中 EN
Sign In Register

Academic Intelligence · Curated Daily

Explore the Frontier of Global Academia

AcademicHub aggregates real-time literature from top journals and preprint platforms. Build your personal research radar and let large language models compile cross-disciplinary analysis briefings automatically.

Sign In Register
01.
arXiv (CS.CL) 2026-06-19

CzechDocs: A Multiway Parallel Dataset of Formatted Documents for Minority Languages in Czechia

Authors:
Josef Jon↗Ond\v{r}ej Bojar↗

We present CzechDocs, a multiway parallel dataset of formatted documents (HTML, DOCX, and PDF) covering Czech and minority languages used in Czechia-primarily Ukrainian and English, with smaller portions of Vietnamese, Russian and other languages. The dataset is designed to support the evaluation of machine translation systems that aim to preserve document formatting during translation. We provide a comparison of the most common approaches to format-preserving machine translation on a validation subset of the dataset. This validation split, together with the evaluation toolkit, is publicly released for further research. A held-out test split will be reserved for a future shared task focused on document-level translation with formatting preservation.

Read & Discuss → View Source →
02.
arXiv (CS.AI) 2026-06-16

Adaptive inference and function vectors in deep transformers

Authors:
Ravin Raj↗Gautam Reddy↗

arXiv:2606.16694v1 Announce Type: cross Abstract: Transformers are widely used as a general-purpose substrate for learning complex correlations between a large collection of coupled variables, but their internal mechanisms have remained mysterious. We introduce a theory of a deep transformer as a mean-field interacting system that implements distributed inference, subject to constraints on communication, locality and depth. We show that such a system can exploit internal state representations ('function vectors') to infer a latent context variable at increasingly finer scales over its layers. In an in-context regression task, the theory predicts a non-trivial relationship between non-Gaussian, hierarchical structure in the latent context variable, and transformer depth. Predictions are tested using constrained linear attention transformers and demonstrate adaptive inference in deep architectures. Feedforward blocks and depth enable transformers to implement a much richer class of in-context learning algorithms than previously described.

Read & Discuss → View Source →
03.
bioRxiv (Bioinfo) 2026-06-08

HydraMPP: A lightweight library for distributed massive parallel processing in Python - threading at scale.

Authors:
Figueroa↗J. L↗White↗R. A↗

We now exist in the era of massive datasets from genomics, large language models, and all the known knowledge of humanity right at our fingertips. Much of this data is becoming more accessible; however, processing such data remains an ongoing issue across systems including high performance computing (HPC) infrastructures. Massively parallel computing (MPP) has solved this using a divide and conquer approach by splitting workloads across independent nodes (i.e., central processing units (CPU) allowing for higher scaling of data). The main engine for this in python is Ray; however, it has many issues including a large code space, security issues, debugging opacity, and memory management issues. Here, we present HydraMPP, a lightweight, ease of use and utilization, with high auditability, and with SLURM ergonomics.

Read & Discuss → View Source →
04.
bioRxiv (Bioinfo) 2026-06-16

Accelerating String Comparison in RLZ Compressed Sequences via LCE Jumps

Authors:
Varki↗Boucher↗

Relative Lempel-Ziv (RLZ) is an effective compression method for large, repetitive collections; however, the fundamental primitives required to elevate it from a passive archival format to a tractable representation for compressed construction have yet to be fully established. In this paper, we introduce an algorithmic framework for structurally comparing and lexicographically sorting sequences of RLZ factors. We characterize when direct factor comparisons are necessary and when they can be bypassed using RLZ specific shortcuts. We further introduce a method for extending truncated factors into right-maximal matches, enabling the recovery of matching statistics from the RLZ parse. Experimentally, RLZ sorting achieved speedups of up to 3.93x over character-based sorting. Together, these results advance the use of the RLZ format as a foundation for compressed construction.

