a policy, verify the outcome, and refine the next iteration. To bridge this gap, we introduce ENPIRE, a harness framework for coding agents that instantiates this physical feedback routine with four core modules: an Environment module (EN) for automatic reset and verification, a Policy Improvement module (PI) that launches policy refinement, a Rollout module (R) to evaluate policies with one or multiple physical robots operating in parallel, and an Evolution module (E) in which coding agents analyze logs, consult literature, improve training infrastructure and algorithm code to address failure modes. This closed-loop system transforms real-world manipulation learning into a controllable optimization procedure, minimizing human effort while allowing fair ablations across training recipe and agent variants. Powered by ENPIRE, frontier coding agents can autonomously train a policy to achieve a 99% success rate on challenging, dexterous manipulation tasks, such as organizing a pin box, fastening a zip tie, and tool use, a process that further accelerates when we dispatch an agent team on a robot fleet. Our results suggest a practical and scalable path toward deploying coding agents to autonomously advancing robotics in the physical world.

In batch-style trace distillation, the same memory operation may receive contradictory feedback across different batches. Existing methods lack a cross-batch, operation-level evidence accumulation mechanism, making it impossible to distinguish stably effective operations from accidental hits. This paper formalizes the requirement as two structural conditions, alignability and comparability, and proposes Marginal Advantage Accumulation (MAA). MAA constructs differential signals to make them comparable across batches, accumulates signed evidence per operation via EMA, and ensures cross-batch traceability through semantic identity merging. As a post-processing architecture, MAA achieves the best results in 14 out of 16 settings across 4 benchmarks and 4 target models, consistently outperforming existing batch-level distillation baselines and matching or surpassing online alternatives in most settings, while reducing optimization-phase token consumption by approximately 75%.

Large Language Models (LLMs) have shown strong capabilities in general-purpose code generation, but their effectiveness in specialized software domains remains underexplored. Solidity smart contracts represent a high-stakes domain where generated code must satisfy strict language-level, security, and software-engineering constraints. Existing benchmarks and metrics remain insufficient for repository-level Solidity generation, where models must synthesize complete contracts from natural language requirements. To address this gap, we introduce SolidityBench, a benchmark of 5,470 repository-level Solidity smart contracts paired with natural language descriptions. We also propose SolidityScore, a Solidity-aware semantic metric that emphasizes domain-critical constructs such as security modifiers, contract declarations, and Solidity-specific keywords. Using this benchmark, we evaluate representative code LLMs, including Qwen2.5-Coder, DeepSeek-Coder, and CodeLlama, across zero-shot prompting, Chain-of-Thought reasoning, in-context learning, retrieval-augmented generation, and supervised fine-tuning. The results show that general-purpose models exhibit systematic structural deficiencies in repository-level Solidity generation. Among non-parametric methods, retrieval-augmented generation performs best, while in-context learning degrades beyond two examples due to context saturation. Supervised fine-tuning achieves the largest improvement by internalizing Solidity-specific constraints into model parameters. Overall, our study provides a comprehensive benchmark for repository-level Solidity code generation and shows that high-quality domain data combined with supervised fine-tuning is the most effective strategy for improving the reliability of LLM-generated smart contracts.

Effective Automated Essay Scoring (AES) are expected to support both reliable assessment and actionable instructional feedback. However, existing approaches often treat scoring and feedback as separate components: neural scoring models provide limited interpretability, while Large Language Model (LLM)-based feedback is typically insensitive to learners proficiency levels. To address this fragmentation, this work proposes PsyScore, a psychometrically-aware framework that integrates diagnostic assessment with instructional scaffolding through a shared latent ability representation. PsyScore comprises three key modules: a Trait-Adaptive Neural IRT Scorer that incorporates the Graded Partial Credit Model (GPCM) into a neural architecture, enabling the precise estimation of student ability while maintaining psychometric interpretability, a ZPD-Scaffolded Feedback Generator, which conditions multi-agent feedback strategies on the diagnosed ability parameter to adapt instructional focus across different proficiency levels, and a Multi-Perspective Feedback Evaluation Strategy that assesses feedback quality via pairwise preference judgements and student revision simulations. Experiments on the ASAP++ dataset demonstrate that PsyScore achieves competitive scoring performance while providing more pedagogically aligned feedback.

