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.LG) 2026-06-15

High-Frequency Pricing at Scale for E-Commerce

Authors:
Stefan Birr↗Tobias Huelden↗Mones Raslan↗Adele Gouttes↗Andreas Schmitt↗Mateusz Koren↗Johannes Stephan↗Robert Streek↗Manuel Kunz↗Tim Januschowski↗

arXiv:2606.13741v1 Announce Type: new Abstract: This paper presents the design, development, and implementation of a specialized forecast-then-optimize algorithmic pricing tool for sales campaigns in fashion e-commerce. Sales events present unique challenges for pricing including volatile demand patterns, rapid pricing decisions, and the need to balance short-term revenue with long-term profitability. We describe our approach combining daily-resolution demand forecasting using gradient-boosted trees with a multi-objective optimization framework that maximizes both long-term profit and net merchandise value for more than 5 million articles. Our solution addresses key limitations of existing weekly-granularity systems by implementing a forecast-then-optimize architecture that reduces pricing decision time from hours to minutes. We validate our approach through 23 A/B tests across 12 markets during 2023-2024 sales campaigns at Zalando, one of Europe's leading online fashion retailers. Experimental results demonstrate that the new pricing system achieves approximately 6% higher profit while maintaining equivalent performance on sales and revenue compared to the previous manual-algorithmic hybrid approach. Based on these results, the algorithm was successfully deployed to production and now handles the majority of algorithmic pricing decisions for sales campaigns at the company.

Read & Discuss → View Source →
02.
arXiv (CS.CV) 2026-06-19

Exploring Multi-Modal Large Language Models and Two-Stage Fine-Tuning for Fashion Image Retrieval

Authors:
Nguyen Cao Hoang↗Hoang Bui Le↗Nam Vo Hoang↗Trung-Nghia Le↗

Composed image retrieval retrieves a target image using a composed query of a reference image and a modified text description. In the fashion domain, this task requires understanding subtle attribute variations such as color, pattern, and texture. However, existing approaches face limitations due to scarce annotated data and simplistic negative sampling. We propose a novel framework that integrates a multi-modal large language model (LLaVA) to generate attribute-aware triplets and introduces a two-stage fine-tuning strategy to enhance contrastive learning. We leverage pretrained vision-language models, such as CLIP-ViT/B32, to generate and concatenate sentence-level prompts with the relative caption and to scale the number of negatives using static representations. Experimental results demonstrate enhanced compositional reasoning and improved fine-grained retrieval behavior, underscoring the feasibility and potential of the proposed framework for fashion retrieval.

Read & Discuss → View Source →
03.
arXiv (CS.CL) 2026-06-15

CORA: Analyzing and bridging thinking-answer gap in Multimodal RLVR via Consistency-Oriented Reasoning Alignment

Authors:
Jiayue Cao↗Zhicong Lu↗Xuehan Sun↗Wei Jia↗Hongling Zheng↗Changyuan Tian↗Zichuan Lin↗Wenqian Lv↗Nayu Liu↗

Reinforcement learning with verifiable rewards (RLVR) has successfully elicited the reasoning capabilities of large language models, motivating its extension to multimodal scenarios. Existing methods primarily focus on improving the visual coverage of reasoning traces and mitigating visual hallucinations, but underestimate the semantic inconsistency between the reasoning process and the final answer. In this paper, we delve into thinking-answer inconsistency in RLVR for large vision-language models (LVLMs), showing thorough analyses of rollouts collected throughout Group Relative Policy Optimization (GRPO) training process and post-RLVR evaluation outputs that this issue persists during training and remains present during inference. Motivated by the analysis, we propose Consistency-Oriented Reasoning Alignment (CORA), which introduces thinking-answer semantic consistency into RLVR through a lightweight plug-and-play consistency reward model, and further incorporates Hybrid Reward Advantage Splitting (HRAS) to stably coordinate task and consistency optimization. Extensive experiments across representative multimodal reasoning benchmarks and mainstream LVLMs show that CORA improves task performance while effectively mitigating thinking-answer inconsistency, leading to more faithful reasoning traces.

