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

Unlocking LLM Code Correction with Iterative Feedback Loops

arXiv:2606.17514v1 Announce Type: cross Abstract: Large Language Models have shown remarkable capabilities in code generation. However, most existing evaluations focus only on single-attempt accuracy and overlook the iterative refinement process that is central to real-world programming. This study presents a systematic investigation of LLMs' ability to rectify their own code through execution feedback. Using real-world programming problems across four models and two major programming languages, this study evaluates performance using iterative refinement framework where LLMs receive compiler error messages and testcase feedback after each attempt. This study introduces metrics to evaluate code failures, analyze rectification patterns, and compare the effectiveness of reasoning and non-reasoning models, offering actionable insights into both the understanding and practical application of feedback loops in LLM-driven code generation systems. Results show that reasoning models consistently improve over iterations, substantially outperforming non-reasoning models in leveraging feedback, while syntactic and runtime errors are far more tractable than logical or algorithmic failures.

02.
arXiv (CS.AI) 2026-06-15

FactoryLLM: A Safe and Open-Source AI Playground for Evaluating LLMs in Smart Factories

arXiv:2606.14119v1 Announce Type: new Abstract: Fault diagnostics and recovery in smart factories is challenging because critical information is dispersed across manuals of multiple machines which are interconnected through the manufacturing process. Large Language Models (LLMs) can provide a promising approach. In this paper, we propose FactoryLLM, a safe and open-source AI playground designed for evaluating different LLM-based retrieval-augmented generation (RAG) models by analysing documents from multiple machines across the manufacturing process. FactoryLLM enables the user to configure the LLM, and assess performance when reasoning over multiple documents, through a dual evaluation setup using both RAGAS and NVIDIA's LLM-as-a-Judge metrics. FactoryLLM is safe because it allows users to run local or open-source LLMs without sharing sensitive industrial data, providing a controlled environment for experimentation. We demonstrate the efficacy of FactoryLLM through a case study which involves an Autonomous Intelligent Vehicle and its Mobile Planner software, evaluating three LLMs across 30 maintenance queries derived from approximately 600 pages of cross-machine documentation. The results suggest that FactoryLLM is effective in cross-machine document reasoning: every model achieved a groundedness score above 0.88. The full code and documentation for community to test FactoryLLM with their manufacturing specific scenarios are publicly available.

03.
arXiv (CS.CV) 2026-06-17

Contactless Respiratory Monitoring on Heterogeneous Mobile Robots: A Multimodal Edge-Computing Framework

Respiratory-rate (RR) monitoring is a critical component of remote triage and victim assessment in emergency response, disaster recovery, and infectious-disease scenarios, where minimizing physical contact can reduce responder risk and improve operational safety. However, field deployment of contactless RR monitoring remains challenging due to variable illumination, posture changes, platform heterogeneity, and the impracticality of wearable sensors in hazardous environments. In this paper, we present a modality-adaptive contactless RR monitoring framework for heterogeneous mobile robots with onboard edge computing. The proposed system combines brightness-adaptive sensor selection across RGB, thermal, near-infrared (NIR), and low-light cameras, keypoint-guided chest ROI extraction for posture-robust monitoring, and a signal-quality-index (SQI)-based filtering mechanism for reliable respiratory estimation. We implement and evaluate the framework on three robotic platforms spanning quadruped and wheeled locomotion and multiple edge-computing architectures. Experiments conducted across diverse lighting conditions, subject poses, and robot-to-subject distances demonstrate that the framework generalizes across platforms without per-platform algorithmic retuning, while revealing modality-specific operational boundaries. RGB provides the broadest coverage up to 8m, NIR remains effective up to 6m, thermal is reliable only at short range, and low-light sensing supports monitoring in complete darkness up to 8m. Overall, the results demonstrate the feasibility of multimodal contactless RR monitoring on mobile robots and support its use as a foundation for autonomous triage and victim assessment in hazardous search-and-rescue settings.

