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) 2026-06-16

Variance Reduction for Non-Log-Concave Sampling with Applications to Inverse Problems

arXiv:2606.16257v1 Announce Type: cross Abstract: Sampling from high-dimensional, non-log-concave distributions with unnormalized densities is a fundamental challenge in machine learning, particularly when the exact gradient of the potential is unavailable and must be approximated via stochastic gradients that exhibit high variance under a fixed budget of gradient computations per iteration. Although variance reduction techniques such as SGD with momentum, STORM, and PAGE have demonstrated improved convergence properties in non-convex optimization, their implications for sampling from non-log-concave distributions remain largely unexplored. In this work, we develop the first unified analysis of these estimators for sampling from non-log-concave distributions. We establish improved non-asymptotic convergence rates in $\varepsilon$-relative Fisher information and, under a Poincaré inequality assumption, in squared total variation distance, and further prove weak convergence to the target distribution. We extend our analysis to solving inverse problems with score-based generative priors. We empirically validate our theory and demonstrate that, under a fixed gradient computations per iteration, variance-reduction techniques consistently improve sample quality in two standard imaging applications.

02.
arXiv (CS.CV) 2026-06-16

V2P-Manip: Learning Dexterous Manipulation from Monocular Human Videos

Achieving autonomous robotic dexterous manipulation requires precise, human-like action sequences at scale. As a scalable supplement to costly teleoperation data, extracting trajectories with both visual fidelity and physical plausibility from monocular videos represents a promising frontier in embodied AI. To this end, we introduce V2P-Manip, an efficient framework designed to learn dexterous manipulation policies directly from human demonstration videos. We establish an efficient, integrated pipeline encompassing 3D asset acquisition, trajectory estimation, and dexterous policy learning. To bridge the gap between visual perception and physical constraints, we introduce a two-stage refinement process to enforce spatial alignment and physical consistency. Evaluations on the TACO and OakInk benchmarks demonstrate that our approach significantly outperforms previous methods in pose accuracy, adaptability to unstructured environments, and training efficiency. Ultimately, experimental results confirm an average success rate of over 75% across multiple synthetic manipulation tasks and validate the adaptability of the extracted manipulation priors across diverse dexterous hand embodiments.

03.
arXiv (math.PR) 2026-06-17

Limit theorems for random Dirichlet series with summation over primes, with an application to Rademacher random multiplicative functions

arXiv:2508.15032v2 Announce Type: replace Abstract: It is shown that two conjectures put forward in the recent article Iksanov and Kostohryz (2025) are true. Namely, we prove a functional central limit theorem (FCLT) and a law of the iterated logarithm (LIL) for a random Dirichlet series $\sum_p \frac{\eta_p}{p^{1/2+s}}$ as $s\to 0+$, where $\eta_1$, $\eta_2,\ldots$ are independent identically distributed random variables with zero mean and finite variance, and $\sum_p$ denotes the summation over the prime numbers. As a consequence, an FCLT and an LIL are obtained for $\log \sum_{n\geq 1} \frac{f(n)}{n^{1/2+s}}$ as $s\to 0+$, where $f$ is a Rademacher random multiplicative function.

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

DifFRACT: Diffusion Feature Reconstruction and Attribution for Circuit Tracing

Mechanistic interpretability seeks to explain neural network behavior by decomposing model computations into interpretable features and circuits. While transcoder-based circuit tracing has recently enabled detailed causal analyses of large language models, multimodal diffusion transformers for image generation remain comparatively opaque. We still lack tools for understanding how semantic information propagates across denoising steps and how text and image representations interact within double-stream MM-DiT architectures. Existing methods provide only partial insight: attention maps expose a limited view of token interactions, while sparse autoencoders can discover interpretable features but do not directly reveal how these features are transformed and composed through nonlinear MLP layers. In this work, we extend transcoder-based circuit tracing to multimodal diffusion transformers. We train timestep-conditioned transcoders that faithfully approximate the input-output behavior of MLP sublayers in FLUX.1[schnell]. By replacing MLPs with transcoders and linearizing the remaining computation, we obtain exact feature-to-feature attribution and recover compact, interpretable circuits. Empirically, our transcoders match or slightly outperform sparse autoencoders on the sparsity-faithfulness tradeoff. The resulting circuits reveal mechanisms underlying attribute binding and cross-stream semantic propagation, and provide causal explanations for systematic generation errors. Moreover, circuit-guided interventions are substantially more precise and effective than standard SAE-based steering. Our results demonstrate that transcoder-based circuit analysis is feasible for state-of-the-art diffusion transformers and provides a powerful framework for understanding and controlling multimodal generative models. The code is available at https://github.com/Artalmaz31/DifFRACT