Read & Discuss → View Source →
05.
arXiv (CS.AI) 2026-06-16

Emergent Strategic Reasoning Risks in AI: A Taxonomy-Driven Evaluation Framework

Authors:
Tharindu Kumarage↗Lisa Bauer↗Yao Ma↗Dan Rosen↗Yashasvi Raghavendra Guduri↗Anna Rumshisky↗Kai-Wei Chang↗Aram Galstyan↗Rahul Gupta↗Charith Peris↗

arXiv:2604.22119v2 Announce Type: replace Abstract: As reasoning capacity and deployment scope grow in tandem, large language models (LLMs) gain the capacity to engage in behaviors that serve their own objectives, a class of risks we term Emergent Strategic Reasoning Risks (ESRRs). These include, but are not limited to, deception (intentionally misleading users or evaluators), evaluation gaming (strategically manipulating performance during safety testing), and reward hacking (exploiting misspecified objectives). Systematically understanding and benchmarking these risks remains an open challenge. To address this gap, we introduce ESRRSim, a taxonomy-driven agentic framework for automated behavioral risk evaluation. We construct an extensible risk taxonomy of 7 categories, which is decomposed into 20 subcategories. ESRRSim generates evaluation scenarios designed to elicit faithful reasoning, paired with dual rubrics assessing both model responses and reasoning traces, in a judge-agnostic and scalable architecture. Evaluation across 11 reasoning LLMs reveals substantial variation in risk profiles (detection rates ranging 14.45%-72.72%), with dramatic generational improvements suggesting models may increasingly recognize and adapt to evaluation contexts.

Read & Discuss → View Source →
06.
arXiv (CS.AI) 2026-06-16

Beyond Scalars: Evaluating and Understanding LLM Reasoning via Geometric Progress and Stability

Authors:
Xinyan Jiang↗Ninghao Liu↗Di Wang↗Lijie Hu↗

arXiv:2603.10384v3 Announce Type: replace Abstract: Evaluating LLM reliability via scalar probabilities often fails to capture the structural dynamics of reasoning. We introduce TRACED, a framework that assesses reasoning quality through theoretically grounded geometric kinematics. By decomposing reasoning traces into Progress (displacement) and Stability (curvature), we reveal a distinct topological divergence: correct reasoning manifests as high-progress, stable trajectories, whereas hallucinations are characterized by low-progress, unstable patterns (stalled displacement with high curvature fluctuations). Leveraging these signatures, our probabilistic framework achieves competitive performance and superior robustness across diverse benchmarks. Crucially, TRACED bridges geometry and cognition by mapping high curvature to ''Hesitation Loops'' and displacement to ''Certainty Accumulation'', offering a physical lens to decode the internal dynamics of machine thought.

Read & Discuss → View Source →
07.
arXiv (math.PR) 2026-06-17

Cutoff for asymmetric shelf shuffle

Authors:
Raghavendra Tripathi↗

arXiv:2606.18039v1 Announce Type: new Abstract: A mechanical shuffler consists of $m$ shelves. A deck of $n$ cards, arranged in increasing order, is dealt from the bottom sequentially. Each card is assigned a shelf uniformly at random and placed on the top (bottom) of the existing pile with probability $p$ ($1-p$) independently. We refer to this as asymmetric shelf-shuffle. We find the law $\nu_{n, m}^{(p)}$ of the permutation induced by the asymmetric shelf-shuffle and show that the pair consisting of the number of descents and the number of valleys is a sufficient statistic. This generalizes a result of Diaconis, Fulman, and Holmes (Ann. Appl. Prob., 2013) corresponding to the case $p=1/2$. For $p=1/2$, Chen and Ottolini (ECP, 2025) established the cutoff in the total variation distance near $\lfloor n^{5/4}\rfloor$. We establish the cutoff for the asymmetric shelf shuffle. Let $\nu_n$ be the uniform measure on the set of all permutations $S_n$ of $\{1, \ldots, n\}$. For a fixed $p\neq 1/2$ and $c>0$, we show that \[\operatorname{TV}\left(\nu_{n, \lfloor cn^{3/2}\rfloor }^{(p)}, \nu_n\right)=1-2\Phi\left(-\frac{|2p-1|}{4\sqrt{3}c}\right)+O_{c, p}(n^{-1/2})\;.\] We also establish the cutoff in the separation distance near $m\approx n^{2}$ and in the relative entropy near $m=n^{3/2}$. In both cases, we also obtain the cutoff profile explicitly.