04.
arXiv (CS.CL) 2026-06-17

Bridging Functional Correctness and Runtime Efficiency Gaps in LLM-Based Code Translation

While large language models (LLMs) have greatly advanced the functional correctness of automated code translation systems, the runtime efficiency of translated programs has received comparatively little attention. With the waning of Moore's law, runtime efficiency has become increasingly important for program quality, alongside functional correctness. Our preliminary study reveals that LLM-translated programs often run slower than human-written ones, and this issue cannot be remedied through prompt engineering alone. Therefore, our work proposes SwiftTrans, a code translation framework comprising two key stages: (1) Multi-Perspective Exploration, where MpTranslator leverages parallel in-context learning (ICL) to generate diverse translation candidates; and (2) Difference-Aware Selection, where DiffSelector identifies the optimal candidate by explicitly comparing differences between translations. We further introduce Hierarchical Guidance for MpTranslator and Ordinal Guidance for DiffSelector, enabling LLMs to better adapt to these two core components. To support the evaluation of runtime efficiency in translated programs, we extend existing benchmarks, CodeNet and F2SBench, and introduce a new benchmark, SwiftBench. Experimental results across all three benchmarks show that SwiftTrans achieves consistent improvements in both correctness and runtime efficiency.

05.
medRxiv (Medicine) 2026-06-12

Genomic wastewater surveillance of seasonal and zoonotic influenza A viruses in California during the 2024-2025 flu season

Wastewater genomic surveillance provides an opportunity to detect human and animal influenza A virus (IAV). We aimed to implement an IAV genomic surveillance framework agnostic to subtype, which enables recovery of IAV from multiple hosts and estimation of proportions across subtypes. We conducted IAV genomic surveillance in wastewater during the 2024-2025 flu season at multiple sites in California and compared these data with available human clinical IAV sequences and test positivity. We applied a custom whole-genome, multi-host IAV probe enrichment panel and adapted our custom expectation-maximization (EM) algorithm to deconvolute IAV mixtures in wastewater and infer subtype relative abundances. Absolute IAV concentrations were quantified using RT-PCR-based assays. H5N1 wastewater and clinical sequences were further characterized by constructing a whole-genome maximum-likelihood phylogenetic tree. Finally, we performed variant analysis to examine amino acid substitutions detected in wastewater. Our IAV probe enrichment method and EM algorithm successfully enriched all eight segments of three circulating IAV subtypes and accurately estimated subclade relative abundances for mixed IAV samples. Seasonal human H1N1pdm09 and H3N2 were detected throughout the study period from both wastewater and clinical sequencing data, with H1N1 subclades 6B.1A.5a.2a.1 and 6B.1A.5a.2a co-circulating, and H3N2 dominated by subclade 3C.2a1b.2a.2a.3a.1. Wastewater surveillance consistently detected H5N1 clade 2.3.4.4b across three monitored wastewater sites, while clinical H5N1 detections, from anywhere in CA, were sporadic and rare. Whole-genome phylogenetic analysis revealed that wastewater H5N1 sequences clustered with reference sequences associated with dairy cow and avian infections, while all human clinical H5N1 sequences clustered exclusively with reference sequences associated with dairy cow infections. Amino acid substitutions were identified across viral segments, and no mutations associated with mammalian adaptation were observed from wastewater samples.

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

Exact Many-body Quantum Dynamics in One-Dimensional Baths via Collective Spins

arXiv:2505.00588v2 Announce Type: replace Abstract: Computing the exact dynamics of many-body quantum systems becomes intractable as system size grows. Here, we present a symmetry-based method that provides an exponential reduction in the complexity of a broad class of such problems $\unicode{x2014}$ qubits coupled to one-dimensional electromagnetic baths. We identify conditions under which partial permutational symmetry emerges and exploit it to group qubits into collective multi-level degrees of freedom, which we term ''superspins.'' These superspins obey a generalized angular momentum algebra, reducing the relevant Hilbert space dimension from exponential to polynomial. Using this framework, we efficiently compute many-body superradiant dynamics in large arrays of qubits coupled to waveguides and ring resonators, showing that $\unicode{x2014}$ unlike in conventional Dicke superradiance $\unicode{x2014}$ the total spin length is not conserved. At long times, dark states become populated. We identify configurations where these states exhibit metrologically useful entanglement. Our approach enables exact treatment of complex dissipative dynamics beyond the fully symmetric limit and provides a rigorous benchmark for approximate numerical methods.

