Explore the Frontier of Global Academia

01.

arXiv (quant-ph) 2026-06-16 DOI: arXiv:2606.15605

Dressed Floquet scars from protected zero modes in a Rydberg chain

Authors:

Saptadip Roy↗Bhaskar Mukherjee↗K. Sengupta↗Arnab Sen↗

arXiv:2606.15605v1 Announce Type: cross Abstract: In this Letter, we present an approximate analytic construction of two zero quasienergy quantum many-body scars in a periodically driven model of Rydberg atoms on a ring, which persist over a range of driving amplitudes and frequencies for finite sizes. An index theorem protects an exponentially large number (in system size) of exact zero energy modes of the Floquet Hamiltonian in this setting. Unlike most of these zero modes which continuously change with drive parameters, these two quantum many-body scars retain the memory of particular states. They can be expressed as {\it dressed versions} of two contrasting states, the Rydberg vacuum and a unitarily rotated variant of a volume-law scar [Ivanov and Motrunich, Phys. Rev. Lett. {\bf 134}, 050403 (2025)], respectively. We provide an analytic understanding of their existence using a Floquet perturbation theory and show their resilience beyond the perturbative regime using exact diagonalization in finite systems. Our study provides insight into the structure of protected zero modes in interacting Floquet settings.

Read & Discuss → View Source →

02.

arXiv (CS.LG) 2026-06-11 DOI: arXiv:2606.12282

PianoKontext: Expressive Performance Rendering from Deadpan Context

Authors:

Dmitrii Gavrilev↗

arXiv:2606.12282v1 Announce Type: cross Abstract: Expressive performance rendering (EPR) aims to generate realistic performances constrained on sequences of notes. However, flow matching audio editing models manipulate only synchronized music samples of the same duration, limiting their understanding of expressive timing. We introduce PianoKontext, a flow matching rendering model for classical piano music that generates variable-length performances in the latent space of a pretrained Music2Latent model. We synthesize MIDI scores into deadpan audio and employ Dynamic Time Warping (DTW) in the latent space to construct paired data for training. The aligned embeddings are concatenated in DiT blocks, allowing for a simple and effective learning of the dependencies between the score and performances. Audio samples are available at our demo page: https://realfolkcode.github.io/pianokontext_demo/.

Read & Discuss → View Source →

03.

arXiv (CS.AI) 2026-06-12 DOI: arXiv:2606.13262

From Verdict to Process: Agentic Reinforcement Learning for Multi-Stage Fact Verification

Authors:

Rongxin Yang↗Shenghong He↗Siyuan Zhu↗Chao Yu↗

arXiv:2606.13262v1 Announce Type: new Abstract: Recent approaches combining Large Language Models (LLMs) with retrieval-augmented reasoning have shown promise for automated fact verification. To process complex claims, these verification pipelines typically execute multi-stage workflows that coordinate tightly coupled modules, including claim decomposition, evidence gathering, and verdict prediction. However, existing methods optimize individual stages in isolation or rely on fixed heuristics, which limits adaptive coordination among stages and can lead to suboptimal outcomes. In this work, we propose ProFact, an agentic reinforcement learning framework for end-to-end optimization of multi-stage fact verification trajectories. ProFact trains a unified policy to coordinate claim decomposition, evidence seeking, answer generation, and verdict prediction. To address the sparse and delayed supervision provided by final veracity labels, ProFact introduces process-aware rewards that provide stage-level learning signals throughout the verification process. Empirical evaluation shows that ProFact consistently outperforms strong baselines in both verification performance and inference efficiency. These results highlight the effectiveness of process-aware trajectory optimization for multi-stage fact verification.

Read & Discuss → View Source →

04.

arXiv (quant-ph) 2026-06-17 DOI: arXiv:2606.18240

Impulse Decoding of Quantum LDPC Codes: Equivalence of Degeneracy and Code-Shortening

Authors:

Shobhit Bhatnagar↗Michele Pacenti↗Nithin Raveendran↗David Declercq↗Bane Vasi\'c↗

arXiv:2606.18240v1 Announce Type: new Abstract: Quantum error correction is essential for building scalable quantum computers. Within the stabilizer formalism, the Calderbank-Shor-Steane framework constructs quantum codes from pairs of classical linear codes. A distinctive feature in this setting is degeneracy, where multiple equivalent error estimates exist-a phenomenon that has no classical counterpart, and the lack of a meaningful classical coding-theoretic interpretation of which has remained a gap in the literature. In this paper, we demonstrate that degeneracy is closely related to the classical operation of shortening of a linear block code. Interestingly, the shortening here takes place at the decoder rather than at the encoder. Leveraging this insight, we present a parallel decoding scheme for quantum low-density parity-check codes, which we term impulse decoding, that significantly outperforms belief propagation with ordered statistics decoding, as well as several other existing techniques, under both code-capacity and circuit-level noise, with significantly lesser complexity. We then present another algorithm based on decoding of residual errors, which when combined with impulse decoding achieves further performance improvement under circuit-level noise.

