Explore the Frontier of Global Academia

01.

arXiv (CS.CL) 2026-06-12 DOI: arXiv:2606.12881

Direct Preference Optimization for Chatbot Fine-Tuning: An Empirical Study

Authors:

Yvonne Qiu↗Dezhi Yu↗ShuoJia Fu↗

We present an approach to fine-tuning large language models using Direct Preference Optimization (DPO), a reinforcement learning technique. Our experimental results demonstrate that DPO simplifies the training pipeline, improves computational efficiency, and achieves competitive performance. The evaluation using BLEU, ROUGE, and cosine similarity metrics indicates effective learning and convergence, though further investigation is needed to address observed training instability.

Read & Discuss → View Source →

02.

arXiv (CS.LG) 2026-06-17 DOI: arXiv:2502.18049

Recursive Learning Without Collapse: A Weighting-Based Stabilization Framework

Authors:

Hengzhi He↗Shirong Xu↗Guang Cheng↗

arXiv:2502.18049v5 Announce Type: replace-cross Abstract: Recent studies identified an intriguing phenomenon in recursive generative model training known as model collapse, where models trained on data generated by previous models exhibit severe performance degradation. Addressing this issue and developing more effective training strategies have become central challenges in generative model research. In this paper, we investigate this phenomenon within a novel framework, where generative models are iteratively trained on a combination of newly collected real data and synthetic data from the previous training step. To develop an optimal training strategy for integrating real and synthetic data, we evaluate the performance of a weighted training scheme in various scenarios, including Gaussian distribution estimation, generalized linear models, and nonparametric estimation. We theoretically characterize the impact of the mixing proportion and weighting scheme of synthetic data on the final model's performance. Our key finding is that, across different settings, the optimal weighting scheme under different proportions of synthetic data asymptotically follows a unified expression, revealing a fundamental trade-off between leveraging synthetic data and model performance. In some cases, the optimal weight assigned to real data corresponds to the reciprocal of the golden ratio. Finally, we validate our theoretical results on extensive simulated datasets and a real tabular dataset.

Read & Discuss → View Source →

03.

arXiv (CS.CL) 2026-06-12 DOI: arXiv:2606.12754

LLMs Can Better Capture Human Judgments–With the Right Prompts

Authors:

Danica Dillion↗Chen Cecilia Liu↗Baihui Wang↗Daniele Barolo↗Tanmay Rajore↗Niket Tandon↗Pranathi Ravikumar↗Kurt Gray↗

Are large language models (LLMs) bad at capturing human judgment? Two commonly stated limitations are that LLMs fail to capture full distributions of responses, and that their judgments are unstable across wording variations. We demonstrate simple prompting strategies that mitigate these limitations. Across two datasets–a U.S.-representative set of 144 moral scenarios and 38 moral beliefs from the International Social Survey Programme's Family and Changing Gender Roles module covering 32 countries–we show how simple elicitation techniques help improve AI-human alignment. First, prompting models to report standard deviations and response proportions recovers the full range of human responses better than common strategies. Second, ensuring scenarios are clear to human participants–as reflected in human confusion ratings–boosts model alignment, and LLMs can track human confusion ratings. At the same time, we find that LLMs' estimates of their own error are poorly calibrated, though they can predict human variability relatively well. These results suggest that asking better questions to LLMs can yield better answers.

Read & Discuss → View Source →

04.

arXiv (CS.CL) 2026-06-11 DOI: arXiv:2602.03141

Short Chains, Deep Thoughts: Balancing Reasoning Efficiency and Intra-Segment Capability via Split-Merge Optimization

Authors:

Runquan Gui↗Jie Wang↗Zhihai Wang↗Chi Ma↗Jianye Hao↗Feng Wu↗

While Large Reasoning Models (LRMs) have demonstrated impressive capabilities in solving complex tasks through the generation of long reasoning chains, this reliance on verbose generation results in significant latency and computational overhead. To address these challenges, we propose CoSMo (Consistency-Guided Split-Merge Optimization), a framework designed to eliminate structural redundancy rather than indiscriminately restricting token volume. Specifically, CoSMo utilizes a split-merge algorithm that dynamically refines reasoning chains by merging redundant segments and splitting logical gaps to ensure coherence. We then employ structure-aligned reinforcement learning with a novel segment-level budget to supervise the model in maintaining efficient reasoning structures throughout training. Extensive experiments across multiple benchmarks and backbones demonstrate that CoSMo achieves superior performance, improving accuracy by 3.3 points while reducing segment usage by 28.7\% on average compared to reasoning efficiency baselines.