07.
PLOS Medicine 2026-05-29

Characterization of the VHH-Fc construct rimteravimab in healthy adults and patients hospitalized for mild-to-moderate COVID-19: Two Phase 1 randomized clinical trials

作者:

by Ellen Jansen, Viki Bockstal, Florence Herschke, Per Olsson Gisleskog, Manuela Rinaldi, Angélique Boerboom, Salah Hadi, Natalia Gaibu, Michel Moutschen, Dominique Tersago Background Variable Heavy domain of Heavy chains (VHH) are innovative tools to target unique epitopes, yet few have been developed as heavy chain-only antibodies for clinical use. Rimteravimab (referred to here as XVR011) is a humanized antibody developed for the treatment of mild-to-moderate coronavirus disease 2019 (COVID-19), consisting of two identical VHHs targeting the receptor binding domain (RBD) of the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) spike, with a human immunoglobulin (Ig) G1 fragment constant of antibody (Fc), silenced for Fc effector functions. We conducted two Phase 1 studies in healthy volunteers or hospitalized COVID-19 patients to evaluate its safety, tolerability, pharmacokinetics and immunogenicity. Methods and findings A randomized, double-blinded, single-center, placebo-controlled, single ascending dose study was performed in healthy volunteers (Phase 1a, EXEVIR0102, EudraCT 2021-003707-17), in parallel to an open-label, multi-center, single ascending dose study in patients hospitalized for mild to moderate COVID-19 (Phase 1b, EXEVIR0101, EudraCT 2020-005299-36, NCT04884295). Participants received a single intravenous infusion of 250, 500 or 1,000 mg of XVR011. The primary objective for both trials was the safety and tolerability of XVR011. Pharmacokinetics were evaluated as a secondary objective in Phase 1a and as an exploratory objective in Phase 1b. Efficacy (evaluated as respiratory parameters and COVID-19 clinical status) and antiviral activity in patients were evaluated as a secondary objective in Phase 1b. Immunogenicity was evaluated as an exploratory objective. Part 2 of the EXEVIR0101 study (initially a phase 1b/2 study) was not conducted due to the loss of XVR011 potency against SARS-CoV-2 Omicron BA.2. Demographics, safety, efficacy, and immunogenicity were analyzed using descriptive statistics, while pharmacokinetics were analyzed with noncompartmental pharmacokinetics (PK) modeling.In the Phase 1a study, there were no infusion-related reactions, serious treatment-emergent adverse events (TEAEs) or TEAEs grade ≥3. 22/30 volunteers (73.3%) reported 53 TEAEs (49 Grade 1, 4 Grade 2) with none being related to XVR011. The most common TEAE was headache (n = 8, 26.7%) in various treatment groups. In the Phase 1b study, 27 hospitalized patients were enrolled, and followed up to 30 days. Seven patients (25.9%) reported a total of 15 TEAEs, the majority (80%) being mild to moderate (Grade 1–2). There were no treatment-related serious TEAEs. All TEAEs resolved by the end of the study. Peak exposure (maximal concentration, Cmax) and systemic exposure (area under the curve, AUC0-t, and AUC0-inf) for XVR011 increased dose-proportionally. Geomean half-life ranged from 15.4 to 17.0 days in Phase 1a, while individual half-life ranged from 11.4 to 15.6 days in Phase 1b. SARS-CoV-2 viral load, as detected in nasopharyngeal samples by reverse transcription and quantitative polymerase chain reaction (RT-qPCR), decreased similarly in all cohorts compared to baseline. No treatment-induced anti-drug antibodies (ADA) were detected in Phase 1a. In Phase 1b, higher XVR011 concentrations increased the likelihood of ADA formation, without impacting pharmacokinetics and pharmacodynamics. No obvious dose-response in COVID-19 clinical status or respiratory parameters was observed.Technological limitations included study size, absence of placebo for the Phase 1b, absence of repeated dosing, evolving SARS-CoV-2 variants and standard-of-care. Conclusions XVR011 displayed a favourable safety, tolerability, pharmacokinetics, and immunogenicity profile, both in healthy volunteers and in patients hospitalized for mild to moderate COVID-19. These data pave the way for the design and clinical development of VHH-Fc constructs.