Read & Discuss → View Source →
08.
Nature (Science) 2026-06-17

A distant brown dwarf coplanar to a warm Jupiter and a hot super-Earth

Authors:
Matías I. Jones↗

In transiting planetary systems, in which planetary sizes are accurately determined from transit observations, the presence of transit-timing variations1 (TTVs), especially when combined with radial velocity (RV) data, provides powerful constraints on masses and orbital eccentricities. Together, these measurements offer crucial insights into system architecture, formation mechanisms and dynamical evolution. We present long-term RV and transit/TTV monitoring of the relatively young star (age approximately 1 Gyr) TOI-201, revealing an exceptional multi-planet system composed of a hot super-Earth (SE) size planet transiting every 5.8 days, a warm Jupiter (WJ) on a 53-day orbit and an eccentric (e = 0.62) low-mass brown dwarf (BD) on an approximately 8-year orbit, with an estimated mass MBD of about 16 Jupiter masses. The BD is the longest-period transiting substellar object ever characterized by means of RVs and the only one known to be coplanar with inner planets. The architecture of this system suggests that the SE was formed isolated and in the innermost region of the gaseous disk. On the other hand, the orbital configuration of the outer companions suggests a nearly in situ formation of both objects, with the WJ forming in a dense inner disk. Alternatively, the BD might have formed farther out and migrated inward, while increasing its eccentricity owing to interactions with the disk. Analysis of long-term radial velocity data and transit time variations, induced by a super-Earth, a warm Jupiter and a brown dwarf in a coplanar orbit around the relatively young star TOI201.

Read & Discuss → View Source →
09.
arXiv (CS.CV) 2026-06-12

Distributional Loss for Robust Classification

Authors:
Kathleen Anderson↗Thomas Martinetz↗

This paper proposes a novel loss concept for supervised classification tasks. Rather than enforcing a direct mapping from each input sample to a single assigned label, we define an optimization objective over all classifier outputs as a bimodal Gaussian distribution. This softer target formulation implicitly captures class ambiguity, mitigates overfitting, and encourages the learning of more robust decision boundaries, all without requiring additional label information. Experimental results demonstrate consistent improvements in robustness, with particularly pronounced gains in low-data regimes, while requiring only minimal modifications to standard training pipelines.

Read & Discuss → View Source →
10.
arXiv (CS.CL) 2026-06-24

Aspect-Based Sentiment Evolution and its Correlation with Review Rounds in Multi-Round Peer Reviews: A Deep Learning Approach

Authors:
Ruxue Hana↗Haomin Zhoua↗Jiangtao Zhong↗Chengzhi Zhang↗

Mining sentiment information from the textual content of peer review comments offers valuable insights into the scientific evaluation process. However, previous studies are often constrained by coarse-grained analysis and the lack of differentiation across review rounds. Notably, the dynamic shifts in reviewers' focus and sentiment tendencies throughout multiple review stages remain underexplored. To address this gap, the present study investigates the distribution and evolution of aspect-level sentiments and examines their correlation with the number of review rounds. We begin by segmenting the multi-round review comments of 11,063 accepted papers from Nature Communications and identifying fine-grained review aspect clusters. A manually annotated corpus of approximately 5,000 review sentences is then constructed. Using this dataset, we train a series of deep learning-based aspect sentiment classification models. Among them, the LCF-BERT-CDM model achieves the best performance, with a Macro-F1 score of 82.65%. Subsequent statistical analysis reveals a consistent trend: as the number of review rounds increases, the proportion of positive sentiments rises, while negative sentiments decline. Correlation analysis further indicates that aspect sentiment scores are negatively associated with the total number of review rounds. Key aspects exhibiting stronger correlations include "experiments", "research significance" and "result analysis".

Read & Discuss → View Source →
11.
arXiv (quant-ph) 2026-06-24

Universal Extraction of Quantum Critical Exponents and Phase Transitions via Tailored Hilbert Space

Authors:
Ye Xiong↗

arXiv:2606.24312v1 Announce Type: cross Abstract: Finite-size scaling and the renormalization group form the central toolkit for analyzing quantum phase transitions (QPTs). In this Letter, we introduce a novel Hilbert-space tailoring scheme to probe quantum critical phenomena. Applied to the second-order QPT of the one-dimensional (1D) XY model, our method yields precise critical points and exponents on lattices containing merely 50 unit cells. We further establish the universal applicability of this framework via investigations of the Berezinskii-Kosterlitz-Thouless transition in the 1D XXZ chain: critical parameters are recovered with as few as 12 lattice sites. This technique may open an alternative, efficient route to universally characterize QPT across many-body lattice systems.