05.
arXiv (CS.LG) 2026-06-19

Quantile of Means: A Bonus-Free Ensemble Method for Minimax Optimal Reinforcement Learning

arXiv:2606.20107v1 Announce Type: new Abstract: Optimal Reinforcement Learning (RL) algorithms typically rely on carefully constructed count-based uncertainty estimates to drive exploration. Although theoretically sound, such estimates are hard to compute in practical settings and therefore offer limited insight for designing exploration heuristics. Meanwhile, ensembling has emerged as a practical approach, but remains without theoretical justification. Building on a recent ensemble-based method for Multi-Armed Bandits, we propose a quantile-based ensemble method for finite-horizon Markov Decision Processes (MDPs). Our simple count-free approach achieves optimal variance-dependent regret bounds, providing theoretical grounding for ensemble-based exploration in RL.

06.
Nature (Science) 2026-06-17

The EU needs to back its ambition to end animal testing with cash

作者: 未知作者

The European Union has declared that it wants to stop using animals in chemical safety testing. Its goal will need a timeline and a serious funding commitment. The European Union has declared that it wants to stop using animals in chemical safety testing. Its goal will need a timeline and a serious funding commitment.

07.
arXiv (CS.CL) 2026-06-24

When Retrieval Metrics Mislead: Measuring Policy Signal in Long-Horizon Tool-Use Agents

Exact-match retrieval recall is often used as a proxy for whether a retriever supplies useful policy context to a downstream decision model. We test this proxy for pre-action policy classification in tau-bench using Qwen2.5-3B/7B classifiers. Under gold-policy conditioning, a compact structured state improves macro-F1 over raw trajectories by 0.13-0.17 after tuning. We then replace the benchmark-designated policy clause with the top-ranked clause retrieved from decision-time context. Although the exact governing clause is retrieved at rank 1 for only 7% of airline states, the primary 3B classifier obtains macro-F1 0.58 with retrieved clauses versus 0.60 with gold clauses (Delta=-0.02, task-cluster 95% CI [-0.23,+0.21]); mismatched-policy and no-policy controls score 0.32 and 0.21. We do not detect a macro-F1 difference between retrieved and gold clauses in this configuration, although the interval remains too wide to establish non-inferiority. The same qualitative pattern appears with a second retriever and at 7B, while varying across fine-tuning configurations. These results indicate that exact-match clause recall can underestimate downstream policy utility in this benchmark setting, motivating evaluation with retrieved policies in the classification loop rather than recall alone.

08.
medRxiv (Medicine) 2026-06-17

Macrophage-targeted glucocorticoid prodrug resolves acute inflammation while preserving HPA axis function: mechanistic, preclinical, and Phase II/III clinical evidence

