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.

01.
arXiv (quant-ph) 2026-06-19

Thermodynamic Value of XOR-Game-Induced Side Information in a Szilard Engine

arXiv:2605.12044v3 Announce Type: replace Abstract: We introduce a Szilard-type thermodynamic valuation of side-information channels induced by Bell-type correlations. In each round, a two-level working system is thermalized with a degenerate Hamiltonian, so that its physical microstate is a uniform classical bit. A trusted referee embeds this bit into a finite two-player XOR game, and a correlation resource produces a compressed controller bit. The controller uses only this compressed bit as side information for feedback. The construction is formulated first for arbitrary finite XOR games. The referee encoding makes the game-winning event equivalent to correct prediction of the physical microstate. Consequently, the induced side-information channel is binary symmetric, with success probability equal to the XOR-game winning probability of the supplied behaviour. The reversible Szilard feedback value is therefore fixed by the mutual information between the microstate and the controller record. Optimizing over local, quantum, and nonsignalling behaviour sets turns the corresponding game values into local, quantum, and nonsignalling thermodynamic ceilings. The construction is an effective-channel valuation, not a claim that Bell nonlocality is thermodynamic fuel. The controller receives only the compressed prediction bit, not the auxiliary variables that define the game. The thermodynamic costs of the referee, the correlation resource, and the preprocessing are not included. When controller-memory reset is included in a full cycle, the net work is non-positive, consistently with the second law.

02.
arXiv (CS.LG) 2026-06-18

Reinforcement Learning for Accelerated Aerodynamic Shape Optimisation

arXiv:2507.17786v2 Announce Type: replace Abstract: We introduce a reinforcement learning (RL) based adaptive optimization algorithm for aerodynamic shape optimization focused on dimensionality reduction. The form in which RL is applied here is that of a surrogate-based, actor-critic policy evaluation MCMC approach allowing for temporal 'freezing' of some of the parameters to be optimized. The goals are to minimize computational effort, and to use the observed optimization results for interpretation of the discovered extrema in terms of their role in achieving the desired flow-field. By a sequence of local optimized parameter changes around intermediate CFD simulations acting as ground truth, it is possible to speed up the global optimization if (a) the local neighbourhoods of the parameters in which the changed parameters must reside are sufficiently large to compete with the grid-sized steps and its large number of simulations, and (b) the estimates of the rewards and costs on these neighbourhoods necessary for a good step-wise parameter adaption are sufficiently accurate. We give an example of a simple fluid-dynamical problem on which the method allows interpretation in the sense of a feature importance scoring.

03.
arXiv (CS.AI) 2026-06-12

EA-WM: Event-Aware World Models with Task-Specification Grounding for Long-Horizon Manipulation

arXiv:2606.13053v1 Announce Type: cross Abstract: Pretrained-feature world models provide a useful substrate for robot imagination, but visual or latent prediction alone does not determine whether an imagined future satisfies task-relevant events. Long-horizon manipulation requires progress signals that are relational, predicate-level, and physically grounded: whether an object has moved, whether a drawer or contact state has changed, whether a placement predicate is satisfied, and whether a candidate future is reliable enough for execution. We introduce EA-WM, an event-aware world-model framework that augments frozen visual-feature dynamics with task-specification-grounded event prediction and verification. EA-WM rolls out candidate futures in pretrained visual-feature space, decodes them into structured event states, and scores them using task-progress, semantic-consistency, physical-feasibility, and uncertainty terms. The verifier guides sampling-based planning, gates candidate actions, and, in the contact-sensitive LIBERO wine-rack setting, selects among PPOgenerated proposals. Across navigation, deformable-object, wall-constrained, and languagedescribed manipulation studies, EA-WM shows that event-aware verification can make featurespace world models more interpretable and better aligned with task progress.