08.
medRxiv (Medicine) 2026-06-15

Artificial Intelligence-Based Detection of Airway Mucus Plugs on CT and Associations With Clinical Outcomes in COPDGene

RATIONALE: Airway mucus plugging is a clinically relevant manifestation of airway pathology in chronic obstructive pulmonary disease (COPD) and is associated with increased mortality even in early disease; however, visual computed tomography (CT) assessment is subjective and labor intensive. OBJECTIVES: To develop an AI-based quantitative CT method for automated detection of airway mucus plugging and evaluate associations with physiologic impairment and clinical outcomes. METHODS: Inspiratory CT scans from 8,971 COPDGene Phase 1 (GOLD 0-4 and PRISm) participants were analyzed. An AI-based framework combining 3D airway segmentation discontinuities and convolutional neural network classification identified mucus plug obstructions, yielding mucus plug burden (total plug count). Associations with outcomes were evaluated using covariate-adjusted models. MEASUREMENTS AND MAIN RESULTS : Higher mucus plug burden was associated with lower post-bronchodilator FEV % predicted ({rho} = -0.41; P < 0.001), greater air trapping (LAA < -856 HU; {rho} = 0.33; P < 0.001), worse health status (SGRQ; {rho} = 0.31; P < 0.001), and shorter 6-minute walk distance ({rho} = -0.26; P < 0.001). Among GOLD 1-4 participants, mucus plug presence was independently associated with increased all-cause mortality (adjusted hazard ratio, 1.28; P < 0.005) and exacerbation frequency (adjusted incidence rate ratio, 1.32; P < 0.005). Plug presence was also associated with increased respiratory mortality across GOLD categories and cardiovascular mortality in GOLD 1-2. CONCLUSIONS: AI-based quantitative CT assessment of airway mucus plugging provides a scalable, reproducible measure associated with physiologic impairment and adverse outcomes in COPD, supporting its role in risk stratification and future therapeutic studies.

09.
arXiv (CS.CL) 2026-06-11

ClawEnvKit: Automatic Environment Generation for Claw-Like Agents

Constructing environments for training and evaluating claw-like agents remains a manual, human-intensive process that does not scale. We argue that what is needed is not just a dataset, but an automated pipeline capable of generating diverse, verified environments on demand. To this end, we introduce ClawEnvKit, an autonomous generation pipeline that instantiates this formalism from natural language descriptions. The pipeline comprises three modules: (1) a parser that extracts structured generation parameters from natural language input; (2) a generator that produces the task specification, tool interface, and scoring configuration; and (3) a validator that enforces feasibility, diversity, structural validity, and internal consistency across the generated environments. Using ClawEnvKit, we construct Auto-ClawEval, the first large-scale benchmark for claw-like agents, comprising 1,040 environments across 24 categories. Empirically, Auto-ClawEval matches or exceeds human-curated environments on coherence and clarity at 13,800x lower cost. Evaluated across 4 model families and 8 agent harness frameworks, we find that harness engineering boosts performance by up to 15.7 percentage points over a bare ReAct baseline, completion remains the primary axis of variation with no model saturating the benchmark, and automated generation enables evaluation at a scale previously infeasible. Beyond static benchmarking, ClawEnvKit enables live evaluation: users describe a desired capability in natural language and obtain a verified environment on demand, turning evaluation into a continuous, user-driven process. The same mechanism serves as an on-demand training environment generator, producing task distributions that adapt to an agent's current weaknesses rather than being bounded by existing user logs.

10.
arXiv (CS.CL) 2026-06-16

Pepti-Agent: An AI Agent for Peptide Design and Optimization

Therapeutic peptides occupy a valuable design space between small molecules and biologics, but their development requires satisfying several competing constraints at once: solubility, hemolytic activity, and nonspecific surface fouling are governed by overlapping sequence features, so improving one property often degrades another. Computational design addresses this by pairing generative models with sequence-based property predictors, iteratively proposing and refining candidates. However, these components are typically wired together as monolithic scripts that are difficult to inspect, extend, or reuse, and they often refine sequences by natural-language reasoning rather than by tracking the evolving multi-property state of each candidate. We present Pepti-Agent, a closed-loop, peptide-specific framework that exposes generation, property prediction, and single-residue mutation as independently inspectable Model Context Protocol (MCP) tools. A large language model controller invokes these tools and consults live predictor output between calls, so refinement is guided by each sequence's current property profile rather than by language reasoning alone. Task-specific PeptideGPT models generate candidates, ProtBERT-based classifiers score solubility, hemolysis, and non-fouling, and two interchangeable mutation operators propose sequence edits. By recording a per-step trace of controller decisions, predictor outputs, and accepted mutations, Pepti-Agent offers a reproducible substrate for benchmarking multi-objective design strategies and for prioritizing candidates for experimental validation.