Read & Discuss → View Source →

05.

arXiv (CS.AI) 2026-06-19 DOI: arXiv:2606.19630

AI4SE and SE4AI Exploration: A Decade Looking Back and Forward

Authors:

H. Sinan Bank↗Daniel R. Herber↗Thomas Bradley↗

arXiv:2606.19630v1 Announce Type: new Abstract: The March 2020 INCOSE INSIGHT special issue on AI and Systems Engineering (SE) became the most downloaded issue in the publication's history and launched a research community that now draws over 250 registrants to its annual workshop. In this article, we trace the progress in AI and SE across three phases (labeled here foundational, applied, and LLM inflection) based on the authors' reading of the field's core papers, and describe our opinions of where the community has converged and where critical gaps remain. Separately, a human-AI agreement literature review leveraging both human expertise and six AI models was performed to assess the relevance of 1,712 INCOSE INSIGHT articles and 889 SERC publications. The results identify five critical research gaps and offer guidance for practitioners navigating AI adoption, assurance, and workforce transformation in SE. We share the agreement data and the AI4SE/SE4AI Explorer web application so readers can compare their own relevance judgments with the human and AI raters.

Read & Discuss → View Source →

06.

arXiv (quant-ph) 2026-06-16 DOI: arXiv:2603.03998

Spectrally Corrected Polynomial Approximation for Quantum Singular Value Transformation

Authors:

Krishnan Suresh↗

arXiv:2603.03998v2 Announce Type: replace Abstract: Quantum Singular Value Transformation (QSVT) provides a unified framework for applying polynomial functions to the singular values of a block-encoded matrix. QSVT prepares a state proportional to $\bA^{-1}\bb$ with circuit depth $O(d\cdot\mathrm{polylog}(N))$, where $d$ is the polynomial degree of the $1/x$ approximation and $N$ is the size of $\bA$. Current polynomial approximation methods are over the continuous interval $[a,1]$, giving $d = O(\sqrt{\kap}\log(1/\varepsilon))$, and make no use of any properties of $\bA$. We observe here that QSVT solution accuracy depends only on the polynomial accuracy at the eigenvalues of $\bA$. When all $N$ eigenvalues are known exactly, a pure spectral polynomial $p_{S}$ can interpolate $1/x$ at these eigenvalues and achieve unit fidelity at reduced degree. But its practical applicability is limited. To address this, we propose a spectral correction that exploits prior knowledge of $K$ eigenvalues of $\bA$. Given any base polynomial $p_0$, such as Remez, of degree $d_0$, a $K\times K$ linear system enforces exact interpolation of $1/x$ only at these $K$ eigenvalues without increasing $d_0$. The spectrally corrected polynomial $p_{SC}$ preserves the continuous error profile between eigenvalues and inherits the parity of $p_0$. QSVT experiments on the 1D Poisson equation demonstrate up to a $5\times$ reduction in circuit depth relative to the base polynomial, at unit fidelity and improved compliance error. The correction is agnostic to the choice of base polynomial and robust to eigenvalue perturbations up to $10\%$ relative error. Extension to the 2D Poisson equation suggests that correcting a small fraction of the spectrum may suffice to achieve fidelity above $0.999$.

Read & Discuss → View Source →

07.

arXiv (CS.LG) 2026-06-19 DOI: arXiv:2605.00457

Utility-Aware DRL-Based TXOP Adaptation for NR-U and Wi-Fi Coexistence Networks

Authors:

Po-Heng Chou↗Yi-Fang Yu↗Shou-Yu Chen↗Chiapin Wang↗

arXiv:2605.00457v4 Announce Type: replace-cross Abstract: The coexistence of NR-U and Wi-Fi in the unlicensed spectrum introduces a challenging resource management problem, where heterogeneous channel access mechanisms can lead to unbalanced spectrum utilization and severe Wi-Fi performance degradation. To address this issue, this paper proposes a utility-aware deep reinforcement learning (DRL) framework for adaptive transmission opportunity (TXOP) control in NR-U/Wi-Fi coexistence networks. The coexistence process is formulated as a Markov decision process (MDP), in which the NR-U TXOP duration is treated as a controllable variable for regulating post-access channel occupancy. A deep Q-network (DQN) is then employed to learn adaptive TXOP control policies through online interaction with the coexistence environment. A key feature of the proposed framework is the integration of a configurable reward and criterion design, which enables explicit control of the fairness-efficiency-utility tradeoff. Three operating policies are developed, namely absolute fairness, moderate fairness, and utility-oriented moderate fairness, to characterize different coexistence operating points. Simulation results show that the proposed framework achieves a Jain fairness index above 0.9 under strict fairness control. Compared with the absolute fairness policy, the moderate fairness policy improves aggregate throughput by 68.22%, while the utility-oriented policy achieves a 177.6% improvement under the adopted utility evaluation metric. These results demonstrate that the proposed utility-aware DRL framework provides an effective and flexible solution for adaptive TXOP control and tradeoff management in heterogeneous unlicensed coexistence networks.