Read & Discuss → View Source →

05.

arXiv (CS.CV) 2026-06-16 DOI: arXiv:2606.00435

Detect Before You Leap: Mirage Detection in Vision-Language Models

Authors:

Sayeed Shafayet Chowdhury↗Md. Shaown Miah↗S. M. Taiabul Haque↗Syed Ishtiaque Ahmed↗

Vision-language models (VLMs) can produce confident visual answers even when the required visual evidence is missing, blank, or unrelated to the question. This failure mode, recently described as mirage (mirage2026), is especially concerning in medical and document VQA, where a plausible but visually ungrounded answer may be mistaken for image-based evidence. We study the complementary problem of pre-release mirage detection: given an image-question pair, determine whether the VLM should answer or abstain before generation. To that end, we propose a novel model-agnostic Text-Conditioned Layer-wise Internal Alignment (TC-LIA) method that probes patch-token representations across the layers of a CLIP ViT-H/14 vision encoder. The key idea is to project layer-wise image patch tokens into the final CLIP embedding space and measure their similarity with the question embedding, thereby tracking whether question-relevant visual evidence emerges across vision layers. TC-LIA summarizes this alignment trajectory using final image-text cosine similarity, late-layer top-k patch-text alignment, early-to-late gain, and layer-wise slope. These features are combined with pixel-statistic based blank/noise detection, zero-shot domain routing, and structured VLM self-assessment in an ensemble. Across five VQA domains with related, unrelated-real, and blank/noise inputs, and across twelve VLM backbones, Qwen2.5-VL-32B achieves the highest three-class detection accuracy of 94.7% with a 3.0% mirage rate, while Qwen2.5-VL-72B achieves 94.6% accuracy with a lower 2.8% mirage rate. Baseline mirage rates span 21.7-66.6%.

Read & Discuss → View Source →

06.

arXiv (CS.AI) 2026-06-18 DOI: arXiv:2510.18085

R2BC: Multi-Agent Imitation Learning from Single-Agent Demonstrations

Authors:

Connor Mattson↗Varun Raveendra↗Ellen Novoseller↗Nicholas Waytowich↗Vernon J. Lawhern↗Daniel S. Brown↗

arXiv:2510.18085v2 Announce Type: replace-cross Abstract: Imitation Learning (IL) is a natural way for humans to teach robots, particularly when high-quality demonstrations are easy to obtain. While IL has been widely applied to single-robot settings, relatively few studies have addressed the extension of these methods to multi-agent systems, especially in settings where a single human must provide demonstrations to a team of collaborating robots. In this paper, we introduce and study Round-Robin Behavior Cloning (R2BC), a method that enables a single human operator to effectively train multi-robot systems through sequential, single-agent demonstrations. Our approach allows the human to teleoperate one agent at a time and incrementally teach multi-agent behavior to the entire system, without requiring demonstrations in the joint multi-agent action space. We show that R2BC methods match, and in some cases surpass, the performance of an oracle behavior cloning approach trained on privileged synchronized demonstrations across four multi-agent simulated tasks. Finally, we deploy R2BC on two physical robot tasks trained using real human demonstrations.

Read & Discuss → View Source →

07.

arXiv (CS.AI) 2026-06-16 DOI: arXiv:2606.16933

A Unified Causal-Origin Taxonomy of Distributional Shifts in Reinforcement Learning

Authors:

Ardianto Wibowo↗Paulo E Santos↗Amer Baghdadi↗Matthew Stephenson↗Karl Sammut↗Jean-Philippe Diguet↗

arXiv:2606.16933v1 Announce Type: cross Abstract: Reinforcement learning (RL) systems often degrade when operating conditions differ from those previously encountered, reflecting distributional shifts in the underlying data-generating process. Such shifts may occur between training and evaluation, as in In-Distribution (ID) and Out-of-Distribution (OOD) generalization, or within non-stationary settings where environment dynamics evolve over time. However, the formal relationship between these views remains unclear, and existing work mainly focuses on mitigation rather than the causal origin of shift within the agent-environment interaction. This work develops a unified causal-origin taxonomy that characterizes sources of distributional shift in RL and relates ID/OOD generalization to non-stationary settings. We transfer the classical dataset-shift principle from supervised learning to RL by reformulating distributional shift in terms of the generative interaction process. Using a Partially Observable Markov Decision Process (POMDP), we decompose the interaction into structural components, including the state distribution, observation process, policy, reward, and transition dynamics, together with the shifted-time boundary. The proposed taxonomy distinguishes internal, agent-driven, and external, environment-driven, distributional shifts. The shifted-time boundary perspective further characterizes explicit, implicit, and hybrid shifts. This formulation unifies ID/OOD generalization and non-stationarity as structured changes in the underlying process. We also introduce an evaluation framework for measuring shift impact and adaptation through performance degradation and recovery metrics. By grounding distributional shift in the causal-origin structure of RL, this work supports systematic analysis of robustness under distributional shift.