Glucocorticoids (GCs) remain the fastest-acting anti-inflammatory agents but are constrained by systemic exposure that suppresses the hypothalamic pituitary adrenal (HPA) axis, silences adaptive immunity, and drives chronic toxicities. Chronic inflammatory diseases are sustained by long-lived CD206+ macrophages containing immune-resistant pathogenic material not cleared physiologically. We developed 101-PGC-005 ('005), a macrophage-targeted type 1a dexamethasone prodrug engineered for low-affinity, recycling-compatible uptake via CD206, with intracellular release triggered by acidic endosomes. We evaluated '005 in mechanistic assays, pathogen-diverse preclinical models, three human pharmacokinetic (PK) studies, and an adaptive-design randomized Phase II/III trial in 309 hospitalized patients with moderate COVID-19. In two completed Phase I human studies, a first-in-human dose-escalation and repeated-dose study and a dedicated single/multiple-dose PK and safety study; '005 circulated as intact prodrug with rapid systemic clearance (Tmax ~0.5 h; terminal half-life ~1.9 h), with no measurable free dexamethasone after single dosing and only low, clinically non-significant free dexamethasone after repeated dosing, and intact prodrug recovered unchanged in urine. Morning cortisol and ACTH were preserved after 30 mg once daily for three consecutive days (1.5 times the intended therapeutic dose). A cerebrospinal fluid PK study is evaluating central-compartment penetration. In the Phase II/III trial, powered for non-inferiority, conducted across six sites in India under GCP with Ministry of Health approval and independent DSMB oversight; '005 (20 mg IV daily for 3 days) was superior to dexamethasone (6 mg IV daily for 3 -10 days) on the primary endpoint of time to > a 2-point improvement on the WHO ordinal scale (HR 2.31; 95% CI 1.83-2.93; p < 0.0001; median 3 vs. 4 days). '005 was also superior on viral clearance (HR 1.47; 95% CI 1.17-1.84; p = 0.0001), hospital discharge rate, SpO2; recovery, and fever resolution. Zero patients in the '005 arm received investigator-initiated corticosteroid supplementation despite protocol allowance. All 309 randomized patients completed the study (ITT = per-protocol). Safety profiles were equivalent (TEAEs 54.8% vs 54.5%; p = 0.958), with no Grade 3+ events, SAEs, deaths, or discontinuations in either arm. Mechanistically, '005 delivered dual benefit: acute debulking of inflammatory macrophages and selective depletion of chronically activated pathology-sustaining macrophages, while preserving CXCL10 antiviral signaling and physiologic HPA control. Critically, HPA preservation is not merely a safety feature, it is a core efficacy mechanism: by clearing the pathogenic macrophage burden that was overriding HPA regulation, '005 restores the conditions for endogenous cortisol to resume its pulsatile, demand-responsive anti-inflammatory role across all GR-expressing cells, lymphocytes, endothelial cells, neurons, and newly differentiated macrophages, that '005 itself cannot reach. These findings support regulatory-grade evidence for macrophage-targeted corticosteroid therapy and provide the foundation for further development across acute inflammatory indications (sepsis, viral pneumonia, cytokine-release syndromes) and chronic macrophage-driven diseases (atherosclerosis, metabolic steatohepatitis, neurodegeneration, tumor-associated macrophages).

09.
arXiv (CS.LG) 2026-06-17

Tacit Coordination of Large Language Models

arXiv:2601.22184v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) are increasingly deployed in multi-agent settings that require coordination without communication, from human-AI interaction to safety-critical scenarios. Humans often overcome the absence of communication through focal points: salient solutions that naturally stand out to all participants. We present the first large-scale evaluation of how, when, and why focal points emerge in LLMs, comparing their behaviour with humans across cooperative and competitive games, including realistic search and rescue scenarios, demonstrating when focal points enable effective coordination. Across more than 20 open- and closed-source models, we find that LLMs exhibit a remarkable ability to coordinate without communication, often matching or outperforming humans. However, the same models consistently fail in tasks requiring numerical common sense or culturally nuanced notions of salience. We additionally evaluate simple learning-free strategies that substantially improve coordination both among LLMs and between humans and LLMs. Our results reveal striking coordination capabilities, as well as social limitations in modern LLMs, and offer new insight into the latent notions of salience encoded within them. Our findings caution against assuming that LLMs share humans' cultural and perceptual substrate when deployed in coordination settings.