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

SceneCompleter: Dense 3D Scene Completion for Generative Novel View Synthesis

Generative models have shown great promise for novel view synthesis (NVS) by leveraging strong image generation priors. However, existing approaches typically follow a 2D inpainting paradigm, first completing missing image regions and then performing 3D reconstruction. This strategy often causes geometry distortion and appearance drift, as 2D inpainting models cannot reliably infer the underlying 3D structure required for cross-view consistent generation. In this paper, we propose SceneCompleter, a geometry-aware framework that reformulates generative NVS as dense 3D scene completion. Instead of hallucinating isolated 2D views, SceneCompleter jointly completes geometry and appearance through a geometry-appearance dual-stream diffusion model in a spatially aligned RGBD latent space. To provide holistic scene context, we further introduce a Scene Embedder that conditions generation on global semantic and stylistic information from reference images. The completed RGBD predictions are then aligned and integrated into an expandable 3D scene representation, enabling iterative and coherent scene completion. Extensive experiments on in-domain and out-of-distribution datasets demonstrate that SceneCompleter produces visually plausible and geometrically consistent novel views across diverse scenarios. Project Page: https://chen-wl20.github.io/SceneCompleter

05.
arXiv (quant-ph) 2026-06-19

Vine Codes: Low-Overhead Quantum LDPC Codes on a Planar Square Grid

arXiv:2606.20263v1 Announce Type: new Abstract: The surface code is a promising route towards large-scale quantum computing, requiring only nearest-neighbour gates amenable to superconducting hardware. However, surface codes incur large qubit overheads. Novel quantum low-density parity check (qLDPC) codes promise to reduce overheads but require long-range connections that are difficult to achieve on superconducting platforms. Here, we introduce "Vine Codes" - qLDPC codes that are implementable on a planar square grid through nearest-neighbour, two-qubit gates native to superconducting platforms (iSWAP and CZ). Our approach generalises "Directional Codes" recently introduced by Gehér et. al. (2025) which are constrained to a torus. In contrast, vine codes have open boundary conditions constructed with the aid of routing qubits. We perform extensive numeric searches and find promising candidate vine codes, e.g. [[121,4,6]], [[221,6,7]], and [[234,9,6]] codes. We verify the circuit distances and show that data and measure qubits required can be reduced by up to ~28% relative to the surface code at a circuit distance of 7. Even including routing qubits, vine codes require fewer total qubits than the surface code (e.g. ~18% reduction at circuit distance 10) and benefits are expected to increase at higher distances. We perform circuit-level noise simulations to demonstrate that under a realistic noise model and at a near-term noise rate of $10^{-3}$, vine codes can perform better than the surface code while using fewer qubits. We give an exhaustive list of all unique vine codes up to stabiliser-weight 9. We additionally introduce "Flip-Vine Codes" which possess single-qubit transversal Clifford gates useful for fault-tolerant logic and magic state cultivation. We furthermore construct examples of generalised open boundaries for vine codes that go beyond the familiar X/Z boundaries of the surface and tile codes.

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

A Generalizable Light Transport 3D Embedding for Global Illumination

Global illumination (GI) is essential for realistic rendering but remains computationally expensive due to the complexity of simulating indirect light transport. Recent neural methods have mainly relied on per-scene optimization, sometimes extended to handle changes in camera or geometry. Efforts toward cross-scene generalization have largely stayed in 2D screen space, such as neural denoising or G-buffer based GI prediction, which often suffer from view inconsistency and limited spatial understanding. We propose a generalizable 3D light transport embedding that approximates global illumination directly from 3D scene configurations, without using rasterized or path-traced cues. Each scene is represented as a point cloud with geometric and material features. A scalable transformer models global point-to-point interactions to encode these features into neural primitives. At render time, each query point retrieves nearby primitives via nearest-neighbor search and aggregates their latent features through cross-attention to predict the desired rendering quantity. We demonstrate results on diffuse global illumination prediction across diverse indoor scenes with varying layouts, geometry, and materials. The embedding trained for irradiance estimation can be quickly adapted to new rendering tasks with limited fine-tuning. We also present preliminary results for spatial-directional radiance field estimation for glossy materials and show how the normalized field can accelerate unbiased path guiding. This approach highlights a path toward integrating learned priors into rendering pipelines without explicit ray-traced illumination cues.