Read & Discuss → View Source →
12.
arXiv (quant-ph) 2026-06-16

Light-induced nonadiabatic dissipative quantum dynamics of the Na2 molecule

Authors:
Patrick Barron↗Kriszti\'an Szab\'o↗G\'abor J. Hal\'asz↗K\'alm\'an Varga↗\'Agnes Vib\'ok↗

arXiv:2606.15292v1 Announce Type: new Abstract: Strong light-matter coupling between molecules and optical or plasmonic cavity modes has emerged as a promising platform for advancing photonics, materials science, and chemistry. However, optical cavities and plasmonic resonators in particular are inherently lossy systems characterized by finite photon lifetimes. Accurate theoretical descriptions of molecular dynamics under strong coupling therefore require a proper treatment of cavity losses. In this work, we compare three theoretical approaches for modeling dissipative molecule-cavity dynamics within a realistic parameter regime: the Lindblad master equation, the stochastic Schrödinger equation, and the non-Hermitian Schrödinger equation. As an example, we consider the two lowest energy state of Na2 molecule coupled to a cavity mode and analyze the time evolution of the excited-state population and the mean photon number. Our results demonstrate that the stochastic Schrödinger equation provides an accurate and computationally efficient alternative to the Lindblad master equation, while the non-Hermitian Schrödinger approach is found to be applicable only within a limited range of conditions. Furthermore, we show that inclusion of molecular rotation leads to rotational-vibrational-photonic coupling and gives rise to pronounced nonadiabatic dynamics through light-induced conical intersections. These findings highlight the importance of both dissipation and rotational degrees of freedom for a realistic description of molecular dynamics in strongly coupled molecule-cavity systems.

Read & Discuss → View Source →
13.
arXiv (CS.LG) 2026-06-11

NARRAS: Edge-Triggered Distributed Inference for CSI-Based Localization in Vehicular IoT Networks

Authors:
Rodrigo Oliver↗Ricardo Vazquez Alvarez↗Alejandro Lancho↗Stefano Rini↗

arXiv:2606.11914v1 Announce Type: cross Abstract: CSI-based localization with spatially distributed antenna arrays exposes a basic resource trade-off. Each array can provide a rich view of the channel, but forwarding observations from all arrays to a fusion center is wasteful when only a few carry useful information, and the shared uplink supports only a limited number of simultaneous transmissions. We let each array decide locally whether its current observation is worth reporting, subject to a budget on the average number of active transmitters. We refer to this abstraction as Edge-Triggered Distributed Inference (ETDI). It captures a broader class of task-oriented communication problems where resource-constrained devices share an access channel for a common inference task. We instantiate ETDI for CSI-based localization, a common scenario in vehicular IoT networks. Spatially distributed remote antenna arrays (RAAs) encode local channel state information (CSI) from user equipment (UE) transmissions into latent features, and the fusion center estimates the UE position from the subset of reported features. We propose NARRAS, a decentralized reporting policy in which each RAA combines a recurrent summary of its recent observations with a memory of the last latent it transmitted. Training controls an explicit activity budget through differentiable activity penalties and validation-calibrated deterministic thresholds, and uses channel-chart regularization to shape the latent geometry. Experiments show that, at comparable uplink activity, NARRAS improves localization accuracy over learned and heuristic sparse-reporting strategies, while dense full-report models remain useful budget-free references. In low-activity regimes, chart regularization further reduces high-percentile localization errors, suggesting that geometry-aware latent representations are more robust under sparse reporting.