Read & Discuss → View Source →
04.
arXiv (CS.CL) 2026-06-15

EiCAP: Beyond Fluency, Probing and Improving Emotional Intelligence in LLMs via Psychologically Grounded Multi-Turn Dialogue

Authors:
Nizi Nazar↗Pardis Sadat Zahraei↗Dilek Hakkani-T\"ur↗Natasa Milic-Frayling↗Ehsaneddin Asgari↗

Large Language Models increasingly serve in emotionally sensitive roles, including mental health support, education, and crisis response, yet they lack a principled framework for assessing or improving Emotional Intelligence (EI). We introduce EiCAP, a unified, psychologically grounded six-layer EI taxonomy operationalized into two complementary resources. EiCAP-Bench is a multi-turn, one-vs-three forced-choice evaluation suite with 3,174 probes across 24 subcategories and cross-turn dependencies that reflect real conversational EI demands. EiCAP-SFT is a 152,820-dialogue supervision corpus aligned to the same taxonomy, enabling controlled, interpretable fine-tuning. Two key findings emerge. First, generic conversational supervised fine-tuning does not confer EI: fine-tuning on UltraChat yields no significant gain in any of the 24 subcategories, with a macro score of 24.6%, near the chance level of 25%. Second, applying EI-grounded LoRA, using approximately 0.8% of parameters, directly to Qwen-2.5-7B-Base achieves significant gains in all 24 subcategories, reaching a macro score of 75.33%, a gain of 51.7 percentage points over Base and 37.1 percentage points over Instruct. Crucially, an ablation shows that the UltraChat pre-stage is counterproductive, reducing performance by 21.4 percentage points: direct EI-grounded training is both necessary and sufficient.

Read & Discuss → View Source →
05.
arXiv (quant-ph) 2026-06-15

Quantum gates with parametrically driven multi-qubit couplers

Authors:
Verena Feulner↗Marjan Fani↗Lukas Heunisch↗Stephan Tasler↗Michael J. Hartmann↗

arXiv:2606.14522v1 Announce Type: new Abstract: Superconducting quantum processors could significantly profit from enhanced connectivity together with precise control of interactions and gates between qubits. Here we investigate plaquettes of four qubits that are coupled via a central tunable coupling circuit, so that not only gates between qubits connected by an edge of the plaquette can be executed but also between qubits across the diagonal. By numerically and analytically analyzing parametrically driven processes, we explore $\sqrt{iSWAP}$-gates between any pair of qubits, also across the diagonal, as well as three-qubit interactions and gates. For experimentally available circuit parameters, we for example find $\sqrt{iSWAP}$-gates with a gate time of 50 ns and 99.9\% fidelity, which is decreased to 99.4\% if two such gates are executed in parallel on disjoint qubit pairs in the plaquette. For three-qubit gates we find fidelities of 95\% fidelity at a gate time of 200 ns.

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

Tacit Coordination of Large Language Models

Authors:
Ido Aharon↗Emanuele La Malfa↗Michael Wooldridge↗Sarit Kraus↗

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

Read & Discuss → View Source →
07.
arXiv (CS.CL) 2026-06-15

CacheRL:Multi-Turn Tool-Calling Agents via Cached Rollouts and Hybrid Reward

Authors:
Md Amirul Islam↗Sumiran Thakur↗Huancheng Chen↗Su Min Park↗Jiayun Wang↗Gyuhak Kim↗

We present CacheRL, a system for training small agent foundation models that achieves 92 percent process accuracy on multi-step tool-calling tasks, approaching GPT-5's 94 percent while requiring 100 times less compute. Our approach addresses three challenges in practical agent training: transferring tool-calling knowledge from large models at scale, enabling reinforcement learning without costly live tool execution, and learning robustly from noisy cached environments. CacheRL introduces three key innovations. First, a hybrid thinking trajectory pipeline augments agent trajectories with LLM-generated reasoning traces, producing training examples that teach models not only what tools to call but also why. Second, the CacheAgentLoop eliminates live execution costs through a three-tier fuzzy cache while preserving trajectory fidelity using token-level masking. Third, a cache-tier-aware reward dynamically adjusts answer-quality weights to avoid penalizing models for cache-induced limitations. Through iterative supervised fine-tuning (SFT) and Group Relative Policy Optimization (GRPO), CacheRL improves Qwen3-4B-Thinking's validation reward from 0.43 to 0.78. On public agentic tool-calling benchmarks, our model achieves competitive performance against frontier models such as GPT-5. Ablation studies show that removing knowledge transfer reduces performance by 41 percent, while cache-aware rewards contribute a 17 percent improvement. Interestingly, reinforcement learning improves training stability but yields limited gains beyond strong supervised fine-tuning, suggesting that data quality and reward design play a more important role than complex optimization methods in building practical small agent models.