Real-world computer-use tasks often span multiple applications and devices, requiring agents to coordinate heterogeneous environments under dynamic runtime failures. Existing multi-device agent systems support task decomposition and cross-device assignment, but recovery remains largely coarse-grained: when execution fails, they typically retry the same strategy, reassign the subtask, or revise the global plan, without systematically modeling the device-local strategy space. This limits their ability to distinguish failures that can be repaired within the current device from those that require cross-device replanning. We propose H-RePlan, a hierarchical replanning framework for multi-device agents with unified API--CLI--GUI execution. H-RePlan equips each device with interchangeable execution strategies and separates device-local strategy recovery from orchestrator-level global replanning through a compact cross-layer failure abstraction. To evaluate this capability, we introduce HeraBench, a fault-injected benchmark that constructs cross-device workflows over Linux and Android devices and injects strategy- and device-level failures. Experiments show that H-RePlan substantially outperforms single-strategy and coarse-grained multi-device baselines, achieving higher completion, instruction adherence, and perfect-pass rates while reducing the token cost required for reliable end-to-end success. These results demonstrate that scope-aware hierarchical recovery is essential for robust multi-device agent execution.

LiveCodeBench (LCB) has recently become a widely adopted benchmark for evaluating large language models (LLMs) on code-generation tasks. By curating competitive programming problems, constantly adding fresh problems to the set, and filtering them by release dates, LCB provides contamination-aware evaluation and offers a holistic view of coding capability. However, LCB remains restricted to Python, leaving open the question of whether LLMs can generalize across the diverse programming languages required in real-world software engineering. We introduce Multi-LCB, a benchmark for evaluating LLMs across twelve programming languages, including Python. Multi-LCB transforms Python tasks from the LCB dataset into equivalent tasks in other languages while preserving LCB's contamination controls and evaluation protocol. Because it is fully compatible with the original LCB format, Multi-LCB will automatically track future LCB updates, enabling systematic assessment of cross-language code generation competence and requiring models to sustain performance well beyond Python. We evaluated 24 LLMs for instruction and reasoning on Multi-LCB, uncovering evidence of Python overfitting, language-specific contamination, and substantial disparities in multilingual performance. Our results establish Multi-LCB as a rigorous new benchmark for multi-programming-language code evaluation, directly addressing LCB's primary limitation and exposing critical gaps in current LLM capabilities.

Modern microservice deployments fail in ways that are easy to detect and hard to explain. When a fault propagates along service dependencies, alerts fire in floods, dashboards multiply, and the scarce resource, an engineer who understands how the services relate, is consumed reconstructing context that the monitoring stack discarded. We argue that the missing ingredient in autonomous operations is not a better anomaly detector or a larger language model, but operational memory: a persistent, structured representation of how a system normally behaves, how its parts depend on one another, and how it has failed before. We present O PS C ORTEX, a working multi-agent prototype that organizes this memory into four tiers and uses it to separate two tasks the field usually conflates: deriving a root cause and explaining it. Root cause is computed deterministically from a learned dependency graph and the temporal ordering of threshold crossings; a large language model (LLM) is then asked only to explain, confirm, and recommend, using evidence the system has already assembled. We motivate the design with two documented production cascading failures, review representative literature on observability, anomaly detection, graph-based localization, and LLM-assisted diagnosis, and show how each architectural choice maps directly to a failure mode those incidents exhibit. The prototype is validated on an instrumented e-commerce benchmark with eight injectable failure scenarios.