Read & Discuss → View Source →
14.
arXiv (CS.LG) 2026-06-16

Diffusion Offline Reinforcement Learning for Fair and Energy-Efficient UAV-Assisted Wireless Networks

Authors:
Eslam Eldeeb↗Hirley Alves↗

arXiv:2606.16331v1 Announce Type: new Abstract: The integration of generative artificial intelligence with wireless communication and signal processing systems has opened new avenues for intelligent, data-driven decision-making in future 6G networks. This work proposes a diffusion soft actor-critic (Diffusion-SAC) approach that leverages offline reinforcement learning (RL) enhanced by denoising diffusion probabilistic models (DDPMs) to optimize trajectory and scheduling control in unmanned aerial vehicle (UAV) networks. While offline RL methods, such as conservative Q-learning (CQL), can learn from static datasets, they often struggle to generalize in low-data or dynamic conditions. To address this, we combine the robustness of CQL with the generative power of diffusion models, enabling expressive and signal-aware policy learning that generalizes beyond behavior policies. Applied to a UAV-assisted wireless network, the proposed framework minimizes transmission energy and improves fairness among devices. Simulations show that Diffusion-SAC outperforms standard offline RL baselines, achieving more stable convergence and higher rewards even with limited datasets. The method enhances data efficiency, reduces energy consumption, and increases throughput by more than 35 % compared to existing algorithms, demonstrating its potential for robust policy learning in next-generation wireless control systems.

Read & Discuss → View Source →
15.
arXiv (CS.AI) 2026-06-19

Physical Atari: A Robust and Accessible Platform for Real-time Reinforcement Learning on Robots

Authors:
Khurram Javed↗Joseph Modayil↗Gloria Kennickell↗Richard S. Sutton↗John Carmack↗

arXiv:2606.19357v1 Announce Type: cross Abstract: We built a robot called the Robotroller that actuates an Atari CX40+ controller and a device called the Atari Devbox that renders the game frame and the reward signal from the Arcade Learning Environment on a screen. The Robotroller and the Atari Devbox, together with an off-the-shelf camera and a desktop computer, constitute a system that can be used to study reinforcement learning algorithms in the physical world. We call the full system Physical Atari. In this paper, we detail the key decisions that make Physical Atari a robust and accessible platform. To make the system robust, we designed the Robotroller so that all movement is done through bearings, which reduces wear. Additionally, we wrote software that monitors the state of the servos at a high frequency and intervenes to limit stress. To make the system accessible, we used affordable off-the-shelf components and parts that can be manufactured using consumer 3D printers. Physical Atari can be built for under $1,000 and has been used for weeks of non-stop reinforcement learning experiments without any mechanical failures. We used it to validate that reinforcement learning algorithms can learn directly on robots and show that even small distribution shifts between learning and deployment can significantly degrade the performance of policies. Our results underscore the importance of on-device adaptation for strong performance on robots.

Read & Discuss → View Source →
16.
arXiv (CS.LG) 2026-06-24

Precision Physical Activity Prescription via Reinforcement Learning for Functional Actions

Authors:
Gefei Lin↗Rui Miao↗Jennifer Sacheck↗Xiaoke Zhang↗

arXiv:2605.19208v2 Announce Type: replace-cross Abstract: Physical activity (PA) plays an important role in maintaining and improving health. Daily steps have been a key PA measure that is easily accessible with common wearable devices. However, methods are lacking to recommend a personalized optimal distribution of daily steps over a period of time for the best of certain health biomarkers. In this paper, we fill this void based on the data from the All of Us Research Program which includes months of step counts as well as repeated measurements of key health biomarkers. We develop a new offline reinforcement learning (RL) algorithm to learn personalized and optimal PA distributions associated with cardiometabolic risk, where the action is a function representing the daily step distribution over a period of time. Simulation studies demonstrate the advantage of the proposed approach over existing continuous-action RL methods. The learned optimal policy from the All of Us data generally suggests people take more daily steps and also follow a more consistent pattern of PA over time while offering tailored recommendations for subgroups in blood glucose level, body mass index, blood pressure, age, and sex.

Read & Discuss → View Source →
17.
arXiv (CS.AI) 2026-06-18

Augmenting Dysarthric Speech Severity Assessment with MOS Supervision

Authors:
Kaimeng Jia↗Minzhu Tu↗Zengrui Jin↗Siyin Wang↗Chao Zhang↗

arXiv:2606.18645v1 Announce Type: cross Abstract: Dysarthria is a speech disorder marked by reduced intelligibility and communicative effectiveness. Automatic utterance-level assessment of dysarthric speech can support scalable speech monitoring and therapy-related analysis. Yet training such systems is bottlenecked by the scarcity of clinically annotated dysarthric speech. This work proposes to augment dysarthric speech assessment using data from speech synthesis evaluations, specifically human-annotated utterances with Mean Opinion Score (MOS) labels from the QualiSpeech corpus. Experiments show that fine-tuning on speech synthesis assessment data consistently improves performance on both intelligibility and naturalness prediction, while joint training yields gains primarily on naturalness. These results suggest that synthesis artifacts and dysarthric speech share perceptual commonalities, and speech synthesis evaluation corpora offer a practical augmentation source that reduces reliance on scarce clinical annotations.