Read & Discuss → View Source →

08.

arXiv (CS.LG) 2026-06-15 DOI: arXiv:2606.14388

A Low-Rank Subspace Analysis of LLM Interventions

Authors:

Angira Sharma↗Christian Schroeder de Witt↗Philip Torr↗Anisoara Calinescu↗Jialin Yu↗

arXiv:2606.14388v1 Announce Type: new Abstract: Interventions designed to modify a particular behavior in LLMs, such as refusal or sycophancy, often produce unintended changes in other behaviors. This lack of targeted control makes it difficult to design and implement reliable safety controls. To understand these side-effects, we introduce a diagnostic framework for analyzing interacting behaviors in LLMs. We model behaviors as low-rank subspaces in activation space, and study how interventions influence across behaviors. Across multiple instruction-tuned models (7B-70B) and across refusal, jailbreak, and sycophancy settings, we find that different behaviors share internal representations, and intervening on one behavior alters others in asymmetric ways. Some behaviors act as upstream control points whose interventions propagate broadly across other behaviors, while others remain more isolated. We relate these effects to two geometric quantities: (i) the overlap between behavior subspaces, measured as the average squared cosine of principal angles, and (ii) the angle between each behavior subspace and the decision subspace (capturing the model's final decision e.g., refuse vs. comply). Empirically, intervention effects on other behaviors tend to be larger for behavior pairs with higher subspace overlap, and for source behaviors whose subspaces lie closer (smaller angle) to the decision subspace. These findings highlight a challenge for targeted behavior control: behaviors are difficult to modify independently, as interventions can propagate through shared representations and asymmetric interactions.

Read & Discuss → View Source →

09.

arXiv (CS.LG) 2026-06-19 DOI: arXiv:2606.20538

Multi-Task Bayesian In-Context Learning

Authors:

Qingyang Zhu↗Eric Karl Oermann↗Kyunghyun Cho↗

arXiv:2606.20538v1 Announce Type: new Abstract: Bayesian predictive inference provides a principled framework for uncertainty quantification, data efficiency, and robust generalization. However, exact inference is often intractable, and scalable approximations may remain computationally expensive or require restrictive modeling assumptions that degrade predictive performance. Prior-Data Fitted and in-context models have recently emerged as an amortized alternative by learning to map datasets directly to predictive distributions, but existing approaches are tightly coupled to the support of the training prior and lack explicit mechanisms for adapting to new priors at test time, resulting in limited robustness under distribution shift. We introduce a multi-task in-context learning framework for amortized hierarchical Bayesian predictive inference that explicitly represents prior information as a prefix of in-context datasets. A transformer trained on sequences of prior and target tasks learns to adapt its predictions across families of priors. On a suite of evaluations with increasing difficulty, including out-of-meta-distribution priors and priors with high-dimensional latent structures, our method matches oracle Bayesian predictors while being orders of magnitude faster. We further demonstrate its practical relevance on a real-world spatiotemporal temperature prediction benchmark. Code is available at https://github.com/martianmartina/multi-task-bayesian-icl/.

Read & Discuss → View Source →

10.

arXiv (CS.CV) 2026-06-16 DOI: arXiv:2606.15992

Multi-Task Tennis Stroke Biomechanics Analysis Using MediaPipe Pose

Authors:

Jigyashman Hazarika↗

We built a multi-task pipeline for tennis stroke biomechanics from plain RGB video. On top of pose-based stroke recognition, it adds two new tasks, predicting shot direction and grading posture quality, plus a rule-based feedback layer that suggests coaching tips. Strokes are found automatically using a weighted joint velocity score, s(t) = 0.5 v_wrist + 0.3 m_elbow + 0.2 m_shoulder, removing the need for manual annotation. Pose comes from MediaPipe Pose Landmarker (33 landmarks, metric world coordinates), with each stroke turned into a 30-frame by 39-feature sequence for TennisTransformerGPU, a compact 564,103-parameter transformer (4 layers, 4 heads, d=128) with three parallel output heads. Trained on 1,281 labeled strokes from 7 pros and 1 amateur across 11 videos, it hits 83.7% stroke-type accuracy, 61.9% on direction, and 62.6% on posture under a random 80/20 split. The interesting test is cross-player: train on pros, evaluate on the amateur. Stroke type barely budges, 82.9%, a 0.8% drop. Direction prediction does not transfer; it just falls back to the majority class. An ablation shows why world coordinates matter so much here: switching to image-space landmarks tanks cross-player stroke-type accuracy from 83% to 47% and direction from 68% to 21%. Everything runs on Kaggle's free T4 GPU tier and is fully reproducible.