11.
Nature (Science) 2026-06-10

Daily briefing: Ancient ground squirrels ate like ‘zombies of the Pleistocene’

作者:

Evidence from fossilized poo reveals the diverse diet of ancient ground squirrels. Plus, the science behind the peptide craze and our innate tendency to wander anticlockwise. Evidence from fossilized poo reveals the diverse diet of ancient ground squirrels. Plus, the science behind the peptide craze and our innate tendency to wander anticlockwise.

12.
arXiv (CS.CL) 2026-06-16

Re-feeding Is Not Replaying: Measuring Replay Noise in Counterfactual Token-Credit Estimation

Per-token counterfactual credit estimation asks which token in a language-model rollout caused the final answer to be right or wrong: cut the transcript at a pivot, substitute an alternative token, replay continuations, and compare outcomes. Published methods re-feed the transcript prefix as a fresh prompt, assuming this reproduces the state the model passed through during generation. We measure what that assumption costs on a stock inference engine, with a three-pass design: continuations resumed from the verified decode-time KV state, an identical second exact pass (a replica noise floor), and a re-feed pass. Across six configurations and three models (including a GRPO-trained checkpoint), at low-margin decision tokens, re-feeding changes the credit estimate at rates 14-28 percentage points above the replica floor (7-21pp under a treatment-independent conditioning; problem-clustered t = 2.9-6.4). Most changes are zero-boundary crossings of the quantized estimator rather than polarity reversals, and the perturbation is consistent with mean-zero, so averaged quantities are largely safe; but selection is not: a critical-token set chosen by thresholding $|\hat{A}_t|$ under re-feed overlaps the exact-resume selection at Jaccard 0.34-0.90, versus a 0.63-0.96 replica ceiling. A causal confirmation closes the loop: under vLLM's batch-invariant kernels all three passes are identical on every measured channel, with both disagreement rates exactly zero. Replica passes themselves disagree on 9-23% of eligible estimates: single-sample credit measurements at decision tokens are unreliable under any replay. Settings were fixed in advance; exact-pass cache hits in the second campaign are instrumented (100% hit rate, 3,434 pivots); total compute was under 10 USD. We recommend that counterfactual credit studies resume decoder state or use batch-invariant kernels, and report a replica floor.

13.
arXiv (math.PR) 2026-06-12

The censored stochastic six-vertex model and parabolic Kazhdan–Lusztig $R$-polynomials

arXiv:2606.12670v1 Announce Type: new Abstract: We introduce a censored version of the stochastic six-vertex model. We show that for parameters $b_1 < b_2$, this model started from the initial condition ${1}_{x>0}$ is stochastically dominated at any time by the blocking measure. This is a partial analog of the censoring inequality for monotone spin systems. In particular, this result allows us to control the behavior of second-class particles. The proof uses parabolic Kazhdan–Lusztig $R$-polynomials, whose appearance is explained using a connection between the stochastic six-vertex model and the Iwahori–Hecke algebras of symmetric groups. Furthermore, we find an intertwining relation for this process using normalized parabolic Kazhdan–Lusztig $R$-polynomials as an intertwining kernel.

14.
PLOS Computational Biology 2026-06-11

Catecholamine precursor modulation of human exploration: Evidence from a large gender-balanced sample

by Angela Mariele Brands, Kilian Knauth, David Mathar, Tim Roedder, Kerstin Lisner, Jan Peters The catecholamine precursor Tyrosine has been linked to improved cognitive performance, but investigations into decision-making and reinforcement learning processes known to be under catecholamine control are sparse. We examined the impact of a single dose of Tyrosine (2g) on reinforcement learning and exploration in a large (n = 63) gender-balanced sample in a within-subjects preregistered study. Reinforcement learning performance was significantly improved under Tyrosine. Based on previous work, we preregistered the hypotheses that Tyrosine would reduce directed exploration, response times, and physiological arousal. However, neither response times nor physiological arousal revealed the predicted reductions. Computational modelling using an established pre-registered reinforcement learning model revealed that the performance improvement under Tyrosine was due to an increase value-driven exploitation, without affecting directed exploration. Non-preregistered modelling analyses then revealed that accounting for higher-order perseveration substantially improved model fit, and substantiated the observation of increased value-driven exploitation under Tyrosine. Furthermore, it revealed reliable reductions in directed exploration and value-independent perseveration under Tyrosine. Tyrosine thus improved reinforcement learning performance by stabilizing choice patterns in the service of optimizing reward accumulation, modulating several computational mechanisms thought to be under catecholamine control.