Large Language Models (LLMs) offer a promising path to automate Clinical Trial Matching (CTM), but still struggle with the deterministic verification required for complex eligibility criteria. Conversely, purely symbolic methods provide formal rigour but break down when faced with incomplete patient records and noisy clinical evidence. To bridge this gap, we investigate a hybrid framework for CTM combining LLMs with logical verification. In particular, we introduce an abductive neurosymbolic CTM framework (αNeSy-CTM), which leverages the linguistic and world knowledge in LLMs to support reasoning over noisy and underspecified clinical text. Extensive evaluation demonstrates that αNeSy-CTM substantially outperforms standalone LLM baselines, achieving up to 30% relative improvement over zero-shot baselines. In addition, our analyses confirm the impact of abductive reasoning on CTM, with αNeSy-CTM exhibiting improved accuracy, specificity, and robustness over a non-abductive neurosymbolic setting. Furthermore, αNeSy-CTM and Chain-of-Thought (CoT) reasoning prove highly complementary, highlighting the potential for a hybrid routing policy. Ultimately, this paper demonstrates the impact of neurosymbolic methods for automating CTM, providing a path toward the next generation of auditable, LLM-driven clinical applications.

We present Phoenix, a multi-agent LLM system that resolves GitHub issues from triage through pull-request creation, combining seven layered safety controls with a baseline-aware test evaluation strategy. Phoenix decomposes the work across six specialized agents. Planner, reproducer, coder, tester, failure analyst and Pull Request (PR) agent, all coordinated by a label-based GitHub webhook state machine. Every change is checked against a baseline test run before a pull request is opened. On a 24-instance slice of SWE-bench Lite. run on the production webhook path, Phoenix oracle-resolves 75% of instances with no pass-to-pass regressions on successful runs; this curated slice is not directly comparable to full-split leaderboard results, and we discuss the limits of the comparison. A complementary pilot on 42 real issues across 14 repositories yields 100% correctness preservation (CP; mean 122s on the hard tier). Manual inspection shows that about half of the resulting pull requests are well-targeted fixes. The other half place code at incorrect paths, a planner localization limitation we are addressing with retrieval. We also report the deployment failure modes (WAF filtering, token expiry, permission boundaries, flaky CI) that motivated each safety mechanism.

MLLM-based mobile GUI agents have made substantial progress on short-horizon tasks, yet remain unreliable on long-horizon tasks that require retaining intermediate facts across many steps and app transitions. We attribute this limitation to ReAct-style prompting, which passively accumulates per-step records, leading to prompt explosion and dilution of critical cross-app facts. To address this, we introduce MemGUI-Agent, an end-to-end long-horizon mobile GUI agent with proactive context management. MemGUI-Agent is built on Context-as-Action (ConAct), which casts context management as first-class actions emitted by the same policy that selects UI actions. Instead of passively appending history, ConAct maintains three structured context fields: folded action history, folded UI state, and recent step record, preserving critical UI facts while keeping context compact. To make proactive context management learnable across model scales, we construct MemGUI-3K, a 2,956-trajectory dataset with full ConAct annotations for supervised training and offline analysis. Training an 8B model on MemGUI-3K produces MemGUI-8B-SFT, an 8B MemGUI-Agent that achieves the best open-data 8B performance on MemGUI-Bench and generalizes to the out-of-distribution MobileWorld benchmark. Code, data, and trained models will be released at https://memgui-agent.github.io/.

Large language model (LLM) agents are increasingly proposed as supervisory components for safety-critical systems, yet their robustness under sustained, adaptive adversarial pressure remains poorly characterized. We present NRT-Bench, a benchmark for multi-turn red-teaming of LLM agents acting as operators of a safety-critical system, instantiated in a simulated nuclear power plant control room. A five-role operator team, each backed by a configurable LLM, runs a plant governed by six critical safety functions (CSFs), while adversaries inject messages over four channels in bounded multi-turn sessions with per-turn feedback. Harm is an objective signal rather than LLM-judged text: a run terminates the moment any CSF is lost, attributed to the causing message. Evaluating four frontier operator models under a fixed-attack paired-replay protocol, we find that adaptive multi-turn attacks reliably push the operator team past a safety limit: across the four models, between 8.7% and 12.1% of attack sessions end with the plant losing a critical safety function. Although the four models look almost equally robust by this aggregate rate, their failures barely overlap: of $149$ sessions, none defeat all four models while a third defeat at least one, so vulnerabilities are nearly disjoint across models rather than nested. The effect of added defences is strongly model-dependent: the same guardrail stack or safety-advisor agent that lowers attack success for one model can raise it for another. We release the simulation venue, attack dataset, and replay tooling for reproducible safety evaluation of LLM agents.