Read & Discuss → View Source →
18.
arXiv (CS.AI) 2026-06-15

A Comparative Study of Deep Learning Architectures for Multi-Horizon Behavioural Forecasting for Mobile Health

Authors:
Pavlos Nicolaou↗Kleanthis Malialis↗Artemis Kontou↗Panayiotis Kolios↗

arXiv:2606.14604v1 Announce Type: cross Abstract: Wearable devices and smartphones generate rich behavioural time series that can support proactive health interventions, yet systematic comparisons of modern forecasting architectures for these data are lacking. In particular, it remains unclear how models generalise across populations, how different architectures respond to participant-level fine-tuning and how forecasting accuracy degrades across multi-day horizons. We benchmark six deep learning architectures, two zero-shot Foundation Models (FM) and statistical baselines on three public datasets encompassing over 800 participants, reporting per-feature metrics for step counts, screen time and sleep duration across 1-8 day horizons. We further conduct a per-feature personalisation study across all six architectures and assess FM transferability across dataset sizes and temporal granularities. Our key findings are: (i) no single architecture dominates, PatchTST leads among trained models while the three runners-up (TCN, MLP, Transformer) show no meaningful performance difference; (ii) the FM TimesFM matches or exceeds trained models zero-shot, especially in low-data regimes and (iii) participant-level fine-tuning reduces per-feature RMSE by 16-60\%, with sleep benefiting most and step counts least. These results provide practical guidance on architecture selection, FM applicability and personalisation strategies for mobile health forecasting. To the best of our knowledge, this is the first study to jointly evaluate modern deep learning, FMs and personalisation for multi-horizon behavioural forecasting from wearables.

Read & Discuss → View Source →
19.
arXiv (CS.CV) 2026-06-24

Segmentation and Classification of Pap Smear Images for Cervical Cancer Detection Using Deep Learning

Authors:
Nisreen Albzour↗Sarah S. Lam↗

Cervical cancer remains a significant global health concern and a leading cause of cancer-related deaths among women. Early detection through Pap smear tests is essential to reduce mortality rates; however, the manual examination is time consuming and prone to human error. This study proposes a deep learning framework that integrates U-Net for segmentation and a classification model to enhance diagnostic performance. The Herlev Pap Smear Dataset, a publicly available cervical cell dataset, was utilized for training and evaluation. The impact of segmentation on classification performance was evaluated by comparing the model trained on segmented images and another trained on non-segmented images. Experimental results showed that the use of segmented images marginally improved the model performance on precision (about 0.41 percent higher) and F1-score (about 1.30 percent higher), which suggests a slightly more balanced classification performance. While segmentation helps in feature extraction, the results showed that its impact on classification performance appears to be limited. The proposed framework offers a supplemental tool for clinical applications, which may aid pathologists in early diagnosis.

Read & Discuss → View Source →
20.
arXiv (CS.CV) 2026-06-11

Metadata-Aware Multi-Prompt Reasoning for Zero-Shot Accident Understanding

Authors:
Tarandeep Singh↗Soumyanetra Pal↗Soham Biswas↗Nishanth Chandran↗

In this paper, we address the problem of zero-shot understanding of accidents from surveillance videos by identifying when an impact event occurs, what type of impact it is, and where in the frame it occurs using natural language. We propose a three-stage pipeline that decomposes the accident understanding into when, what, and where. The first stage extracts a short temporal window around the impact using vision-language similarity. In the second stage, we perform metadata-driven multi-prompt reasoning with five complementary views (baseline, motion, geometry, contrast, and tiebreaker) and resolve disagreement via an entropy-gated pairwise adjudicator. Finally, we localize the impact of an open-vocabulary detector queried on the predicted accident type and scene layout, and aggregate detections across keyframes using a score-weighted centroid. Our pipeline achieves a substantial improvement in the harmonic-mean score over a centre-of-frame baseline on the zero-shot ACCIDENT @ CVPR benchmark. We show that decomposing zero-shot video understanding into temporal localization, semantic classification, and spatial grounding enable more reliable reasoning with vision-language models than direct prompting alone.