07.
arXiv (CS.AI) 2026-06-16

Token Reduction Should Go Beyond Efficiency in Generative Models – From Vision, Language to Multimodality

arXiv:2505.18227v4 Announce Type: replace-cross Abstract: In Transformer architectures, tokens\textemdash discrete units derived from raw data\textemdash are formed by segmenting inputs into fixed-length chunks. Each token is then mapped to an embedding, enabling parallel attention computations while preserving the input's essential information. Due to the quadratic computational complexity of transformer self-attention mechanisms, token reduction has primarily been used as an efficiency strategy. This is especially true in single vision and language domains, where it helps balance computational costs, memory usage, and inference latency. Despite these advances, this paper argues that token reduction should transcend its traditional efficiency-oriented role in the era of large generative models. Instead, we position it as a fundamental principle in generative modeling, critically influencing both model architecture and broader applications. Specifically, we contend that across vision, language, and multimodal systems, token reduction can: (i) facilitate deeper multimodal integration and alignment, (ii) mitigate "overthinking" and hallucinations, (iii) maintain coherence over long inputs, and (iv) enhance training stability, etc. We reframe token reduction as more than an efficiency measure. By doing so, we outline promising future directions, including algorithm design, reinforcement learning-guided token reduction, token optimization for in-context learning, agentic framework design, and broader ML and scientific domains.

08.
arXiv (CS.AI) 2026-06-11

Libra: Efficient Resource Management for Agentic RL Post-Training

arXiv:2606.03077v2 Announce Type: replace-cross Abstract: Reinforcement learning (RL) has emerged as a standard post-training paradigm for shaping large language models (LLMs) into capable agents. In agentic RL, the rollout stage generates trajectories while invoking tools, producing long-tailed and non-stationary workloads that expose two fundamental challenges in resource management. First, due to the long-tail distribution, a small fraction of trajectories dominates rollout makespan. Second, rollout and training are subject to cross-stage imbalance, as they exhibit strong asymmetry in compute patterns, memory demands, and sensitivity to sequence length. Compounding this asymmetry, the sequence length distribution drifts continuously as the policy evolves, rendering any static resource split progressively suboptimal. We present Libra, a resource management system to address both challenges via two core mechanisms. The first is a global resource planner that jointly optimizes GPU allocation across rollout and training clusters. It leverages an elastic hybrid pool to enable lightweight, non-blocking worker reallocation between stages. The second is a causality-driven multi-level feedback queue (C-MLFQ) scheduler, which routes requests to heterogeneous rollout buckets based on causal signals derived from tool-return outcomes, rather than relying on fragile length predictions. Evaluated on 48 A800 GPUs, Libra achieves up to 3.0x higher throughput and converges up to 2.5x faster in reward compared to the baselines.

09.
arXiv (CS.CV) 2026-06-16

Towards Global AI-Driven Cervical Cancer Screening

The global elimination of cervical cancer is a key public health goal set by the World Health Organization (WHO), with screening programs reducing mortality by up to 80%. However, access to experts and biopsy services is limited in low- to middle-income countries (LMICs). Deep learning (DL)-based algorithms offer promising support for screening, but most existing approaches have been developed and validated on private datasets from single countries. We present the first DL-based approach to cervical cancer screening validated on data from multiple countries. Technically, we phrase the problem of detecting and classifying lesions in colposcopy images as a multi-task learning problem, in which we simultaneously perform image-level classification and lesion segmentation. Our model was trained on a private data set of acid stain colposcopy images with manually generated lesion segmentation masks and corresponding histopathological results, employing extensive data augmentation to address image variability. In an in-distribution validation with pathology results serving as ground truth, our algorithm outperformed medical experts (Balanced Accuracy: 0.68 vs 0.64) in CIN1- (Cervical intraepithelial neoplasia grade 1 or lower) versus CIN2+ (grade 2 or higher) classification. External validation on four colposcopy data sets from four countries featuring radical differences in prevalence and patient characteristics yielded superior performance of our method compared to baseline methods. Performance variability across countries was high with AUC values ranging from 0.54 - 0.80. Overall, algorithm performance varied with age, transformation zone (cervical area most prone to lesion development), presence of comorbidities and pathognomonic signs, with comorbidities having by far the largest negative effect. Future work should focus on improving model robustness and generalizability.