Read & Discuss → View Source →

08.

arXiv (CS.LG) 2026-06-16 DOI: arXiv:2409.18909

Best Arm Identification with Minimal Regret

Authors:

Junwen Yang↗Vincent Y. F. Tan↗Tianyuan Jin↗

arXiv:2409.18909v2 Announce Type: replace Abstract: Motivated by real-world applications that necessitate responsible experimentation, we introduce the problem of best arm identification (BAI) with minimal regret. This variant of the multi-armed bandit problem elegantly amalgamates two of its most ubiquitous objectives: regret minimization and BAI. More precisely, the agent's goal is to identify the best arm with a prescribed confidence level $\delta$, while minimizing the cumulative regret up to the stopping time. Focusing on single-parameter exponential families of distributions, we leverage information-theoretic techniques to establish an instance-dependent lower bound on the expected cumulative regret. Moreover, we present an impossibility result that underscores the tension between cumulative regret and sample complexity in fixed-confidence BAI. Complementarily, we design and analyze the Double KL-UCB algorithm, which achieves asymptotic optimality as the confidence level tends to zero. Notably, this algorithm employs two distinct confidence bounds to guide arm selection in a randomized manner. Our findings elucidate a fresh perspective on the inherent connections between regret minimization and BAI.

Read & Discuss → View Source →

09.

arXiv (CS.CL) 2026-06-17 DOI: arXiv:2606.17973

Fine-tuning LLMs for Passive Depression Severity Estimation from AI Mental Health Dialogue

Authors:

Olivier Tieleman↗Ziyi Zhu↗Ting Su↗Samuel J. Bell↗Thomas D. Hull↗Caitlin A. Stamatis↗

Depression is the leading cause of disability worldwide, and early detection of symptom change is essential for timely intervention. Validated instruments such as the Patient Health Questionnaire-9 (PHQ-9) support symptom monitoring at scale, but real-world completion rates are low, introducing response bias and systematic missingness. Passive approaches that infer severity from routinely generated data could close this gap. We address this by predicting PHQ-9 total scores directly from transcripts of conversations between users and an AI mental health application, requiring only conversation text and no additional clinical data. We fine-tune a Qwen3.5-27B backbone with a regression head, augment 3,111 ground-truth labels with pseudolabels generated by a reasoning model (Claude Opus) and iteratively trained intermediate models, for a combined dataset of 6,283 users. On a held-out test set of 842 users, our best model achieves MAE = 2.6, RMSE = 4.0, Pearson r = 0.80, and AUC = 0.91 at the PHQ-9 >= 10 clinical threshold. We also find AUC > 0.87 at every severity threshold from PHQ-9 >= 3 to PHQ-9 >= 24, demonstrating that the model captures depression severity across the full clinical spectrum. This work opens the door to passive, continuous symptom monitoring in AI mental health platforms, without requiring users to complete self-report measures.

Read & Discuss → View Source →

10.

arXiv (CS.CV) 2026-06-17 DOI: arXiv:2606.17953

MLLMs Get It Right, Then Get It Wrong: Tracing and Correcting Late-Layer Textual Bias

Authors:

Xingming Li↗Ao Cheng↗Qiyao Sun↗Xixiang He↗Xuanyu Ji↗Runke Huang↗Qingyong Hu↗

When vision contradicts text, multimodal large language models (MLLMs) consistently favor text, even when images provide clear evidence otherwise. This bias poses risks for applications requiring visual grounding, yet its cause remains unclear. In this paper, we uncover a surprising finding: models often get it right initially, forming correct vision-based predictions in their intermediate layers, before changing their minds and favoring text in the final output. We call this "late-layer textual override". The visual information is encoded, it simply does not survive to the output. More intriguingly, we find that how predictions change reveals whether they're correct: 85% of failures shift toward text, while 89% of successes shift toward vision. This directional signature enables a simple but powerful intervention: when we detect a confident visual prediction being suppressed, we restore it. We propose CALRD (Conflict-Aware Layer Reference Decoding), a training-free method that recovers overridden predictions at inference time. Experiments across five MLLMs of varying architectures demonstrate up to 9.4% absolute improvements on conflict benchmarks while largely preserving standard performance, without training or external knowledge. It recovers what the model already knew but failed to preserve.