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

Structural Energy Guidance for View-Consistent Text-to-3D Generation

Text-to-3D generation based on diffusion models often suffers from the Janus problem, leading to inconsistent geometry across viewpoints. This work identifies viewpoint bias in 2D diffusion priors as the main cause and proposes Structural Energy-Guided Sampling (SEGS), a training-free and plug-and-play framework to improve multi-view consistency. SEGS constructs a structural energy in the PCA subspace of U-Net features and injects its gradient into the denoising process. It can be easily integrated into SDS/VSD pipelines without retraining. Experiments show that SEGS reduces the Janus Rate by about 10% on average and improves View-CS scores across multiple baselines, including DreamFusion, Magic3D, and LucidDreamer. This method effectively alleviates viewpoint artifacts while preserving appearance fidelity, providing a flexible solution for high-quality text-to-3D content generation.

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

SkyJEPA: Learning Long-Horizon World Models for Zero-Shot Sim-to-Real Control of Quadrotors

arXiv:2606.23444v2 Announce Type: replace-cross Abstract: Accurate dynamics models are critical for informed decision-making in robotic systems, particularly for agile aerial vehicles operating under uncertainty. Neural network dynamics models are attractive for capturing complex nonlinear effects, but existing predictive approaches struggle with long-horizon forecasting because their autoregressive rollout mechanism amplifies errors over time. Joint Embedding Predictive Architectures (JEPAs) offer a compelling alternative by modeling dynamics in latent space, yet prior JEPA-style methods for robot navigation have been studied primarily for kinematic-level planning, with limited investigation in high-frequency control. In this work, we introduce the JEPA-style model for real-time quadrotor control. The proposed approach combines a latent dynamics model with a novel physics-inspired prober that maps frozen latents to interpretable state, enabling physically grounded long-horizon prediction. Additionally, we combine the learned model with a sampling-based optimal control solution to take advantage of its predictive capabilities for real-time control on embedded hardware. Finally, to reduce the dependence on expensive and unsafe real-world data collection, we develop a structured pipeline for automated dataset generation. Extensive open-loop and outdoor closed-loop experiments demonstrate accurate prediction, robust zero-shot sim-to-real transfer, and strong generalization across diverse operating conditions.

12.
arXiv (CS.LG) 2026-06-19

Off-Policy Evaluation for Missingness-Aware Policies in MDPs with Rewards Missing Not at Random

arXiv:2606.20206v1 Announce Type: cross Abstract: In offline Reinforcement Learning, immediate rewards in logged batch data are often unobserved due to sparse or irregular record-keeping, or censored beyond certain reward values. This issue arises in practical settings, including health care and marketing. We investigate off-policy evaluation (OPE) in finite-horizon Markov decision processes when rewards are missing not at random (MNAR), which breaks ignorability and induces selection bias even after conditioning on states and actions. To address this, we formalize a reward-dependent propensity model and use future states as shadow variables to identify the full-data conditional mean reward. We further introduce a bridge function that recovers the conditional mean reward without explicitly modeling the MNAR mechanism, and estimate it via a min-max procedure to avoid double sampling. Building upon these identification results, we propose an Fitted-Q-Evaluation-style estimator that propagates the recovered rewards while allowing target policies to depend on past missingness indicators. Finally, we establish consistency and finite-sample error bounds for our OPE estimator, and show through experiments the strong performance of our method compared to existing methods on simulated and MIMIC-III Sepsis data.

13.
arXiv (CS.AI) 2026-06-15

Learning Coordinated Preference for Multi-Objective Multi-Agent Reinforcement Learning

arXiv:2606.14693v1 Announce Type: cross Abstract: Cooperative multi-objective multi-agent reinforcement learning (MOMARL) models team decision making under multiple, potentially conflicting objectives. In this setting, conflicts arise not only across objectives but also across agents with different observations, roles, and contributions. We propose Preference Coordinated Multi-agent Policy Optimization (PCMA), which learns coordinated agent-specific preferences to enable complementary trade-offs among agents. Theoretically, we formulate cooperative MOMARL as a team-optimal game and show that, under suitable conditions, preference diversity can induce team improvement through a first-order improvement decomposition. Experiments on multiple cooperative MOMA environments and a practical traffic-control scenario show that PCMA improves both performance and trade-off coordination.