Read & Discuss → View Source →

11.

arXiv (CS.LG) 2026-06-12 DOI: arXiv:2508.14143

The Urysohn Machine: A Metric-Topological Model of Computation

Authors:

Xin Li↗

arXiv:2508.14143v2 Announce Type: replace Abstract: We introduce the Urysohn Machine, an effective model of classification-oriented computation in which metric separation, frontier structure, and contraction are explicit parts of the computational state. Its basic object is a Urysohn Triple: a support region, a target partition, and a separating classifier stored in a reusable Metric Library. The topological foundation is a constructive Urysohn Realization theorem for finite simplicial settings. It builds separators from dyadic ladders of nested polyhedral regions and equips their frontiers with a chain-level calculus: frontiers are cycles, and shells between levels have boundaries given by differences of frontiers. This construction yields two related complexity measures: decision-boundary width, the geometric measure of a single classifier's boundary, and Urysohn width, the total frontier mass represented by a library or realization. We prove an Amortized Separation Theorem showing that approximating a boundary of width to accuracy requires a number of simple basis triples proportional to boundary width and inversely proportional to resolution, under explicit boundary-footprint assumptions. We also introduce a contrastive separation operator whose graph-cut functional consistently estimates decision-boundary width from sampled metric data, while its Laplacian spectrum certifies class-component structure and conductance. Finally, we analyze the dynamic Urysohn ladder and prove four guarantees: separability under quotient collapse, stability of committed frontiers, bounded capacity under contraction, and scalability with quotient distance. Together, these results give a metric-topological account of classification complexity, amortized inference, and compositional reuse that preserves classical computability while exposing geometric structure hidden by purely symbolic descriptions.

Read & Discuss → View Source →

12.

arXiv (CS.AI) 2026-06-12 DOI: arXiv:2605.16430

A Theory of Training Profit-Optimal LLMs

Authors:

Sophie Hao↗William Merrill↗

arXiv:2605.16430v3 Announce Type: replace-cross Abstract: Scaling LLMs requires tremendous computational resources, and recent advances in AI have gone hand in hand with massive amounts of capital expenditure. While it is established that scaling up LLMs reliably increases model quality (quantified in terms of loss or downstream evaluations), it is unclear how these quality improvements translate to potential revenue, and whether revenue increases would offset costs of larger-scale training and inference. In this work, we develop an economic model for characterizing the rational behavior of an LLM training firm by combining scaling laws with microeconomic theory. Under our model of firm behavior, LLM quality can be increased with more parameters and training tokens, leading to more potential adoption by consumers, who each have a quality threshold for using the LLM. On the other hand, additional parameters and training tokens both incur additional costs. We analyze the profit maximization problem for this model under compute-bound and data-bound regimes. In the compute-bound regime, optimal model size and token budget track hardware efficiency $E$ (FLOPs/\$) at a near-linear rate; total training cost then scales sub-quadratically in $E$. Data efficiency improvements incentivize larger models and training expenditure. When we are limited to $D$ data, profit-optimal training expenditure scales as $D^2/E$, i.e, increase with data and decreases with hardware efficiency (as well as data efficiency). Finally, we analyze practical trends in training expenditure: current trends are consistent with our most permissive model variants in the compute-bound regime, but are not profit-optimal in the data-bound regime or assuming hardware advances will stall. Overall, our results provide a theory of profit-optimal LLM training, providing a foundation for engaging critically with industry statements and supporting long-term economic decision making.

Read & Discuss → View Source →

13.

arXiv (CS.CL) 2026-06-19 DOI: arXiv:2606.19750

Manifold Bandits: Bayesian Curriculum Learning over the Latent Geometry of Large Language Models

Authors:

Darrien McKenzie↗Nicklas Hansen↗Xiaolong Wang↗

Reinforcement learning (RL) is a central approach for improving reasoning capabilities in large language models (LLMs), where training efficiency depends critically on how problems are sampled during optimization. Existing adaptive curriculum learning methods typically prioritize prompts of intermediate difficulty, treating problem selection as a standard bandit problem with independent arms and overlooking the structured, heterogeneous nature of the task space. In this work, we frame problem sampling as a manifold-structured bandit problem with endogenous non-stationarity: problems are related through the model's latent representation space, and sampling decisions can steer how learning signals evolve across that space. To operationalize this perspective, we introduce Bayesian Manifold Curriculum (BMC), a structure-aware framework that organizes problems into a hierarchical task tree and applies Bayesian learning to guide sampling. Empirically, we find that different sampling strategies induce non-trivial tradeoffs between productivity (learning signal), diversity (coverage of the task manifold), and utility (evaluation relevance). These results show that prioritizing difficulty alone is insufficient for strong downstream performance, highlighting the importance of incorporating structure and type-awareness into problem sampling.