Read & Discuss → View Source →

11.

arXiv (CS.LG) 2026-06-17 DOI: arXiv:2602.03045

Clarify Before You Draw: Proactive Agents for Robust Text-to-CAD Generation

Authors:

Bo Yuan↗Zelin Zhao↗Petr Molodyk↗Bin Hu↗Yongxin Chen↗

arXiv:2602.03045v2 Announce Type: replace Abstract: Large language models have recently enabled text-to-CAD systems that synthesize parametric CAD programs (e.g., CadQuery) from natural-language prompts. In practice, however, geometric descriptions can be under-specified or internally inconsistent: critical dimensions may be missing and constraints may conflict. However, existing fine-tuned models tend to reactively follow the user instructions and hallucinate dimensions when the text is ambiguous. To address this, we propose a proactive agentic framework for text-to-CadQuery generation, named as ProCAD, that resolves specification issues before code synthesis. Our framework pairs a proactive clarifying agent, which audits the prompt and asks targeted clarification questions only when necessary to produce a self-consistent specification, with a CAD coding agent that translates the specification into an executable CadQuery program. We fine-tune the coding agent based on a curated high-quality text-to-CadQuery dataset and train the clarifying agent via agentic SFT on clarification trajectories. Experiments show that proactive clarification significantly improves robustness to ambiguous prompts while keeping interaction overhead low. ProCAD outperforms frontier closed-source models, including Claude Sonnet 4.5, reducing the mean Chamfer distance by 79.9% and lowering the invalidity ratio from 4.8% to 0.9%. Our code and datasets are made publicly available on https://github.com/BoYuanVisionary/Pro-CAD.

Read & Discuss → View Source →

12.

arXiv (CS.LG) 2026-06-16 DOI: arXiv:2602.00781

Fast Non-Episodic Finite-Horizon RL with K-Step Lookahead Thresholding

Authors:

Jiamin Xu↗Kyra Gan↗

arXiv:2602.00781v2 Announce Type: replace Abstract: Online reinforcement learning in non-episodic, finite-horizon MDPs remains underexplored and is challenged by the need to estimate returns to a fixed terminal time. Existing infinite-horizon methods, which often rely on discounted contraction, do not naturally account for this fixed-horizon structure. We introduce a modified Q-function: rather than targeting the full-horizon, we learn a K-step lookahead Q-function that truncates planning to the next K steps. To further improve sample efficiency, we introduce a thresholding mechanism: actions are selected only when their estimated K-step lookahead value exceeds a time-varying threshold. We provide an efficient tabular learning algorithm for this novel objective, proving it achieves fast finite-sample convergence: it achieves minimax optimal constant regret for $K=1$ and $\mathcal{O}(\max((K-1),C_{K-1})\sqrt{SAT\log(T)})$ regret for any $K \geq 2$. We numerically evaluate the performance of our algorithm under the objective of maximizing reward. Our implementation adaptively increases K over time, balancing lookahead depth against estimation variance. Empirical results demonstrate superior cumulative rewards over state-of-the-art tabular RL methods across synthetic MDPs and RL environments: JumpRiverswim, FrozenLake and AnyTrading. Code is provided on \href{https://github.com/jamie01713/K-Step-Lookahead}{github}.

Read & Discuss → View Source →

13.

arXiv (CS.AI) 2026-06-17 DOI: arXiv:2606.18024

Catastrophic Forgetting is Low-Rank: A Function-Space Theory for Continual Adaptation

Authors:

Ido Nitzan Hidekel↗Dan Raviv↗

arXiv:2606.18024v1 Announce Type: cross Abstract: Catastrophic forgetting in continual adaptation is usually studied through parameter drift, replay, or distillation, but these views do not identify which output-space directions are vulnerable. We give a function-space account in the NTK regime: new-task training induces old-task prediction drift through the cross-task kernel, yielding a closed-form predictor for the forgetting vector before any new-task gradient step. In frozen-backbone linear-head PEFT-CL, where the model is linear in the trainable parameters, the predictor is exact up to numerical precision; for nonlinear adapters/full fine-tuning, it is a local NTK approximation. The same expression reveals that forgetting concentrates in a small number of old-task NTK eigenmodes and under frozen linear heads gives a Kronecker scaling rule for the vulnerable rank. These results clarify the relation to prior NTK-overlap theory, explain why parameter-space regularizers can miss output-space interference, and motivate a targeted spectral regularizer.