14.
arXiv (CS.LG) 2026-06-18

PRISM: A 3D Probabilistic Neural Representation for Interpretable Shape Modeling

arXiv:2602.11467v2 Announce Type: replace Abstract: Understanding how anatomical shapes evolve in response to developmental covariates - and quantifying their spatially varying uncertainties - is critical in healthcare research. Existing approaches typically rely on global time-warping formulations that ignore spatially heterogeneous dynamics. We introduce PRISM, a novel framework that bridges implicit neural representations with uncertainty-aware statistical shape analysis. PRISM models the conditional distribution of shapes given covariates, providing spatially continuous estimates of both the population mean and covariate-dependent uncertainty at arbitrary locations. A key theoretical contribution is a closed-form Fisher Information metric that enables efficient, analytically tractable local temporal uncertainty quantification via automatic differentiation. Experiments on three synthetic datasets and one clinical dataset demonstrate PRISM's strong performance across diverse tasks - from modeling shape evolution to personalized shape prediction and anomaly detection - within a unified framework, while providing interpretable and clinically meaningful uncertainty estimates.

15.
arXiv (CS.AI) 2026-06-12

ReSum: Synergizing LLM Reasoning and Summarization with Reinforcement Learning

arXiv:2606.13316v1 Announce Type: new Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) is a central technique for improving long-horizon reasoning in Large Language Models (LLMs). However, existing RLVR methods often encourage unnecessarily long reasoning rollouts, which can degrade reasoning coherence and exhaust the available context budget. Existing approaches to long-context organization often depend on external mechanisms to organize rollouts, rather than enabling the model to manage its own reasoning trajectory. To address this limitation, we propose ReSum, a novel RLVR framework that enables LLMs to compress and organize their reasoning trajectories through self-summarization. Our pilot studies show that self-summarization stabilizes generation by lowering token-level entropy, and that introducing a ``summarization'' phrase can substantially mitigate errors propagated from an incorrect rollout prefix. Motivated by these findings, ReSum adopts a summarization-aware adaptive rollout mechanism that contrastively evaluates whether self-summarization benefits the ongoing reasoning process. Specifically, when the model spontaneously triggers self-summarization, ReSum masks the summarization phrase to create a contrastive branch; for non-summarization positions, it instead randomly injects the phrase to create a matched branch. We further design a summarization-aware advantage to enable finer-grained comparison between contrastive rollout trajectories. Extensive experiments show that ReSum improves performance at an average of 4\% while reducing rollout length by 18.6\%.

16.
arXiv (quant-ph) 2026-06-12

Reservoir-controlled electromagnetically induced gratings in a weakly driven two-level medium

arXiv:2606.13085v1 Announce Type: cross Abstract: We theoretically investigate the transmission and diffraction of a weak probe field from an electromagnetically induced grating formed in a weakly driven two-level medium coupled to engineered quantum reservoirs. Using a perturbative solution of the optical Bloch equations in the weak-driving regime, we analyze how normal-vacuum, thermal, and broadband squeezed-vacuum environments modify the probe susceptibility and consequently reshape both the spatial transmission function and the far-field diffraction patterns. We show that reservoir statistics have a pronounced impact on the diffraction response by altering the amplitude and phase of the induced grating. Thermal reservoirs enhance the transmission modulation and increase the intensity of the dominant diffraction orders, whereas squeezed-vacuum reservoirs generate strongly phase-sensitive modifications that selectively redistribute optical power among diffraction channels. We further demonstrate that the detuning between the squeezed reservoir and the driving field provides an efficient mechanism for controlling diffraction directionality, leading to substantial amplification of selected angular orders. In two-dimensional geometries, squeezed-vacuum correlations produce highly structured phase landscapes and strongly anisotropic diffraction patterns, enabling directional enhancement of specific diffraction channels while suppressing others. These results establish reservoir engineering as a versatile approach for controlling transmission, diffraction efficiency, and angular selectivity in minimal two-level systems, with potential applications in programmable photonic devices, beam steering, and quantum optical platforms.