10.
medRxiv (Medicine) 2026-06-22

Mapping abstraction and metacognition onto distinct transdiagnostic symptom profiles

Transdiagnostic psychiatric research on reward-guided learning has largely focused on simple associative processes, leaving it unclear whether or how higher-level processes are disrupted. Here, we studied how abstraction, the ability to extract relevant features from complex information, and metacognition, the ability to monitor and evaluate one's own mental processes, map onto specific transdiagnostic dimensions. Using an online sample (N = 249), we examined associations between these processes and three cross-culturally robust transdiagnostic dimensions derived from a large existing dataset (N = 19,505): Compulsive hypersensitivity, Social withdrawal, and Addictive behaviours. Computational modelling of an abstract representation learning task with confidence judgments revealed that Compulsive hypersensitivity was negatively associated with both abstraction ability (pboot = 0.003) and metacognitive sensitivity (pboot = 0.005), while Social withdrawal was positively associated with metacognitive sensitivity alone (pboot = 0.002). Moreover, transdiagnostic dimensions revealed more coherent associations with higher-order cognition than symptom-level analyses, highlighting the added value of examining psychopathology at the factor rather than the symptom level. These findings portray a hierarchical view of cognitive dysfunctions in psychopathology and point to representational and metacognitive processes as potential targets for transdiagnostic intervention.

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

Automatic Part-of-Speech Tagging of Arabic-English Dictionary Senses through WordNet

This paper proposed an algorithm for part-of-speech (POS) tagging senses of a bilingual dictionary. The algorithm is applied on the Al-Mawrid Arabic-English dictionary. The tagging task is accomplished by transferring the POS tags of the English translation equivalences (TEs) to the dictionary senses after dis-ambiguities process. The English POS tags of senses are acquired from the Princeton WordNet. POS tagging of bilingual dictionary senses is prerequisite to link a bilingual dictionary to WordNet and/or standardizing that dictionary into WordNet-LMF format where the synset (set of synonyms), not word, is the basic brick. The registered accuracy is high though the cost is little. Building NLP/HLT tools needs linguistic experts, large investments, and long time. For statistical approach, we need large annotated corpora and for rule-based approach, we need large lexicon that contains rich linguistic and world knowledge. That motivates the appearance of what are called resource-light approaches to develop natural language processing (NLP) tools for poor-resource languages.

12.
medRxiv (Medicine) 2026-06-23

Timing of S. aureus-related mortality in a large randomized clinical trial: Implications for future study design

Background: Longer follow-up periods in clinical trials for S. aureus bacteremia (SAB) may capture unrelated deaths, adding random noise that risks biasing trial results towards the null. Objective: To evaluate the timing and infection-relatedness of deaths within a large SAB clinical trial platform. Design: Blinded duplicate adjudication of trial deaths using a modified 7-point Likert-Scale. A third reviewer settled disagreements. Setting: 37 Canadian hospitals participating in the S. aureus Network Adaptive Platform (SNAP) Trial. Participants: 1515 adult patients recruited to SNAP between February 2022 and May 2026. Measurements: Timing and relatedness of 90-day deaths categorized as at least possibly SAB-related not likely to be SAB-related. Optimal follow-up cut-off was determined using Youden's index and graphically. Results: 247 deaths occurred; 97 (39.3%) were adjudicated as at least possibly SAB-related and 150 (60.7%) as not likely related. For probably/definitely related deaths, interrater agreement was 85.0% (Gwet's AC 0.73, substantial); for at least possibly related, it was 77.3% (Gwet's AC 0.55, moderate). Median survival was significantly shorter for SAB-related deaths (12 vs. 30.5 days; difference: 19 days earlier, 95% CI: 12-26, p