Read & Discuss → View Source →

14.

arXiv (CS.LG) 2026-06-18 DOI: arXiv:2606.18525

Hierarchical Attention via Domain Decomposition

Authors:

Stephan K\"ohler↗Oliver Rheinbach↗

arXiv:2606.18525v1 Announce Type: new Abstract: We propose a hierarchical attention mechanism based on two-level overlapping Schwarz domain decomposition. The method is motivated by the observation that two-level Schwarz domain decomposition methods combine local subdomain corrections with a coarse level that communicates global, long-range information. We test its usefulness in the context of finite-dimensional operator learning using a simple, one-dimensional diffusion problem with homogeneous Dirichlet boundary conditions. Although elementary, this problem provides a controlled sequence-to-sequence setting in which the exact nonlocal solution operator is known. After discretization, learning the solution operator amounts to approximating the inverse of a symmetric positive definite matrix. As a baseline, we use a global softmax-free low-rank attention operator of the form $QK^T$. The proposed construction replaces this dense global factorization by a two-level additive structure: local low-rank attention blocks on overlapping subdomains are combined with a coarse attention block. The resulting operator has the form $$M_{\theta}^{-1} = \Phi Q_0 K_0^T \Phi^T + \sum_{i=1}^{N} R_i^T D_i^{1/2} Q_i K_i^T D_i^{1/2} R_i.$$ Here $R_i$ restricts to an overlapping subdomain, $D_i$ is a partition-of-unity weight, and $\Phi$ is a coarse interpolation (or prolongation) matrix. Numerical experiments for synthetic Fourier right-hand sides indicate that the domain-decomposition attention operator is able to train faster and can give more accurate approximations than a global low-rank attention baseline while using significantly fewer parameters.

Read & Discuss → View Source →

15.

arXiv (CS.CL) 2026-06-15 DOI: arXiv:2606.14516

Every Eval Ever: A Unifying Schema and Community Repository for AI Evaluation Results

Authors:

Jan Batzner↗Sree Harsha Nelaturu↗Anastassia Kornilova↗Jon Crall↗Tommaso Cerruti↗Yanan Long↗Yifan Mai↗Sanchit Ahuja↗Asaf Yehudai↗Marek \v{S}uppa↗John P. Lalor↗Oluwagbemike Olowe↗…

AI evaluations are widely used for testing and understanding progress. However, the diverse evaluators bring with them inconsistencies that challenge analysis and comparison. First, results are saved in incompatible formats, scattered across leaderboards, papers, blog posts, evaluation harness logs, and custom repositories. Second, results are created by different evaluation frameworks, which produce divergent scores for nominally identical evaluations and record metadata inconsistently, hindering comparison, cross-community evaluation science, cost reduction, and reuse. We introduce Every Eval Ever, the first shared schema and community-crowdsourced repository for AI evaluation results. The schema standardizes how evaluations are represented in a unified, single JSON document. It is source-agnostic by design, ingesting results from evaluation harnesses and papers alike, and optionally stores per-instance outputs for fine-grained analysis. We contribute: (i) a community-governed metadata schema with a companion instance-level schema, the first standardization effort of its kind; (ii) automatic converters from popular formats, evaluation harnesses, and leaderboards to the unified schema; and (iii) a crowdsourced community database hosted on Hugging Face, currently spanning to date 22,235 models, 2,273 unique benchmarks, and 31 evaluation formats.

Read & Discuss → View Source →

16.

arXiv (CS.AI) 2026-06-19 DOI: arXiv:2606.19579

FlowFake: Liquid Networks for Audio Deepfake Detection

Authors:

Shivaay Dhondiyal↗Divyansh Sharma↗Dinesh Kumar Vishwakarma↗

arXiv:2606.19579v1 Announce Type: cross Abstract: Audio deepfakes generated by neural text-to-speech and voice-cloning systems threaten speaker verification and public discourse at scale. The core challenge is cross-dataset generalization: detectors trained on one synthesis pipeline collapse on unseen forgeries. We argue that this failure is primarily because of structural synthetic speech artifacts which are multi-timescale trajectory anomalies. Though every existing detector aggregates a fixed-window frame statistics, this misaligns the architecture with the signal. We propose FlowFake, a Liquid Time-Constant (LTC) architecture whose hidden state evolves via a learned ODE, with per-neuron adaptive time constants simultaneously resolving spectral (10ms) and prosodic (2s) cues. At only 34K parameters FlowFake achieves formal BIBO stability and O(dt^4) integration error. On a four-dataset cross domain benchmark (ASVspoof2019-LA, FakeOrReal, InTheWild, MLAAD), FlowFake reaches 75.29% on ASVspoof2019 trained only on FakeOrReal and 79.97% trained only on MLAAD. It outperforms RawGAT-ST and Whisper-DF on every evaluated pair and matching SSL Wav2vec2 (300x larger) at 0.01% of its parameter count. The source code is available on : https://github.com/GhostRider2023/FlowFake

Read & Discuss → View Source →

17.

arXiv (CS.AI) 2026-06-19 DOI: arXiv:2606.19812

Human-on-the-Loop Orchestration for AI-Assisted Legal Discovery

Authors:

Anushree Sinha↗Srivaths Ranganathan↗Abhishek Dharmaratnakar↗Debanshu Das↗

arXiv:2606.19812v1 Announce Type: new Abstract: Autonomous Large Language Model (LLM) agents are increasingly deployed in electronic discovery (e-discovery), where compounding errors across multi-step reasoning chains can constitute legal malpractice. Unlike single-turn retrieval, agentic workflows operating over privileged document corpora exhibit a class of failure we term "trajectory collapse": an early misclassification silently propagates, rendering an entire privilege review invalid. This paper makes three contributions. First, we propose a structured taxonomy of agentic failures in legal information retrieval, organized by functional stage. Second, we introduce a four-layer verification architecture – spanning planning, reasoning, execution, and uncertainty quantification – designed to intercept these failures before they compound. Third, we present a preliminary simulation study on a synthetic e-discovery corpus that demonstrates how mandatory Human-on-the-Loop (HOTL) escalation thresholds reduce privilege-waiver risk relative to fully autonomous baselines. Our results suggest that calibrated uncertainty thresholds can reduce privilege-waiver risk by up to 61% versus fully autonomous deployment, while routing fewer than one quarter of documents to attorney review.

Read & Discuss → View Source →

18.

arXiv (CS.CL) 2026-06-16 DOI: arXiv:2606.17029

DEEPRUBRIC: Evidence-Tree Rubric Supervision for Efficient Reinforcement Learning of Deep Research Agents

Authors:

Minghang Zhu↗Chuyang Wei↗Junhao Xu↗Yilin Cheng↗Zhumin Chen↗Jiyan He↗

Deep research agents synthesize long-form reports by searching and reasoning over retrieved evidence. Reinforcement learning with rubric-based rewards improves these agents by optimizing them against checkable criteria that translate report quality into reward signals, but its efficiency depends on whether those criteria reliably capture the task scope and evidence needs. Most existing studies ask an LLM to generate rubrics for a given query, but when the model fails to infer the underlying information needs, the generated rubrics may be incomplete and reduce RL efficiency. To obtain more reliable query–rubric supervision, we introduce DeepRubric, a data construction framework that reverses this process: instead of inferring evaluation criteria for a given query, it first determines what an evidence-backed report should be evaluated on and then synthesizes aligned query–rubric pairs from those evaluation targets. Starting from a sampled seed topic, DeepRubric builds an evidence tree by recursively expanding evidence-backed sub-questions, whose leaves serve as atomic and verifiable evaluation targets. It then uses the evidence tree to synthesize the training query and rubrics, ensuring that the reward evaluates exactly the information requested by the query. Using DeepRubric, we construct 9K query–rubric supervision examples and train DeepRubric-8B with rubric-based GRPO, achieving comparable performance to prior open state-of-the-art deep research models across three benchmarks with roughly 13x fewer RL GPU-hours.

Read & Discuss → View Source →

19.

arXiv (CS.CV) 2026-06-11 DOI: arXiv:2606.11792

MultiToP: Learning to Patch Visual Tokens to Mitigate Hallucinations in Video Large Multimodal Models

Authors:

Yuansheng Gao↗Wenbin Xing↗Jiahao Yuan↗Kaiwen Zhou↗Han Bao↗Zonghui Wang↗Wenzhi Chen↗

Video Large Multimodal Models have achieved remarkable progress in video understanding, yet they remain prone to hallucinations, where generated responses are not faithfully supported by the input video. In this paper, we propose MultiToP, a multimodal-context-aware visual token patching framework that mitigates hallucinations by refining unreliable visual tokens before language generation. MultiToP introduces a lightweight Visual Token Patcher to predict token-level replacement distributions and selectively substitute unreliable visual tokens with a dynamic global patch token. To train the patcher effectively, we further propose information-guided rank calibration, which uses answer-conditioned frame-level information cues derived from the backbone to guide token replacement. Combined with ground-truth answer supervision and sparsity regularization, MultiToP enables localized visual evidence refinement without modifying the original model. Extensive experiments demonstrate that MultiToP effectively reduces hallucinations on Vript-HAL with negligible inference overhead, improving the F1 scores of Qwen3-VL-4B-Instruct by 50.60% over the vanilla model. Meanwhile, MultiToP preserves general video understanding ability, yielding an 18.58% relative accuracy gain on ActivityNet-QA for Video-LLaVA-7B.