Read & Discuss → View Source →

14.

arXiv (CS.AI) 2026-06-17 DOI: arXiv:2606.17649

A Risk Decomposition Framework for Pre-Hoc Fine-Tuning Prediction

Authors:

Yuxiang Luo↗Chen Wang↗Nan Tang↗

arXiv:2606.17649v1 Announce Type: cross Abstract: The high cost of fine-tuning LLMs poses a significant economic barrier; pre-hoc performance prediction offers a critical solution to substantially reduce this expense. However, the theoretical limits of pre-hoc performance prediction remain unexplored. We formulate it as a stochastic estimation problem under information constraints, decomposing prediction risk into two components: an intrinsic limit (static data-model compatibility) and a reducible optimization variance. We prove that optimization variance admits a necessary lower bound on its decay rate, implying fundamental constraints on how quickly uncertainty dissipates, regardless of the predictor used. Based on these dynamics, we derive a budget-optimal probing principle and introduce a predictability phase diagram that organizes tasks into three distinct regimes: Static-Sufficient, Dynamic-Critical, and Noise-Dominant. Extensive experiments on synthetic and real-world benchmarks validate these theoretical regimes and demonstrate the efficiency of our probing strategy.

Read & Discuss → View Source →

15.

PLOS Medicine 2026-05-11 DOI: HASH:149a28e3ce6ea28b01955dbe0de39e43

Connected or chained by social media? Child and adolescent mental health in a digital era

Authors:

Silja Kosola↗

by Silja Kosola Social media has evolved from connection to compulsion, disproportionately harming children and adolescents. Addictive designs together with developmental vulnerability fuel mental health risks and highlight the urgent need for stricter age limits and stronger protections. In this Perspective, Silja Kosola outlines how social media disproportionately harms child and adolescent mental health, and argues that while recent policy changes aimed at protecting youth from social media are welcome, stricter age limits and greater accountability of social media companies are needed.

Read & Discuss → View Source →

16.

arXiv (CS.LG) 2026-06-16 DOI: arXiv:2604.09361

Stochastic-Dimension Frozen Sampled Neural Network for High-Dimensional Gross-Pitaevskii Equations on Unbounded Domains

Authors:

Zhangyong Liang↗

arXiv:2604.09361v4 Announce Type: replace Abstract: This paper introduces the Stochastic-Dimension Frozen Sampled Neural Network (SD-FSNN), a novel computational framework for solving high-dimensional Gross-Pitaevskii equation (GPE) on unbounded domain. The proposed method circumvents the curse-of-dimensionality that plagues traditional discretizations and the computational bottlenecks of gradient-based neural network solvers through a synergistic combination of techniques. First, a prescribed Gaussian envelope encodes the far-field decay of the wavefunction, enabling a space-time separation where the spatial approximation is handled by a frozen, single-hidden-layer neural network with data-driven sampled features. This yields a gradient-free formalism where spatial derivatives are analytically precomputed and time-dependence is evolved via reduced ODEs. Second, a stochastic-dimension sampler provides a conditionally unbiased estimate of the spatial operator by evaluating only a small subset of spatial dimensions at each time step, essentially reducing computational and memory costs. Discrete conservation laws are also enforced, ensuring long-term stability. Extensive numerical experiments on GPE in up to 1000 dimensions demonstrate that SD-FSNN achieves significantly higher accuracy and efficiency compared to state-of-the-art methods, including PINNs, randomized feature methods, and tensor-network approaches. The results confirm that SD-FSNN effectively mitigates the Kolmogorov $n$-width barrier for frozen-basis models on structured solution manifolds.

Read & Discuss → View Source →

17.

arXiv (CS.LG) 2026-06-16 DOI: arXiv:2606.16978

Task-Error Residual Learning for Real-Robot Five-Ball Juggling

Authors:

Kai Ploeger↗Jan Peters↗

arXiv:2606.16978v1 Announce Type: cross Abstract: For residual learning that refines existing behavior, sample efficiency depends on two things: how much information each rollout returns, and how efficiently the learner uses that information. Reinforcement learning's standard scalar reward carries far less information than the directional task error that defines the task. Random exploration further discards whatever information each rollout returns. Through residual learning with directional task-error supervision and a task error model that drives sample selection, we achieve stable three-, four-, and five-ball juggling on anthropomorphic Barrett WAM arms. Despite planning and controlling through a simple, idealized stack, the system converges from the second attempt. The first attempt drops, after which task error decreases monotonically without further failures. In comparison, five-ball juggling typically takes humans years of practice. We compare residual learners across two ternary axes, the directional information in the learning feedback and the commitment of the analytic prior, spanning Newton-style Jacobian updates, Composite Bayesian Optimization, and stochastic search methods. Both axes prove necessary: neither directional feedback nor an informative prior suffices alone, and the simplest method that combines them, a fixed-Jacobian Newton update, is the most reliable. The learned residual tolerates substantial prior misalignment and degraded joint tracking, affecting mainly convergence speed. The bottleneck for residual learning on real robots is therefore the information content of the supervision signal and how the learner uses it, not the accuracy of the surrounding stack. Video documentation of all experiments is available at https://kai-ploeger.com/residual-juggling.

Read & Discuss → View Source →

18.

arXiv (CS.AI) 2026-06-16 DOI: arXiv:2606.14935

PrologMCP: A Standardized Prolog Tool Interface for LLM Agents

Authors:

Agnieszka Mensfelt↗Adarsh Prabhakaran↗Adrian Haret↗Vince Trencsenyi↗Kostas Stathis↗

arXiv:2606.14935v1 Announce Type: new Abstract: Frontier reasoning-tuned language models still fail on deductive tasks at depth, and the cost of improved performance through extended internal reasoning scales poorly. Symbolic delegation offers a complementary route: a language model translates the problem, while a solver performs the inference. However, current autoformalization pipelines for logic programming are typically bespoke integrations tied to particular tasks or agents. We introduce PrologMCP, a task-agnostic, open-source server that exposes Prolog as a stateful tool through the Model Context Protocol (MCP). Its compact tool interface, structured error reporting, and per-session isolation make the translate-run-inspect-repair loop a reusable primitive for MCP-capable agents. We evaluate a formalizer agent enhanced with PrologMCP against standard and reasoning LLMs (Claude Sonnet 4.6, GPT-4.1, and o4-mini) on two subsets of PARARULE-Plus: a general-purpose sample and a more challenging one targeting a specific failure mode of natural-language reasoning. On the general sample, the formalizer matches or exceeds reasoning LLMs (accuracy 1.00 vs.\ 1.00 / 0.998), with the largest gains over standard models (0.762 for GPT-4.1). On the challenging subset, the formalizer remains near-perfect (1.00 / 0.99) while reasoning LLMs drop to 0.95 / 0.94. These results suggest that delegating inference to Prolog via MCP is a robust and inspectable alternative to extended natural-language reasoning.

Read & Discuss → View Source →

19.

arXiv (CS.CV) 2026-06-12 DOI: arXiv:2605.16713

GeoWorld-VLM: Geometry from World Models for Vision-Language Models

Authors:

Renjie Gu↗Kaichen Zhou↗Yan Luo↗Mengyu Wang↗

Modern Vision-Language Models (VLMs) achieve strong semantic recognition, yet remain brittle on elementary spatial relations such as left of, on, behind, and between. One cause of this failure arises before language reasoning begins: the visual pathway may compress or discard critical 3D structural cues during feature extraction, so the language model receives image representations that are already insufficient for reliable spatial judgment. We introduce GeoWorld-VLM, a VLM-side distillation framework that transfers geometric structure from frozen camera-conditioned video world models into VLMs. GeoWorld-VLM fine-tunes only the image encoder and multimodal projector, aligning post-projector image features with intermediate world-model representations while leaving the main backbone frozen. Given images, a prompt, and a sampled camera trajectory, the world-model teacher converts static visual input into a synthetic multi-view spatial signal. Training combines spatial answer supervision, teacher-student feature alignment, and a preservation anchor to the original VLM. Since the language model remains frozen, GeoWorld-VLM preserves the original model's linguistic capabilities while attributing spatial improvements to the enhanced visual pathway. To evaluate the effectiveness and generality of the proposed method, we apply GeoWorld-VLM to two distinct VLM architectures and observe consistent improvements across both backbones. GeoWorld-VLM improves performance by approximately 4 percent on both the What'sUp and VSR benchmarks, suggesting that world-model-guided visual alignment generalizes across model structures and spatial reasoning datasets.