13.
arXiv (CS.CV) 2026-06-25

Hypergraph Normal World Models for Logical Visual Anomaly Detection

Visual anomaly detection is often deployed with only normal training images. Most one-class detectors map test patches or features to a normal reference distribution. This works well for local structural defects. Logical anomalies are different. Each visible part may look normal, while the whole image violates a normal count, co-occurrence, or spatial relation. This paper studies whether a model can learn such a category-specific normal world from nominal images alone. We propose the Hypergraph Normal World Model, a normal-only detector that distills frozen DINOv2 patch tokens into patch, relation, and hypergraph statistics. It builds spatial hyperedges over token groups. It then scores each test image with an information quotient that separates local, relational, hyperedge, and hyperedge-relation evidence. On the available MVTec LOCO breakfast-box validation data, the full hypergraph model improves logical anomaly AUROC from 0.8434 for DINOv2 patch-kNN to 0.9279. It also improves over the non-hypergraph variant, from 0.9013 to 0.9279. Few-shot experiments show that the model remains effective with very limited normal images. We also test whether the score reflects normal-world knowledge rather than a shallow mapping. t-SNE separates logical anomalies in the learned energy space. Relation counterfactuals increase the information quotient by 83.13 on average. Random hypergraphs reduce logical AUROC, and hyperedge attribution is much larger on logical anomalies. Qualitative examples show that high scores are driven by relation-bearing terms. These results suggest that logical visual anomaly detection should model normal relations, not only normal local patches.

14.
arXiv (CS.CL) 2026-06-16

Depth-Attention: Cross-Layer Value Mixing for Language Models

Self-attention selects information freely across the sequence, but across depth, Transformers merely add each layer's output to the residual stream, so later layers cannot selectively reuse earlier-layer representations. Recent cross-layer methods improve this flow but operate on hidden states outside attention, adding state beyond the key-value cache at inference–a cost that becomes increasingly salient as modern LLMs compress the cache with grouped-query and multi-head latent attention. We introduce Depth-Attention, which performs this selection inside the attention module itself: before a layer attends over the sequence, its query attends over the keys of earlier layers at the same token position and mixes their values into the value that self-attention then reads. Because Depth-Attention reuses the standard attention queries, keys, and value-cache slots, storing depth-mixed values in place of the original values, it adds no parameters and introduces no persistent inference state beyond the standard key-value cache–the same cache size as a vanilla decoder and less than hidden-state-based cross-layer methods. On Qwen3-style decoders at 1.5B and 3B parameters, Depth-Attention attains the lowest perplexity and the highest average downstream accuracy, improving over the vanilla Transformer by up to 2.3 accuracy points and surpassing strong cross-layer baselines in perplexity and average accuracy, while adding under 0.01% extra arithmetic FLOPs and no additional persistent inference state. The gains hold from 360M to 3B parameters and extend to looped Transformers.

15.
arXiv (CS.LG) 2026-06-17

Provably Efficient Regularized Online RLHF with Generalized Bilinear Preferences

arXiv:2602.23116v3 Announce Type: replace Abstract: We consider the problem of regularized best-response max-regret minimization in online RLHF under general preferences and bandit feedback. While various regularizers are utilized to robustify alignment, known polylogarithmic regret guarantees remain heavily specific to KL. To investigate whether such fast rates extend beyond KL, we adopt the Generalized Bilinear Preference Model (GBPM) – capturing intransitive preferences over $d$-dimensional item-wise features via a rank-$2r$ skew-symmetric matrix – to isolate the impact of generic regularization. Crucially, under GBPM, we prove that the dual gap of any greedy policy is bounded by the squared estimation error, derived using only strong convexity and skew-symmetry. Under a feature coverage assumption, we establish a generic polylogarithmic regret of $\tilde{\mathcal{O}}(\eta d^4 C_{\min}^{-1} (\log T)^2 \wedge d^2 C_{\min}^{-1/2} \sqrt{T})$ with Greedy Sampling, and a dimension-wise improved regret (for well-conditioned arm-sets) of $\tilde{\mathcal{O}}(C_{\min}^{-2} \sqrt{\eta r T} \wedge r^{1/3} C_{\min}^{-4/3} T^{2/3})$ with Explore-Then-Commit, where $\eta^{-1}$ is the regularization coefficient, $T$ is the time horizon, and $C_{\min}$ is an arm-set dependent quantity. This demonstrates that ``fast'' regrets are not KL-specific, but rather a fundamental consequence of generic strongly convex geometry.