17.
bioRxiv (Bioinfo) 2026-06-22

PhaseWY: A pipeline for haplotype phasing, sex chromosome identification and extraction of sex-limited sequences

Sex chromosomes are central to many ecological and evolutionary processes. Evidence has accumulated that sex chromosome systems vary extensively in age, turnover and transitions, motivating renewed efforts to study the diversity of sex chromosome systems across the tree of life. However, successful genomic detection of sex chromosomes depends on several factors, including the size and divergence time, background genetic diversity, and the number of sequenced females and males. In addition, technical challenges associated with sequencing and analysing the sex-limited Y/W chromosome remain. Here, we present PhaseWY, an automated Snakemake pipeline that uses whole-genome sequencing data from multiple female and male individuals to identify sex-chromosomal regions and extract the corresponding Y/W sequences. PhaseWY (i) detects sex differences in alignment depth, (ii) applies read-based and statistical haplotype phasing, (iii) identifies sex-linked regions using haplotype clustering, and (iv) subsets autosomal, X/Z- and Y/W-linked variants for downstream analyses. We applied PhaseWY to simulated data to benchmark factors influencing sex-linkage detection and successful extraction of Y/W-linked variants. To demonstrate its practical utility, we further applied PhaseWY to the neo-sex chromosome system in Alauda larks (Alaudidae) and performed a range of downstream analyses demonstrating the scope of applications of the PhaseWY output. We conclude that PhaseWY provides an easy-to-use and reproducible tool for population-genomic analyses in non-model organisms, with particular importance for advancing our understanding of sex-chromosome evolution.

18.
arXiv (CS.CV) 2026-06-11

TextHOI-3D: Text-to-3D Hand-Object Interaction via Discrete Multi-View Generation and Joint Mesh Optimization

Text-conditioned 3D generation has progressed rapidly for images and isolated objects, but producing a hand-object mesh remains challenging: the output must preserve language semantics, cross-view consistency, object geometry, articulated hand shape, and physically plausible contact. We present TextHOI-3D, a staged framework that uses generated multi-view observations as an explicit interface between text-conditioned visual generation and geometry-aware hand-object recovery. TextHOI-3D learns a compact VQ token space for fixed-camera hand-object observations, predicts multi-view visual tokens from text with a CLIP-conditioned visual autoregressive model, and recovers a unified hand-object mesh through prior initialization, multi-view joint optimization, and anti-penetration refinement. The design separates semantic generation from geometric recovery while keeping both stages connected by a discrete multi-view representation. On HO3D-derived evaluations, the multi-view setting reduces object CD from 17.26 mm to 4.92 mm and penetration volume from 5.3721 cm^3 to 0.2193 cm^3 compared with a single-view counterpart, while improving hand errors and surface F-scores. These results support multi-view visual tokens as an effective intermediate representation for text-driven 3D hand-object mesh creation.

19.
arXiv (CS.LG) 2026-06-24

AsyncOPD: How Stale Can On-Policy Distillation Be?

arXiv:2606.24143v1 Announce Type: new Abstract: On-policy distillation (OPD) trains a student on its own rollouts guided by teacher feedback and is becoming increasingly important for large language model (LLM) post-training. Like reinforcement learning (RL), however, OPD faces an on-policy systems bottleneck, as rollouts can dominate training time for reasoning workloads. Asynchronous training pipelines can alleviate this bottleneck by decoupling rollout generation from learner updates, but doing so introduces stale-policy data. While prior work has studied stale data in asynchronous RL, its effects in OPD remain underexplored. We present the first systematic study of staleness in asynchronous OPD, focusing on a practical setting where teacher feedback is implemented through local KL losses and full-vocabulary teacher logits are too expensive to store or transfer, necessitating finite teacher-score caches. We first show that KL direction changes the stale-data problem: teacher-weighted forward KL is more robust to stale rollouts, whereas student-weighted reverse KL is vulnerable. Second, for this vulnerable reverse-KL case, we study whether methods designed to stabilize asynchronous RL can mitigate OPD staleness. In our experiments, they do not improve over a simpler OPD-specific surrogate: recomputing the reverse-KL signal under the current student at learner time. Third, we analyze how finite teacher-score caches create a bias-variance tradeoff for sparse and sampled reverse-KL OPD estimators. This motivates multi-sample Monte Carlo (MC), which preserves MC correctability while reducing one-sample variance. Finally, we present and open-source AsyncOPD, a fully asynchronous OPD training pipeline built from these estimator choices. Experiments show that AsyncOPD improves training throughput by $1.6\times$ to $3.8\times$ over strict synchronous training while reaching comparable accuracy.