Read & Discuss → View Source →

20.

arXiv (CS.CL) 2026-06-11 DOI: arXiv:2606.11502

When Roleplaying, Do Models Believe What They Say?

Authors:

Benjamin Sturgeon↗David Africa↗Sid Black↗

Language models can state that "the Earth orbits the Sun" and, when role-playing Aristotle, assert the opposite. Recent work argues that persona adoption is fundamental to how language models operate, with models constantly selecting the most appropriate persona for a given context. Does such role-playing merely change the model's outputs, or does it also affect what the model internally represents as truthful? We study this question with linear truth probes, applying them to LLMs role-playing historical personas whose likely beliefs differ from modern consensus. For each persona, we compare false claims the persona would likely have endorsed (*era-believed*) with topic-matched false claims they would not have endorsed (*era-false*). Across prompting, in-context learning, and supervised fine-tuning, persona induction suppresses era-believed statements less than equally false alternatives, yet they remain classified as false overall. Role-play therefore shifts what these models say more than what they internally represent as true. We contrast this with models trained on harmful advice that exhibit Emergent Misalignment (EM). Across three model families (Qwen 2.5 14B, Qwen 3 8B, and Llama 3.3 70B), their false claims move substantially toward the true region of probe space, are defended under challenge roughly half the time versus about a sixth for role-play, and are used in downstream reasoning. Role-play and Emergent Misalignment thus are points on a spectrum of belief internalization, where role-play changes what a model says with little representational change, while Emergent Misalignment shifts the internal representation of false claims without fully marking them as true.

Read & Discuss → View Source →

21.

arXiv (CS.LG) 2026-06-11 DOI: arXiv:2606.11982

PAWS: Preference Learning with Advantage-Weighted Segments

Authors:

Aleksandar Taranovic↗Onur Celik↗Niklas Freymuth↗Ge Li↗Serge Thilges↗Huy Le↗Tai Hoang↗Rania Rayyes↗Gerhard Neumann↗

arXiv:2606.11982v1 Announce Type: new Abstract: Preference-based reinforcement learning (PbRL) learns policies from human trajectory-level comparisons, avoiding explicit reward design and expert demonstrations. Existing methods typically train utility functions on trajectory or segment-level preferences while relying on per-step utility estimates during policy optimization. This training and inference mismatch induces a distribution shift that severely degrades temporal credit assignment and limits policy learning. We analyze this issue and propose PAWS, a segment-based preference learning method that performs policy updates directly using segment-level advantage functions. By aligning utility training with policy optimization, PAWS preserves trajectory-level preference information and avoids unreliable per-step learning signals. Experiments on simulated robotic manipulation and locomotion tasks demonstrate that PAWS consistently outperforms existing PbRL approaches, highlighting the importance of distribution-consistent preference learning.

Read & Discuss → View Source →

22.

arXiv (CS.AI) 2026-06-16 DOI: arXiv:2606.11692

Evaluation of Alternative-Based Information Systems for Deliberative Polling using an Agentic Simulator

Authors:

Rwaida Alssadi↗Khulud Alawaji↗Balaji Kasula↗Muntaser Syed↗Badria Alfurhood↗Markus Zanker↗Marius Silaghi↗

arXiv:2606.11692v1 Announce Type: cross Abstract: Deliberative polling promises to improve collective decision-making by exposing shareholders to a broad range of arguments before they vote. Yet ensuring that every voter encounters a representative sample of the reason space, the coverage problem, remains an open challenge, particularly at scale and in adversarial or strategically motivated electorates. This paper introduces a way of evaluating solutions using the LLM-based Agentic Bipolar Argumentation Simulator, grounded in a framework which formalises a poll as a six-tuple of endorsing and opposing justifications, attack and enhance relations, and shareholder- and relation-weights. ABAS simulates N autonomous shareholder agents, each assigned a latent opinion according to desired distributions in [-1, 1], who sequentially vote, choose or author justifications, and optionally submit argumentation-graph links. The simulator implements recommendations that rank existing justifications by their observable endorsement mass. It evaluates the mechanism's success by coverage, namely the fraction of the corpus reason-tag set represented in the K recommendations presented to each shareholder, as a solution to the NP-hard Subsuming Justification Problem. Reported experiments characterise how creativity rate (pown), recommendation size (K), argumentation density (plinks), and population size (N) affect coverage and corpus diversity. In an authenticated electorate where Sybil attacks are impossible and only the relation graph is gameable, we stress-test the scoring with coordinated strategic voting attacks: a tag-flood attack collapses coverage, while author-count relation weighting through a reversed-PageRank rule resists the flood markedly better than uniform weights.