16.
arXiv (CS.LG) 2026-06-11

Bootstrapped Monitoring: Leveraging Transparent Reasoning to Oversee Stronger AI Agents

arXiv:2606.11998v1 Announce Type: new Abstract: Trusted monitoring is a cornerstone of AI control. However, as frontier models grow more capable, the increasing capabilities gap between trusted and untrusted models may render trusted models unreliable monitors. We introduce bootstrapped monitoring, a protocol that addresses this by inserting a stronger, intermediate untrusted model with transparent chain-of-thought reasoning into the oversight chain. The untrusted monitor ($U_m$) evaluates the agent's actions, while a weaker trusted model ($T$) oversees $U_m$'s reasoning to detect collusion. We evaluate bootstrapped monitoring on multi-turn software engineering tasks (BashArena) across multiple agents and monitors. Bootstrapped monitoring substantially improves catch rates over trusted-only monitoring, even when the untrusted monitor actively colludes with the agent, provided we have access to its raw chain-of-thought. Our results suggest that bootstrapped monitoring can extend the useful lifetime of trusted models in control as AI capabilities advance.

17.
arXiv (CS.LG) 2026-06-25

Blasto-Net: An Explainable Multi-Task Learning for Blastocyst Segmentation, Grading, and Implantation Prediction

arXiv:2606.25463v1 Announce Type: cross Abstract: This study introduces Blasto-Net, a multi-task deep learning model for comprehensive blastocyst analysis. The proposed model performs three tasks simultaneously in a single forward pass: segmentation of the ZP, TE, and ICM compartments, morphological grading, and implantation outcome prediction. Accurate blastocyst analysis in in vitro fertilization (IVF) is challenging. The compartments often have similar textures but very different structures. To address these challenges, Blasto-Net employs an EfficientNet-B3 encoder with a UNet-style decoder enhanced by the Convolutional Block Attention Module (CBAM) and a novel Edge-Aware Attention Module (EAAM) to effectively capture both semantic and boundary information. To handle distinct compartment topologies, the network employs specialized segmentation heads and a composite region- and boundary-based loss. Additionally, Grad-CAM++ visualizations are used to verify the anatomical consistency of the model's predictions. Evaluated on a public HMC blastocyst dataset, Blasto-Net achieves Dice scores of 94.93%, 91.60%, and 88.82% for ICM, ZP, and TE, respectively, alongside an implantation F1-score of 80.0%. These results demonstrate that Blasto-Net offers an accurate, interpretable, and efficient solution for automated blastocyst assessment, with strong potential to support clinical decision-making in IVF.

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

Do as the Romans Do: Learning Universal Behaviors from Heterogeneous Agents

arXiv:2606.18537v1 Announce Type: new Abstract: Humans often acquire new skills by observing others, since observed behaviors implicitly reveal how to act in an environment. However, observations drawn from a heterogeneous population introduce conflicting behavioral signals, making it difficult to determine which behaviors are worth imitating. We address this challenge with General Reward Inference and Disentanglement (GRID), a social learning method that extracts universally useful behaviors from a heterogeneous population of demonstrators pursuing different goals. GRID decomposes per-agent reward functions into a general reward, capturing behaviors shared across all agents, and specific rewards, capturing individual preferences and objectives. Training exclusively on the general reward provides a new paradigm of generalist pretraining. It yields a generalist agent that internalizes universal environmental competencies, such as safety and basic task proficiency, without the mode-averaging bias that afflicts standard learning from demonstration techniques. This generalist serves as a superior prior for fine-tuning to downstream tasks, including preferences unseen during training. Experiments across a synthetic basis function decomposition, multi-agent Craftax, and a continuous autonomous driving simulator (Highway-Env) confirm that GRID successfully disentangles reward structure in a semantically meaningful way, outperforms standard learning from demonstration baselines, and enables more efficient and stable specialization.