Read & Discuss → View Source →
08.
arXiv (CS.CV) 2026-06-12

Iterative Visual Thinking: Teaching Vision-Language Models Spatial Self-Correction through Visual Feedback

Authors:
Animesh Tripathy↗Aswanth Krishnan↗

Vision-language models (VLMs) achieve strong singleshot spatial grounding, yet lack any mechanism to observe and correct their own predictions. We find that naively prompting a VLM to iterate over rendered visualizations of its predictions causes catastrophic failure: Acc@0.5 on referring expression comprehension collapses from 79.6% to 48.7% (a 31 percentage point drop), revealing a fundamental gap between grounding capability and self-correction ability. We propose Iterative Visual Thinking (IVT), a closed-loop framework in which the model predicts a bounding box, observes the prediction rendered on the image, and iteratively refines through visual feedback. A two-phase training recipe closes the self-correction gap: first, we exploit the base model's own predictions as realistic errors and prompt a teacher VLM to generate corrective reasoning traces, yielding supervised data without human annotation; second, we apply Group Relative Policy Optimization (GRPO) with a simple IoU reward to stabilize multi-step refinement. On a mixed benchmark spanning RefCOCOg, Ref-Adv, and Ref-L4 (505 test samples), SFT warm-up with IVT surpasses the single-shot base model on every metric: Acc@0.5 rises to 82.0% (+2.4pp), Acc@0.7 to 74.1% (+3.2pp), and Acc@0.9 to 48.3% (+2.8pp). GRPO further reduces per-step IoU degradation by 5x, stabilizing the refinement trajectory. All training uses only 2,400 samples on a single GPU, demonstrating that spatial self-correction is a learnable capability that can be instilled at modest scale.

Read & Discuss → View Source →
09.
arXiv (quant-ph) 2026-06-16

On-chip semi-device-independent quantum random number generator exploiting contextuality

Authors:
Maddalena Genzini↗Caterina Vigliar↗Mujtaba Zahidy↗Hamid Tebyanian↗Andrzej Gajda↗Klaus Petermann↗Lars Zimmermann↗Davide Bacco↗Francesco Da Ros↗

arXiv:2601.08392v2 Announce Type: replace Abstract: We present a semi-device-independent quantum random number generator (QRNG) based on the violation of a contextuality inequality, implemented by the integration of two silicon photonic chips. Our system combines a heralded single-photon source with a reconfigurable interferometric mesh to implement qutrit state preparation, transformations, and measurements suitable for testing a KCBS contextuality inequality. This architecture enables the generation of random numbers from the intrinsic randomness of single-photon interference in a complex optical network, while simultaneously allowing a quantitative certification of their security without requiring entanglement. We observe a contextuality violation exceeding the classical bound by more than 10{\sigma}, unambiguously confirming non-classical behavior. From this violation, we certify a conditional min-entropy per experimental round of Hmin = 0.077 +- 0.002, derived via a tailored semidefinite-programming-based security analysis. Each measurement outcome therefore contains at least 0.077 +- 0.002 bits of extractable genuine randomness, corresponding to an asymptotic generation rate of 21.7 +- 0.5 bits/s. These results establish a viable route towards general-purpose, untrusted quantum random number generators compatible with practical integrated photonic quantum networks.