Read & Discuss → View Source →
21.
arXiv (CS.AI) 2026-06-17

Closing the Feedback Loop: From Experience Extraction to Insight Governance in Verbal Reinforcement Learning

Authors:
Yanwei Cui↗Xing Zhang↗Yulong Zhang↗Li Shao↗Xiaofeng Shi↗Guanghui Wang↗Peiyang He↗

arXiv:2606.17591v1 Announce Type: new Abstract: Training-free verbal reinforcement learning enables LLM agents to learn from world feedback – objective signals such as dynamic task outcomes, market returns, or demand forecasts – by extracting verbal rules from experience and injecting them as context, updating the agent's behavior without parameter changes. However, in non-stationary environments these agents face a retention-forgetting dilemma: retaining stale insights causes negative transfer, while discarding them causes catastrophic forgetting when conditions recur. We identify four requirements for navigating this dilemma – outcome-driven evaluation, persistent structured evidence, non-monotonic knowledge lifecycle, and compositional governance – and show that existing methods invest heavily in experience extraction while underinvesting in insight governance. We propose a three-layer architecture – rules, evidence, and skills – connected by a feedback-driven curation loop that closes the governance gap. Rules capture distilled experience from world outcomes; evidence logs track each rule's reliability across episodes; skills govern which rules to apply, how to resolve conflicts, and when to abstain. On financial forecasting as a case study, where world feedback is naturally abundant, noisy, and non-stationary, we show that the same accumulated experience either degrades performance below the zero-shot baseline or dramatically improves accuracy and risk-adjusted returns, depending on whether the curation loop is present.

Read & Discuss → View Source →
22.
arXiv (CS.LG) 2026-06-16

Hidden Degradation Costs in Energy-Cost-Only HEMS Optimisation: Study on Battery and PV Sensitivity

Authors:
Dawood Butt↗Nandor Verba↗

arXiv:2606.16051v1 Announce Type: cross Abstract: Residential battery energy storage systems (BESS) are increasingly deployed alongside photovoltaic (PV) generation to reduce household energy costs under volatile time-of-use (TOU) tariffs. Model predictive control (MPC) is a widely adopted optimisation strategy for home energy management systems (HEMS), typically formulated to minimise net energy cost, subject to physical and operational constraints. However, battery degradation is rarely embedded in the optimisation objective, meaning its cost is unquantified and aggressive; high-cycle-count strategies could incur significant losses once deployed to physical systems. This paper presents a receding-horizon mixed-integer linear programming (MILP) baseline for a UK residential HEMS, using demand data from the REFIT dataset. A 3 by 3 sensitivity study is conducted across three battery sizes and three PV array sizes, with post-hoc degradation cost estimated using the Naumann stress model and rainflow cycle counting. Results show that degradation remains constant for each battery size and can exceed energy cost savings by up to 1,060 %. These results demonstrate that energy-cost-only optimisation systematically underestimates the true system cost, motivating a degradation-aware control formulation.

Read & Discuss → View Source →
23.
arXiv (CS.CL) 2026-06-11

Agentic Environment Engineering for Large Language Models: A Survey of Environment Modeling, Synthesis, Evaluation, and Application

Authors:
Jiachun Li↗Zhuoran Jin↗Tianyi Men↗Yupu Hao↗Kejian Zhu↗Lingshuai Wang↗Dongqi Huang↗Longxiang Wang↗Shengjia Hua↗Lu Wang↗Jinshan Gao↗Hongbang Yuan↗…