20.
arXiv (CS.AI) 2026-06-24

CompressKV: Semantic-Retrieval-Guided KV-Cache Compression for Resource-Efficient Long-Context LLM Inference

arXiv:2606.24467v1 Announce Type: new Abstract: Long-context large language model (LLM) inference is increasingly constrained by the memory footprint and decoding cost of key-value (KV) caches, limiting sustainable deployment on resource-constrained hardware. Existing KV cache eviction methods typically apply heuristic token scoring over all heads in GQA-based LLMs. These methods ignore the different functionalities of attention heads, leading to the eviction of critical tokens and thus degrading the performance of LLMs. To address this issue, we propose CompressKV, a resource-efficient KV-cache compression framework for GQA-based LLMs. Instead of aggregating attention scores from all heads, CompressKV identifies Semantic Retrieval Heads (SRHs) that capture both the initial and final tokens of a prompt and semantically important mid-context evidence, and uses them to select tokens whose KV pairs should be retained. Furthermore, CompressKV allocates cache budgets across layers according to offline estimates of layer-wise eviction error. Experiments on LongBench and Needle-in-a-Haystack show that CompressKV consistently outperforms existing KV-cache eviction methods across memory budgets. Notably, it preserves over 97\% of full-cache performance using only 3\% of the KV cache on LongBench question-answering tasks and achieves 90\% accuracy with just 0.7\% KV storage on Needle-in-a-Haystack. These results demonstrate an improved resource–performance trade-off for long-context LLM inference. Our code is publicly available at: https://github.com/TUDa-HWAI/CompressKV

21.
arXiv (CS.AI) 2026-06-24

An Introduction to Causal Reinforcement Learning

arXiv:2606.24160v1 Announce Type: new Abstract: Causal inference provides a set of principles and tools that allow one to combine data and knowledge about an environment to reason with questions of counterfactual nature, i.e., what would have happened had reality been different, even when no data of this unrealized reality is currently available. Reinforcement learning provides methods to learn a policy that optimizes a specific measure (e.g., reward, regret) when the agent is deployed in an environment and pursues an exploratory, trial-and-error approach. These two disciplines have evolved independently and with virtually no interaction between them. We note that they operate over different aspects of the same building block, counterfactual relations, which makes them umbilically connected. Based on these observations, novel learning opportunities arise when this connection is explicitly acknowledged and mathematized. To realize this potential, we note that any environment where the RL agent is deployed can be decomposed as a collection of autonomous mechanisms with different causal invariances, parsimoniously modeled as a structural causal model; any standard RL setting implicitly encodes such a model. This formalization allows us to put under a unifying treatment different modes of learning, including online, off-policy, and causal calculus learning, which appear unrelated in the literature. However, these modalities are not exhaustive: we introduce several natural and pervasive classes of learning settings that entail novel dimensions of analysis. Specifically, we introduce and discuss through causal lenses generalized policy learning, where to intervene, imitation learning, and counterfactual learning. These tasks lead to a broader view of counterfactual learning and suggest great potential for studying causal inference and reinforcement learning side by side, which we call causal reinforcement learning (CRL).