Read & Discuss → View Source →

20.

arXiv (CS.CL) 2026-06-12 DOI: arXiv:2606.12923

Order Is Not Control

Authors:

Gareth Seneque↗Lap-Hang Ho↗Nafise Erfanian Saeedi↗Jeffrey Molendijk↗Tim Elson↗

AI alignment, interpretability, steering, and neural perturbation studies identify order-inducing objects. We argue that order is not control. Control requires a receiver-gated response law: a denominator-indexed operator mapping material state, action/drive, bath, and receiver state to response displacement, sinks, effort, and basin projection. We identify it across biological, LLM, adapter, and stochastic-operator panels. The laws are local: an intervention can be admitted, saturated, sign-changing, leaky, or overdriven depending on medium, bath, receiver state, action port, and comparator. Control is assigned when finite effort moves a target or outcome-readout class under the same denominator while damage, null/evasive, invalid format, overdrive, and unnecessary effort stay bounded. Mouse ALM, C. elegans, and zebrafish panels provide physical response-operator evidence while excluding coordinate identity and controller conclusions. LLM panels show generated-output response laws: across four material conditions, response vectors are predictable at 72.8-73.7% component-sign accuracy, rising to 84.3-84.8% on nonzero components; held-out observers predict system-effect and target/oracle families at 93.6% and 91.7% accuracy. Constitution-conditioned adapters reshape susceptibility as prepared media, and stochastic-operator panels separate measured opportunity from deployable action policies. This gives a driven-dissipative response-system account at the mesoscopic control level: drives act through prepared media, baths, and receivers, producing admitted movement, impedance, sinks, or overdrive. The evidence supports local admitted control and measurable stochastic response operators, while leaving deployable pre-generation control, hidden/logit causal sufficiency, biological-to-LLM coordinate identity, and literal thermodynamic quantities outside scope.

Read & Discuss → View Source →

21.

arXiv (CS.LG) 2026-06-12 DOI: arXiv:2508.04888

Retrieval-Augmented Foundation Models for Water Level Prediction in the Everglades

Authors:

Rahuul Rangaraj↗Jimeng Shi↗Rajendra Paudel↗Giri Narasimhan↗Yanzhao Wu↗

arXiv:2508.04888v2 Announce Type: replace Abstract: Accurate water level forecasting in the Everglades is essential for flood mitigation, drought management, water resource planning, and biodiversity conservation. While recent time-series foundation models have shown strong performance on generic tasks (represented in their pre-training), their effectiveness in domain-specific applications remains insufficiently understood. In this work, we curate a domain-specific dataset for water-level forecasting in the Everglades and observe that the performance of current state-of-the-art models remains limited. To address this gap, we leverage a retrieval-augmented mechanism that retrieves analogous multivariate hydrological episodes from an external archive of historical observations to enrich the input context of those pre-trained models. We study two retrieval strategies, statistical similarity-based retrieval and mutual information-based retrieval, and analyze how incorporating retrieved historical contexts affects predictive performance. Extensive experiments show that retrieval augmentation consistently improves long-horizon water level forecasts and yields disproportionately larger gains during extreme events, which is particularly critical for environmental decision-making. Our study provides empirical evidence that analog-based retrieval can benefit pretrained time-series foundation models in environmental science, offering practical insights into their strengths, limitations, and failure modes when applied to hydrological forecasting in the Everglades. Although evaluated in the Everglades, the proposed framework is general and can be applied to other hydrological systems given time series data. The code and data have been made publicly available at https://github.com/rahuul2992000/WaterRAF.

Read & Discuss → View Source →

22.

arXiv (CS.CL) 2026-06-11 DOI: arXiv:2606.08011

Rewrite to Translate, Translate to Reward: Reinforcement Learning for Source Rewriting in Machine Translation

Authors:

Boxuan Lyu↗Haiyue Song↗Zhi Qu↗Hidetaka Kamigaito↗Kotaro Funakoshi↗Manabu Okumura↗

Rewriting source text with large language models (LLMs) before translation has been shown to improve machine translation (MT) quality. However, we find that prompt-based rewriting can degrade translation quality rather than improve it, particularly when smaller LLMs, such as 4B-parameter models, are used. We argue that this limitation stems from the difficulty of controlling rewriting behavior through natural-language prompts alone: a rewrite is useful only if it improves downstream translation, yet existing prompt-based methods do not explicitly optimize for this signal. To address this issue, we propose RLSR (Reinforcement Learning for Source Rewriting), a reinforcement learning framework that trains the rewriting model with a reward based on the downstream translation-quality improvement produced by each rewrite. Experiments across six MT systems and 16 language pairs show that our 4B RLSR-trained rewriting models significantly outperform both the no-rewriting baseline and prompt-based rewriting baselines at the same model scale, while remaining competitive with baselines that use a 235B LLM.