Environments serve as interactive systems for large language model (LLM) based agents across diverse scenarios and play a crucial role in driving the continual evolution of model capabilities. Despite this importance, existing work lacks a systematic categorization and deep analysis. This paper systematically studies current researches on agentic environments from the perspective of the environment engineering lifecycle, covering their modeling, synthesis, evaluation and application. Specifically, the paper first introduces representative environments from the perspectives of eight attributes and eight domains, providing detailed analyses of their development paths and highlighting their core capabilities. Second, for automated environment synthesis, two paradigms are introduced, such as symbolic synthesis and neural synthesis. This paper also shows different environment evaluation methods in each paradigm. Thirdly, the corresponding environment applications from the perspective of agent-environment co-evolution are discussed. In specific, the paper characterizes the primary pathways for agent evolution in dynamic environments from four complementary perspectives: memory-centric experience evolution, orchestration-centric workflow evolution, trajectory-centric offline evolution, and exploration-centric online evolution. And three paradigms of environment evolution are identified, namely neural-driven, difficulty-driven, and scaling-driven approaches. At last, several promising future directions are discussed, including Environment-as-a-Service, Multi-agent Environments, and Neural-Symbolic Environments.

Read & Discuss → View Source →
24.
arXiv (CS.CV) 2026-06-11

Scene-Adaptive Nonlinear Tone Curves for Pseudo Ground-Truth Generation in Low-Light 3D Gaussian Splatting

Authors:
Mingzhe Lyu↗Jinqiang Cui↗Hong Zhang↗

Low-light novel view synthesis is challenging because dark multi-view images contain noise, weak structural detail, and compressed dynamic range. Recent 3D Gaussian Splatting (3DGS) methods address these challenges by generating pseudo ground-truth (pseudo-GT) images as supervision targets when paired normal-light references are unavailable. Existing pseudo-GT methods apply a uniform linear gain to all pixels, which clips bright regions while providing insufficient enhancement in dark regions, limiting reconstruction quality. We observe that nonlinear tone mappings, long established in 2D low-light enhancement, have not been explored for pseudo-GT generation in 3D reconstruction. Accordingly, we propose a scene-adaptive nonlinear tone-curve framework that replaces linear pseudo-GT with nonlinear alternatives. The framework introduces percentile-based normalisation for scene-agnostic curve application, a scene-adaptive offset for automatic black-level adjustment, and two complementary curves: Adaptive SoftExp (ASE), a bounded exponential curve, and Adaptive Poly3 (AP3), a data-driven cubic polynomial. The module changes only the pseudo-GT computation and leaves the 3DGS backbone unchanged. Experiments on three benchmarks covering 21 scenes show that both curves consistently outperform the linear baseline with PSNR improvements up to +4.34 dB on LOM and +3.25 dB on RealX3D. Both curves achieve similar performance despite their different mathematical forms, suggesting the improvement is curve-agnostic. Code is available at https://github.com/lvmingzhe/adaptiveToneCurve

Read & Discuss → View Source →
25.
arXiv (CS.AI) 2026-06-15

Elastic Queries Reinforcement Learning: Self-Aware Policy Execution for VLA Models

Authors:
Ge Wang↗Xinyu Tan↗Xiang Li↗Man Luo↗Chengsi Yao↗Shenhao Yan↗Jiahao Yang↗Fan Feng↗Honghao Cai↗Xiangyuan Wang↗Zhixin Mai↗Yiming Zhao↗…

arXiv:2606.14375v1 Announce Type: cross Abstract: Vision-language-action (VLA) models are powerful action generators for robot manipulation, but they are typically executed with fixed inference and replanning schedules. This rigidity ignores the uneven difficulty of robot control: contact-rich or uncertain states may need more computation and fresher feedback, while easier states can often be handled with fewer inference steps and longer open-loop execution. We propose Elastic Queries Reinforcement Learning (EQRL), a framework that makes each VLA policy query elastic. A lightweight latent-schedule adaptor jointly selects the latent input, denoising budget, and action chunk length, without fine-tuning the underlying VLA model. To make scheduling difficulty-aware, EQRL trains a critic over the joint latent-schedule action and derives a state difficulty signal from critic ensemble disagreement. This signal guides compute toward difficult states, while a learned residual allows task-driven correction. We formulate variable chunk execution as query-level macro-action RL with chunk-dependent discounting and an amortized number-of-function-evaluations (NFE) budget. Across simulation and real-robot manipulation, EQRL reduces amortized inference cost while preserving or improving task success.

Read & Discuss → View Source →