15.
arXiv (CS.LG) 2026-06-11

The ASE-LSE Disagreement Landscape: An End-to-End Characterisation of Extremes and Structural Drivers

arXiv:2605.22346v3 Announce Type: replace-cross Abstract: Two of the most widely used methods for analysing graph data, Adjacency Spectral Embedding and Laplacian Spectral Embedding, often produce different results when applied to the same graph. Yet the structural reasons behind this disagreement remain incompletely understood. This paper provides an end-to-end account of ASE-LSE latent subspace disagreement. We first prove that the two methods produce identical latent subspaces for every embedding dimension whenever the Laplacian is a scalar multiple of the adjacency matrix, and show that this scalar relationship holds if and only if the graph is either regular or bipartite biregular. This anchor result identifies a sufficient condition for perfect agreement that pins down the floor of the disagreement spectrum and supplies the baseline for the perturbation analysis. We then prove that no maximal-disagreement graph or family of graphs exists: the disagreement is always strictly below its theoretical ceiling, and we exhibit a witness family demonstrating that no finite maximum is attainable, so the disagreement landscape has no maximiser. With both endpoints established, we derive a Regularity Departure Bound whose two terms isolate degree heterogeneity and eigengap as the primary structural factors influencing disagreement in the middle regime. Empirical validation across thousands of simulated graphs confirms the mechanisms predicted by the bound: heterogeneity pushes disagreement up, eigengap suppresses it, and their joint ratio emerges as a unified predictor of ASE-LSE disagreement, suggesting when the two embeddings can be treated as interchangeable and when they cannot.

16.
arXiv (CS.AI) 2026-06-19

Multi-LCB: Extending LiveCodeBench to Multiple Programming Languages

arXiv:2606.20517v1 Announce Type: new Abstract: 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.

17.
arXiv (CS.CL) 2026-06-11

SAGE: Answer-Conditioned Uncertainty Targets for Verbal Uncertainty Alignment

Large language models increasingly express uncertainty through natural-language statements, yet these expressions often fail to reflect the model's sampled behavior. We study verbal uncertainty alignment as a distributional calibration problem: the appropriate uncertainty target for a prompt should be estimated from repeated model outputs rather than from an isolated response. However, group rollouts alone are insufficient, since the resulting target must provide a useful training signal. Existing targets only partially satisfy this requirement. We propose SAGE, Semantic-Answer Guided Entropy, a group-level uncertainty target that constructs an answer-conditioned uncertainty geometry over sampled responses. SAGE preserves categorical, numeric, and symbolic answer distinctions while maintaining a smooth and scale-preserving calibration signal. We further apply this target through Group-Uncertainty Preference Optimization, or GUPO, an uncertainty-channel training framework that supervises verbal uncertainty expressions rather than the full response. Experiments across factual, mathematical, and multiple-choice reasoning tasks show improved uncertainty ranking, lower calibration error, and reduced overconfidence.

18.
arXiv (CS.CL) 2026-06-12

Beyond Uniform Tokens: Adaptive Compression for Time Series Language Models

Large language models (LLMs) have enabled time series (TS) analysis by jointly modeling numerical observations and textual context through a shared token interface. However, TS tokens and prompt tokens exhibit fundamentally different information structures, making uniform token processing inefficient. In this paper, we study token efficiency in TS language modeling from an asymmetric-token perspective. We show that TS tokens have highly uneven spectral contributions, where many tokens share redundant frequency patterns while a small subset preserves critical temporal evidence. We also observe that prompt-token influence attenuates with model depth, suggesting that full prompt retention across all layers is unnecessary. Based on these findings, we develop an adaptive token budgeting framework that compresses TS tokens via frequency-domain structure and progressively reduces prompt tokens across layers. Experiments across forecasting, classification, imputation, and anomaly detection demonstrate up to 7.68$\times$ inference acceleration and performance gains in 78\% of evaluated settings, showing the effectiveness of asymmetric token compression for scalable TS foundation models.