Read & Discuss → View Source →

23.

arXiv (CS.CL) 2026-06-12 DOI: arXiv:2606.09073

A Unifying Lens on Reward Uncertainty in RLHF

Authors:

Ely Hahami↗Yoel Zimmermann↗Ray Zhou↗Jack Benarroch Jedlicki↗

Reinforcement learning from human feedback (RLHF) is bottlenecked by reward hacking, where the policy exploits errors in a proxy reward model (RM) and produces high RM scores without genuine quality gains. A natural mitigation is pessimism: lowering rewards in regions where the RM is uncertain. However, standard scalar RMs provide no principled notion of uncertainty. We argue that the right object is a distributional reward model $p(r\mid x,y)$. Under either a Bayesian inference or a KL-distributionally robust optimization (KL-DRO) lens, the KL-regularized RLHF objective admits a closed-form effective reward $\tilde r(x,y) = \pm\beta\log\mathbb{E}_p[e^{\pm r/\beta}]$. The pessimistic branch unifies the prior heuristics for RM ensemble aggregation: mean aggregation, worst-case optimization (WCO), and uncertainty-weighted optimization (UWO) all emerge as limits or truncations of this single expression. This also clarifies the implicit assumptions of each existing rule.

Read & Discuss → View Source →

24.

arXiv (quant-ph) 2026-06-19 DOI: arXiv:2606.19462

Quantum deformations of $\mathcal{U}(\mathfrak{sl}(2, \mathbb{R}))$. Part I: Fidelity and experimental benchmarking

Authors:

V. Mariscal↗J. J. Relancio↗L. Santamar\'ia-Sanz↗

arXiv:2606.19462v1 Announce Type: new Abstract: This work explores the effects of both the standard quantum $q$-deformation and the non-standard $h$-deformation of the Hopf algebra $\mathcal{U}(\mathfrak{sl}(2, \mathbb{R}))$ on multi-qubit systems. By constructing the states of a Hilbert space of $N$ qubits through the Clebsch-Gordan coefficients associated with the deformed algebras, we show that these states naturally coincide with the eigenstates of the Hamiltonian of the $q$- and $h$-deformed Kittel-Shore models. We compare the resulting deformed states with those typically targeted in quantum information experiments, providing a bridge between algebraic constructions and experimentally relevant quantum resources. Fidelities with respect to the undeformed states are computed to establish how the quantum correlations are affected, both for few-qubit systems (including Dicke and non-Dicke states), and in the macroscopic limit ($N \to \infty$) through closed-form formulas derived for arbitrary Dicke states. The results reveal different behaviors between the two deformations. The $q$-deformation smoothly modifies the states and maintains a residual overlap with the original configurations, while the $h$-deformation rapidly makes the states orthogonal to their undeformed counterparts. Both models demand a standard $N^{-1}$ rescaling to preserve fidelity stability in the macroscopic limit.

Read & Discuss → View Source →

25.

arXiv (CS.CV) 2026-06-12 DOI: arXiv:2606.13239

ComAct: Reframing Professional Software Manipulation via COM-as-Action Paradigm

Authors:

Jiaxin Ai↗Tao Hu↗Xuemeng Yang↗Shu Zou↗Hairong Zhang↗Daocheng Fu↗Yu Yang↗Hongbin Zhou↗Nianchen Deng↗Pinlong Cai↗Zhongyuan Wang↗Botian Shi↗…

Existing computer-use agents remain fundamentally limited in professional software manipulation: GUI-based agents suffer from fragile visual grounding and long-horizon error accumulation, while API-basedapproaches struggle with heterogeneous protocols and inaccessible commercial interfaces. In this work,we identify the Component Object Model (COM) as a unified executable abstraction, proposing COM-as-Action: a new paradigm that reframes professional software interaction as deterministic program synthesisrather than sequential visual control. To validate this paradigm in the most demanding environments, weintroduce ComCADBench, the first benchmark for agents operating real industrial CAD software. Ourexperiments reveal a substantial paradigm gap: frontier proprietary models achieve near-zero successunder GUI-based interaction, whereas COM-based execution yields substantial immediate gains. Tobridge the remaining gap between syntactic correctness and geometric accuracy, we develop ComActor, aself-correcting agent trained through a progressive three-stage framework, alongside ComForge, a scalableplatform for large-scale training in Windows containers. Extensive experiments show that ComActorachieves state-of-the-art performance on ComCADBench, with strong resilience in long-horizon taskswhere baselines collapse, and generalizes to external CAD benchmark.

Read & Discuss → View Source →