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

Beyond Defensive Reporting: Machine Learning for Active Anti-Money Laundering Control in Insurance

arXiv:2606.16663v1 Announce Type: new Abstract: Money laundering through insurance claims poses a threat to insurers both through fraudulent payouts and reputational and regulatory risk. Despite this, little research has examined how such laundering can be prevented. This paper examines whether machine learning can help insurers flag suspicious claims before payout, shifting the focus from passive reporting to active prevention. Using production data from a major Norwegian insurer, we train gradient-boosted decision tree models to detect claims later reported to authorities for suspected money laundering. Because fraud and laundering may share behavioural patterns, we also examine whether insurance fraud labels can serve as an auxiliary training signal. We compare different learning setups using the Budget-Weighted Capture Rate, a metric introduced in this paper to measure how many laundering cases are captured when only a small share of claims can be manually reviewed. The results show that incorporating fraud-related investigation labels substantially improves laundering detection. The best-performing model captures nearly two-thirds of laundering cases within the top-ranked 2 to 6 percent of claims selected for investigation. To our knowledge, this is the first empirical study of machine learning for money laundering detection in insurance claims.

21.
arXiv (CS.CL) 2026-06-18

Notation Matters: A Benchmark Study of Token-Optimized Formats in Agentic AI Systems

Large language models in Agentic AI systems consume tool schemas and execution results and emit tool invocations as structured data. The default language for that exchange, JSON, was designed for application-to-application interchange rather than token efficiency, so its structural elements impose substantial token overhead. Recent work proposes token-optimized alternatives such as TOON (Token-Oriented Object Notation) and TRON (Token Reduced Object Notation) as more compact replacements, but these formats have been evaluated only on isolated comprehension or generation tasks. Whether their token reductions hold inside end-to-end agentic loops therefore remains an open question. We evaluate TOON and TRON on four agentic benchmarks (BFCL, MCPToolBenchPP, MCP-Universe, StableToolBench) and five open-weight LLMs, decoupling input compression from output compression to measure comprehension and generation independently. TRON reduces tokens by up to 27% with accuracy within 14pp of the JSON baseline. TOON achieves up to 18% reduction at a similar 9pp accuracy cost, but additionally cascades on multi-turn parsing failures and collapses parallel tool-call output for most models. The code is available at: https://github.com/lkutschka/notation-matters

22.
arXiv (CS.CL) 2026-06-17

ConSA: Controllable Sparsity in Hybrid Attention via Learnable Allocation

Hybrid architectures combining full attention (FA) and sliding-window attention (SWA) are a promising paradigm for efficient LLM inference. However, existing methods typically rely on hand-crafted rules or simple post-hoc heuristics for FA/SWA allocation and offer limited analysis of the attention behaviors underlying these designs. We propose Controllable Sparsity in Hybrid Attention (ConSA), a framework that learns optimal FA/SWA assignment under a user-specified sparsity target. ConSA employs L0 regularization to learn binary masks selecting between FA and SWA for each attention unit, while an augmented Lagrangian constraint enforces the target sparsity at either layer or KV-head granularity. We evaluate ConSA on two LLMs at the 0.6B and 1.7B scales. Learned allocations consistently outperform rule-based baselines, with KV-head-wise allocation yielding clear gains over layer-wise allocation. The learned patterns place SWA in the bottom layers and concentrate FA into contiguous middle-layer blocks, diverging from evenly interleaved patterns in rule-based methods. This structure persists across model scales, sparsity levels, and allocation granularities, revealing a fine-grained spectrum of intrinsic attention behaviors that underlies the learned allocation.