19.
arXiv (CS.AI) 2026-06-16

Automating Low-Risk Code Review at Meta: RADAR, Risk Calibration, and Review Efficiency

arXiv:2605.30208v2 Announce Type: replace-cross Abstract: AI-assisted coding tools have altered software production. At Meta, significant lines of code per human-landed diff grew by 105.9% year over year and per-developer diff volume rose 51%, with agentic AI responsible for over 80% of that growth. Meanwhile, the share of diffs receiving timely review has declined, exposing a widening gap between code supply and reviewer bandwidth. We ask three questions that progress from feasibility through calibration to impact: (1) can risk-stratified automation operate at scale across diverse organizations, (2) how does tuning the risk threshold affect the trade-off between automation yield and safety, and (3) to what extent does automated review reduce end-to-end latency for AI-generated changes? We deployed RADAR (Risk Aware Diff Auto Review), a multi-stage funnel that classifies each diff by authorship and source type, applies eligibility gates, static heuristics, a machine-learned Diff Risk Score, LLM-based Automated Code Review, and deterministic validation before landing qualifying changes. We evaluate RADAR through telemetry covering 535K+ RADAR-reviewed diffs, observational before-after comparisons for policy changes, and difference-in-differences analysis of efficiency outcomes. RADAR has reviewed 535K+ diffs and landed 331K+. Relaxing the Diff Risk Score threshold from the 25th to the 50th percentile increased the approve rate to 60.31%. The revert rate for RADAR-reviewed diffs is 1/3 that of non-RADAR diffs, and the Production Incident rate is 1/50 that of non-RADAR diffs. RADAR reduces median time to close by over 330% and median diff review wall time by 35%. Risk-aware layered automation can materially reduce review bottlenecks created by AI-driven code growth without compromising production safety.

20.
arXiv (CS.CL) 2026-06-11

Evolving Agents in the Dark: Retrospective Harness Optimization via Self-Preference

AI agents rely on a harness of skills, tools, and workflows to solve complex problems. Continually improving this harness is essential for adapting to new tasks. However, existing optimization methods typically require ground-truth validation sets, yet such labeled data is difficult to acquire in practical deployment settings. To address this problem, we introduce Retrospective Harness Optimization (RHO), a self-supervised method that optimizes the agent harness using only past trajectories. Specifically, RHO selects a diverse coreset of challenging tasks from past trajectories and re-solves them in parallel. The agent analyzes these rollouts using self-validation and self-consistency, then generates candidate harness updates and selects the most effective one by its own pairwise self-preference. We evaluate RHO across three diverse domains, spanning software engineering, technical work, and knowledge work. Notably, a single optimization round improves the pass rate on SWE-Bench Pro from 59% to 78% without any external grading. Furthermore, our analysis demonstrates that RHO effectively targets prior failure modes. As a result, the optimized harness alters the agent's behavior patterns and sustains higher accuracy during long-horizon sessions.

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

Towards Conditional Feature Alignment for Cross-Domain Counting

Object counting models often degrade under cross-domain deployment because density composition varies across domains and is itself task-relevant. Standard feature alignment methods tend to suppress such variation by encouraging global domain invariance, which can be harmful when source and target domains contain different proportions of background, sparse foreground, and dense foreground. We propose Conditional Feature Alignment (CFA), a cross-domain counting framework that aligns representations within label-induced conditions rather than across full marginal feature distributions. Given density annotations or pseudo-density predictions, CFA constructs foreground/background or density-level conditions and aligns only features belonging to matching conditions. We formalise this idea through a conditional divergence perspective, showing that conditional alignment removes within-condition discrepancy while preserving condition-marginal density shift. For unsupervised domain adaptation, CFA estimates source conditions from annotations and target conditions from detached pseudo-density maps, then performs condition-wise adversarial alignment with full-image consistency regularisation. For source-domain generalisation, we instantiate the same principle with MPCount by enforcing condition-wise memory-consistency between generated source-domain views. Experiments on crowd and cell counting benchmarks show competitive or improved performance across diverse UDA and DG settings. For example, on JHU-CROWD++ FH$\rightarrow$SN, CFA-DG reduces MAE/RMSE from MPCount's 216.3/421.4 to 90.5/169.9, indicating that condition-wise alignment is especially effective under large weather- and density-induced shifts. These results suggest that condition-wise alignment is a promising design principle for domain-adaptive counting.