22.
arXiv (quant-ph) 2026-06-19

A Finite-Volume Scheme for the Continuum Extrapolation of Lattice Step-Scaling in (2+1)D Hamiltonian U(1) Gauge Theory

arXiv:2606.20029v1 Announce Type: cross Abstract: We propose a finite-volume scheme to perform controlled continuum extrapolations of the lattice step-scaling function, a key ingredient for determining the running coupling in a Hamiltonian lattice gauge theory in small volumes. As a testbed, we employ a dual Hamiltonian formulation of pure U(1) gauge theory in (2+1) dimensions and an operator basis that remains efficient toward weak coupling. We describe the implementation of static external charges on the spatial lattice and study, using matrix product states, the resulting confining string, from which we extract the static potential and a force-based renormalized coupling. Using the proposed finite-volume scheme, we demonstrate a stable continuum limit of the step-scaling function on the lattice sizes accessible to present Hamiltonian simulations. The method is readily extendable to other gauge groups and dimensions, providing a pathway toward Hamiltonian step-scaling studies in other theories.

23.
arXiv (CS.AI) 2026-06-18

Where Did the Variability Go? From Vibe Coding to Product Lines by Regeneration

arXiv:2606.19042v1 Announce Type: cross Abstract: In vibe coding, an emerging AI-driven paradigm, an LLM generates an entire program from a natural language prompt, but what happens to the variability that traditional software engineering carefully builds into code? To answer this question, we conducted an exploratory analysis on 10 vibe coded C/C++ projects, which suggests that there is near-zero in-artifact variability, i.e., at compile and runtime. All variability decisions are resolved at a single new binding time, generation time, the moment the LLM produces the source code. Rather than treating this as a defect to fix, we propose Variability by Regeneration (VbR), to our knowledge the first product-line approach in which the LLM acts as the derivation engine, generating a purpose-built, free of dead code binary for each variant from a declarative specification, while a variant dispatcher transparently routes user requests to the matching binary. We formalise VbR, contrast it with classical SPL derivation, and demonstrate its full pipeline on a wc product family. For SPL engineering, variability in AI-generated software belongs in the specification, not in the code.

24.
arXiv (math.PR) 2026-06-17

Moment generating function of the tacnode process

Authors:

arXiv:2606.17771v1 Announce Type: cross Abstract: The tacnode process is a universal determinantal point process arising in non-intersecting particle systems and random tiling models. In this paper, we study the generating function for the counting functions of the tacnode process on a union of $m$ intervals, $m\in\mathbb{N}^{+}$. Our first result provides an integral representation for the $m$-point generating function in terms of the Hamiltonian governing a system of $8m+4$ coupled differential equations. Combined with several differential identities for this Hamiltonian, the representation yields the large gap asymptotics, up to and including the constant term. As further applications, we obtain asymptotic formulae for the expectations, variances, and covariances of the counting functions, and establish a central limit theorem for their joint fluctuations. These results extend the previously known $1$-point theory for the tacnode process to the multi-interval setting with multiple discontinuities.

25.
arXiv (CS.AI) 2026-06-12

Counterfactual Credit Policy Optimization for Multi-Agent Collaboration

arXiv:2603.21563v5 Announce Type: replace Abstract: Collaborative multi-agent large language models (LLMs) can solve complex reasoning tasks by decomposing roles, but reinforcement learning for such systems is limited by credit assignment: shared terminal rewards obscure individual contributions and can encourage free-riding. We introduce two optimizer-agnostic credit assignment methods for converting joint outcomes into agent-specific learning signals. Counterfactual Credit for Policy Optimization (CCPO) estimates an agent's marginal contribution by comparing the realized joint outcome with a counterfactual outcome where that agent is removed. Self-Evaluated Credit for Policy Optimization (SEPO) uses constrained self- and peer-evaluations as a verifier-anchored credit signal while keeping the external task outcome dominant. Both operate at the reward-construction layer rather than as policy optimizers, producing role-specific rewards or advantages for GRPO, GSPO, or REINFORCE++. We instantiate these credit signals in a sequential Think–Solve setting and evaluate them on mathematical reasoning benchmarks. Results show that explicit credit assignment often improves dual-agent reasoning, especially on MATH500 and several out-of-distribution settings, while gains vary across models and datasets. Our code is available at: https://github.com/bhai114/ccpo.