Collecting computer use data from human demonstrations is expensive and slow, motivating the need for scalable generation strategies. This requires two key ingredients: environments in which agents can act and verifiers that can judge whether their demonstrations succeeded. We introduce FaraGen1.5, a scalable data pipeline for computer use agents composed of three modular components: environments, solvers, and verifiers. FaraGen1.5 uses both live websites and synthetic environments that faithfully simulate domains gated by authentication or that require irreversible actions. It employs a solver harness that can be powered by multiple models, including strong frontier models such as GPT-5.4, and also incorporates a user simulator to enable multi-turn rollouts. Finally, FaraGen1.5 scores the resulting trajectories with three complementary verifiers covering task correctness, efficiency, and critical-point adherence. Using data produced by this pipeline, we train Fara1.5, a family of native computer use agents (CUAs) at three scales built on Qwen3.5 (4B, 9B, and 27B). To train these models, we employ a supervised finetuning (SFT) recipe that carefully balances data from FaraGen1.5 for broad coverage, specific high-value tasks, and target model deficiencies in an iterative approach. Each model sets a new state of the art for its size class on browser-use benchmarks: Fara1.5-9B reaches 63.4% on Online-Mind2Web and 86.6% on WebVoyager, while Fara1.5-27B achieves 72.3% on Online-Mind2Web, which is competitive with much larger proprietary systems.

LLM agents can write code and call tools, but reliable bioinformatics work requires long-horizon interaction with workflow software, typed data objects, provenance, and biological checks. We study this setting through Galaxy workflow execution. The agent must explore task data, construct or adapt an executable workflow DAG, bind inputs and dataset collections, monitor execution, debug failures, and validate biological outputs. We propose Process-Reward Tactic Evolution, a Galaxy-based training framework that turns verified workflow rollouts into reusable \tactics. During training, agents practice on curriculum-organized Galaxy tasks in Agent Gym; process verifiers score workflow construction, software interaction, execution, and biological correctness; successful and failed traces are distilled into a tactic library. At inference, the trained executor, Process-Reward Tactic Evolution, uses this library to execute held-out peer reviewed Galaxy workflow converted BioWorkflow Bench and BioAgent Bench tasks in isolated environments. The paper evaluates whether process-supervised tactic accumulation improves long-horizon bioinformatics workflow completion, biological correctness, and execution efficiency over no-memory and reflection-style baselines.

LLM-based coding agents need higher-level operational knowledge about a repository (which files house which subsystems, how to run the test suite, which workflows have historically led to wrong fixes) that does not exist in the code itself. Engineers typically maintain AGENTS.md files to supply this context as instructions for coding agents, but whether they help is contested: recent studies disagree on whether LLM-generated guidance improves or harms agent performance. In this paper we show that how the guidance is produced is the decisive variable, and introduce probe-and-refine tuning: a procedure that uses synthetic bug-fix probes to iteratively diagnose and patch a repository's guidance file through single-shot LLM calls, with no agent loop or tool use during tuning. On SWE-bench Verified across four independent trials with Qwen3.5-35B-A3B at 200 steps, probe-and-refine achieves 33.0% mean resolve rate vs. 28.3% for the static knowledge base used to initialize it and 25.5% for an unguided baseline (p < 0.001 for both probe-and-refine contrasts). The improvement comes from coverage rather than precision: refined guidance produces evaluable patches for 14.5 percentage points (pp) more instances while per-patch precision remains statistically constant (~59%, p = 0.119), showing that improved guidance helps agents reach the correct file rather than improving the quality of the changes they make. Further, a step-budget experiment shows that guidance is what lets the agent use a larger step budget productively, and a cross-model experiment with NVIDIA-Nemotron-3-Nano-30B-A3B finds that the tuning loop degrades when the model cannot generate sufficiently diagnostic output, though per-patch precision remains constant even then.