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

Flickering Multi-Armed Bandits

arXiv:2602.17315v3 Announce Type: replace-cross Abstract: We introduce Flickering Multi-Armed Bandits (FMAB) to model sequential decision-making in environments with changing action availability, where accessibility of the next action is restricted to a subset dependent on the agent's current choice. We formalize these constraints through stochastically evolving graphs where actions are limited to local neighborhoods. This mobility-constrained structure imposes a dual challenge: the statistical requirement of information acquisition and the physical overhead of navigation. We analyze FMAB under i.i.d. Erdős–R'enyi and Edge-Markovian process, proposing a two-phase lazy random walk algorithm for robust exploration. We establish high-probability sublinear regret bounds and prove near-optimality via a matching information-theoretic lower bound. Our results characterize the intrinsic cost of learning under local-move constraints, complemented by a robotic disaster-response simulation.

23.
arXiv (CS.LG) 2026-06-11

Spectrally Regularized Latent Flow Matching for Turbulence Generation

arXiv:2606.11691v1 Announce Type: new Abstract: Latent diffusion and flow matching have emerged as leading approaches for synthetic turbulence generation, yet they systematically under-represent dissipation-range amplitudes. We introduce a latent flow matching framework with a spectrally regularized compression stage that directly targets this failure mode. On a 256^2 DNS dataset at Re_f \approx 2250, replacing an MSE-trained VAE with a zone-weighted log-spectral objective raises deep-dissipation retained spectral power from 25% to 94% in reconstruction and from 20% to 79% in unconditional generation. The improved latent representation also yields a substantially better sampling cost-fidelity tradeoff: the MSE-trained latent space imposes a fundamental quality ceiling near DD bias -0.70 that no integrator or step-count can overcome, while the spectrally regularized latent space reaches DD bias -0.117 at just 20 function evaluations. Mechanistically, encoder-decoder swap experiments show that the improvement is driven primarily by encoder-induced latent reorganization rather than decoder capacity, while a support-amplitude decomposition reveals that MSE-trained models behave as conservative suppression models, minimizing pointwise error by attenuating intermittent high-wavenumber structure. Both pipelines recover the second-order structure function and the correct sign of S_3, indicating the correct cascade direction without explicit supervision. A small residual gap in the magnitude of S_3 suggests that phase-coherent triadic organization remains a complementary axis to amplitude fidelity for future generative turbulence models.

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

SCAIL-2: Unifying Controlled Character Animation with End-to-end In-Context Conditioning

Controlled character animation requires transferring motion from a driving sequence to a reference character. Prior works heavily rely on intermediate representations, including pose skeletons to represent motion or masked background to represent environment, which inevitably leads to information loss. To address this, we present SCAIL-2, a framework that bypasses those intermediates and achieves end-to-end character animation. By directly concatenating driving videos to the sequence, the model can obtain all the required visual information from the input video. To address the lack of end-to-end data, we unify sub-tasks of character animation with decoupled conditions and then curate a pipeline to synthesize MotionPair-60K, an end-to-end motion transfer dataset containing heterogeneous tasks of character animation. To achieve the unification, we utilize in-context mask conditioning and mode-specific RoPE as soft guidance beyond textual instructions and raw visual information. To address synthetic discrepancy in detailed regions, we propose Bias-Aware DPO to construct preference items to mitigate the errors. Extensive experiments demonstrate that our method substantially outperforms existing state-of-the-art approaches in various character animation tasks. A large subset of synthetic data as well as model weights will be released at our project page: https://teal024.github.io/SCAIL-2/.

25.
arXiv (CS.CL) 2026-06-16

A Unified Definition of Hallucination: It's The World Model, Stupid!

Despite numerous attempts at mitigation since the inception of language models, hallucinations remain a persistent problem even in today's frontier LLMs. Why is this? We review existing definitions of hallucination and fold them into a single, unified definition wherein prior definitions are subsumed. We argue that hallucination can be unified by defining it as simply inaccurate (internal) world modeling, in a form where it is observable to the user. For example, stating a fact which contradicts a knowledge base OR producing a summary which contradicts the source. By varying the reference world model and conflict policy, our framework unifies prior definitions. We argue that this unified view is useful because it forces evaluations to clarify their assumed reference "world", distinguishes true hallucinations from planning or reward errors, and provides a common language for comparison across benchmarks and discussion of mitigation strategies. Building on this definition, we also connect our framework to HalluWorld, a complementary benchmark that instantiates fully specified reference world models for stress-testing model hallucinations.