Read & Discuss → View Source →

23.

arXiv (CS.AI) 2026-06-15 DOI: arXiv:2606.14357

No Accidental Software Agent First Canonical Code for Human Code Entropy Reduction and 30 to 500 times Lower Frontier Model Requirements

Authors:

Jepson Taylor↗

arXiv:2606.14357v1 Announce Type: cross Abstract: Frontier coding models may spend substantial capacity learning not only program behavior, but also accidental entropy in human repositories. Such repositories contain valuable signals: tests, incidents, migrations, edge cases, product judgment, and operational history. These signals are entangled with framework churn, naming drift, generated-source ambiguity, dependency rituals, CI dialects, weak proof routes, and human-oriented review customs. We propose agent-first canonical code, a proof-carrying substrate that rewrites routine product software into canonical behavior profiles, typed change algebra, proof lanes, constrained edit grammars, semantic patch cells, runtime negative memory, and proof-carrying change objects. The core hypothesis is that quotienting software by behavior equivalence under a declared oracle can collapse equivalent encodings into governed representatives with explicit evidence and proof obligations. The endpoint is amortized cost per verified correct change, including source, context, reasoning, tools, verification, security, provenance, review, failed loops, defects, and foundry cost under a common oracle. Reported reduction bands are hypotheses, not measured frontier results. The proposed limit is a No-Accident Horizon: removable accident decreases until residual novelty, evidence, governance, risk, and future optionality dominate. For supported routine-product distributions, this gives a defensible planning target near 100-fold all-in cost reduction, not a guarantee for all software. Preliminary QLoRA experiments on Qwen2.5-Coder-14B show that 64,088 canonical trajectories are learnable and suppress tested forbidden-language markers, but do not establish behavior preservation, scaling economics, or verified-change cost. The contribution is a falsifiable program centered on minimum functional description length and verified-change cost.

Read & Discuss → View Source →

24.

arXiv (CS.CV) 2026-06-11 DOI: arXiv:2606.11889

Task-Aligned Stability Analysis of Vision-Language Models for Autonomous Driving Hazard Detection

Authors:

Everett Richards↗

Vision-language models (VLMs) are increasingly used for scene understanding in autonomous driving, but robustness analysis often relies on task-agnostic embedding stability alone. We study whether corruption-induced embedding drift predicts changes in a task-aligned hazard score derived from CLIP image-text similarities. Using controlled corruptions on BDD100K road scenes, we compare embedding drift against margin drift, defined as the change in hazard score under perturbation. The relationship is highly corruption-dependent: some families exhibit strong coupling between representation drift and decision drift, while others induce hazardous decision instability despite relatively modest embedding change. Furthermore, corruption families differ in failure direction: most suppress hazard detections via false negatives, while occlusion instead triggers false alarms, suggesting that benchmark design should account for asymmetric failure modes, not just overall instability rates. These results suggest that robustness benchmarks should include task-aligned stability measures in addition to embedding-level perturbation statistics.

Read & Discuss → View Source →

25.

medRxiv (Medicine) 2026-06-15 DOI: HASH:a48ce293a7fd4e190e47329e4e2336b5

Differential DNA Methylation and Delirium After Anesthesia and Surgery

Authors:

Hogan↗Berger↗Kolstad↗Madrid↗Hsia↗Wright↗Devinney↗Smith↗Aisch↗

Background: DNA methylation is an epigenetic modification that regulates gene expression in response to environmental exposures. We measured differential DNA methylation levels in blood before after general anesthesia and surgery in participants with and without postoperative delirium (POD) and postoperative neurocognitive disorder (PNCD). Methods: Blood sampling, delirium assessment and cognitive testing were prospectively performed at baseline before non-cardiac, non-neurologic surgery, and at 24 hours (24h) and 6 weeks (6wk) thereafter in 94 participants comprising 13 with POD and 81 without POD, and 40 with PNCD and 54 without PNCD 6wk after surgery who were matched for age and sex in the INTUIT and MADCO cohorts. DNA methylation was assessed using the Illumina Infinium MethylationEPIC Beadchip. Results: 132 differentially methylated positions (DMPs) annotated to 198 differentially methylated genes (DMGs) were identified in 94 participants 24h after surgery compared to baseline with a local false discovery rate (LFDR)

Read & Discuss → View Source →