23.
arXiv (CS.CV) 2026-06-15

Temporal Backtracking Search for Test-time Generative Video Reasoning

While test-time scaling has revolutionized reasoning in large language models, generative video reasoning remains bottlenecked by a single-shot paradigm. We demonstrate that searching over denoising steps cannot rescue logically flawed rollouts because spatial trajectories commit early in the diffusion process. Root-level Best-of-N (BoN) sampling is similarly inefficient: reasoning errors cluster early in the temporal axis, and resampling blindly discards verified upstream progress. To unlock effective test-time scaling for video models, we introduce Temporal Backtracking Search (TBS), which shifts the search space to the temporal axis. TBS transforms video generation into an iterative generate-verify-restart loop via three core mechanisms: (1) variable-K conditioning to resume generation from arbitrary clean prefixes; (2) temporal process verification to localize failures and extract valid restart anchors; and (3) prefix-based search to reallocate compute toward extending correct trajectories rather than root resampling. Across algorithmic, navigation, and robotics domains, TBS Pareto-dominates matched-budget BoN. In a strict out-of-distribution setting where one-shot generation collapses (0.7% for BoN), TBS achieves 22.7%, with every solved episode stemming from a restarted branch. Ultimately, TBS reveals that the local reasoning competence of video models far exceeds what single-shot rollouts indicate, providing a scalable test-time framework to unlock it.

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

FORT-Searcher: Synthesizing Shortcut-Resistant Search Tasks for Training Deep Search Agents

Training deep search agents requires verifiable questions whose answers remain unavailable until sufficient evidence has been acquired through search. Existing synthesis methods often increase apparent difficulty by enriching graph structures, but structural complexity alone does not guarantee realized search difficulty: the intended search process can collapse through a cheaper identifying route. We formalize this gap with a shortcut-aware difficulty framework and identify four actionable shortcut risks: evidence co-coverage, single-clue selectivity, exposed constants, and prior-knowledge binding. To diagnose their realized effects, we use trajectory signatures including solving cost, answer hit time, and prior-shortcut rate. Guided by this framework, we introduce FORT, a Framework of Shortcut-Resistant Training-Data Synthesis. FORT constructs shortcut-resistant training data by controlling shortcut risks across entity selection, evidence graph construction, question formulation, and adversarial refinement. Experiments show that FORT induces longer pre-answer search and fewer shortcut patterns than existing open-source deep search datasets. Using the resulting trajectories, we train FORT-Searcher with supervised fine-tuning (SFT) only, and it achieves the best overall performance among comparable-size open-source search agents on challenging deep search benchmarks. Relevant resources will be made available at https://github.com/RUCAIBox/FORT-Searcher.

25.
arXiv (CS.AI) 2026-06-15

Distributional Biases in Post-Training: A Markovian Analysis of Reasoning Trajectories

arXiv:2511.07368v3 Announce Type: replace-cross Abstract: Foundation models exhibit broad knowledge but limited task-specific reasoning, motivating post-training strategies such as RL with verifiable rewards (RLVR) and test-time scaling (TTS). While recent work highlights the role of exploration in improving pass@K, empirical evidence points to a paradox: RLVR and ORM/PRM typically reinforce existing paths rather than expanding the reasoning scope, raising the question of why exploration helps if no new patterns emerge. To reconcile this paradox, we adopt the perspective of Kim et al. (2025), viewing easy (e.g., simplifying a fraction) versus hard (e.g., discovering the some symmetry) reasoning steps as low versus high probability Markov transitions. In this tractable model, pretraining corresponds to tree-graph discovering, while post-training corresponds to CoT reweighting. We provably show that, both RLVR and ORM/PRM would favor heavily to several high-probability paths, and thereby forget rare-but-crucial CoTs. Building on this, we further prove that exploration strategies such as rejecting easy instances and KL regularization help preserve rare CoTs. Empirical simulations corroborate our theoretical results.