Read & Discuss → View Source →
10.
arXiv (math.PR) 2026-06-17

Non-asymptotic Tail Bounds for the Kostlan–Shub–Smale Field: Tensor PCA and Spherical $k$-Spin Complexity

Authors:
Jean-Marc Aza\"is↗Federico Dalmao↗Yohann De Castro↗

arXiv:2606.17665v1 Announce Type: cross Abstract: This paper builds a hierarchy of explicit, non-asymptotic tail bounds for the supremum of the Kostlan–Shub–Smale (KSS) random field on the sphere, and applies it to two problems: Spiked Tensor PCA and the landscape of the spherical $k$-spin model. For Tensor PCA, we study the non-asymptotic statistical limits of estimating a rank-$R$ symmetric signal tensor of order~$k\ge 3$ and dimension~$d\ge 3$ from a single Gaussian observation at signal-to-noise ratio~$\lambda$, through the profile maximum likelihood estimator, the MLE restricted to normalized rank-$R$ tensors of coherence at least~$\kappa$. Our analysis uses a single reduction: a deterministic geometric inequality (the Tube Method) and a rank-reduction step bound the estimation error by the supremum of the canonical KSS field, which the Kac–Rice formula turns into a Gaussian integral against the expected absolute characteristic polynomial of a shifted Gaussian Orthogonal Ensemble, controlled in turn by the four explicit tail bounds of our hierarchy (three from a Mehta–Fyodorov representation, one from a Ben Arous–Dembo–Guionnet large deviation). The same reduction yields two results, each with explicit constants. For estimation, a finite-$(k,d)$ error bound recovers the asymptotically optimal rate~$\sqrt{d\log k}$ of Perry, Wein and Bandeira, with explicit dependence on the rank~$R$ and the coherence~$\kappa$. For the landscape, a two-sided non-asymptotic bracketing of the annealed complexity of the spherical $k$-spin Hamiltonian recovers the Auffinger–Ben Arous–\v{C}ern\'y complexity function in the high-dimensional limit.

Read & Discuss → View Source →
11.
arXiv (CS.LG) 2026-06-19

Multi-Task Bayesian In-Context Learning

Authors:
Qingyang Zhu↗Eric Karl Oermann↗Kyunghyun Cho↗

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

Read & Discuss → View Source →
12.
arXiv (CS.CL) 2026-06-17

ALAS: An Automatic Latent Alignment Score for Audio Language Models

Authors:
Pooneh Mousavi↗Yingzhi Wang↗Mirco Ravanelli↗Cem Subakan↗

Large Language Models (LLMs) are extended into Speech-LLMs, and the quality of the audio–text alignment they learn affects most downstream Spoken Language Understanding (SLU) behavior. Yet despite a growth of fusion strategies, there is no standard way to measure how well a Speech-LLM internally binds audio frames to text tokens. We introduce ALAS (Automatic Latent Alignment Score), a model and task-agnostic metric that probes the LLM's per-layer hidden states, scoring the cross-modal cosine similarity between audio and text representations against a Whisper-derived reference. ALAS needs only a frozen forward pass and an off-the-shelf ASR reference, with no training or fitted classifier, and is calibrated to an interpretable uniform baseline comparable across tasks. Applying ALAS to four open-source Speech-LLMs (AF3, Qwen2-Audio, Qwen-Omni, SALMONN) across emotion recognition (IEMOCAP), open-ended SQA (LibriSQA), and multi-choice audio understanding (MMAU-speech), we find that the depth and strength of alignment reflect each model's audio-encoder design and the acoustic-versus-semantic demands of the task, and that ALAS tracks but does not duplicate task accuracy, exposing models that score well without genuinely grounding in the audio. We release ALAS as an open-source library so that practitioners can probe their own Speech-LLMs or try it on new tasks.

Read & Discuss → View Source →
13.
arXiv (CS.CV) 2026-06-12

TetherCache: Stabilizing Autoregressive Long-Form Video Generation with Gated Recall and Trusted Alignment

Authors:
Yu Meng↗Xiangyang Luo↗Letian Li↗Wenyuan Jiang↗Chen Gao↗Xinlei Chen↗Yong Li↗Xiao-Ping Zhang↗

Autoregressive video diffusion models provide a natural formulation for streaming and variable-length video generation by conditioning newly generated frames on previously generated content. However, extending these models to minute-level generation remains challenging: the limited KV-cache budget prevents the model from retaining the full history, while repeatedly conditioning on self-generated frames induces a context distribution shift that accumulates over time, leading to visual artifacts, quality degradation, and temporal drift. In this paper, we propose TetherCache, a training-free and plug-and-play cache management strategy for drift-resistant long video generation. TetherCache organizes the cache into sink, memory, and recent regions, and introduces two complementary mechanisms. First, GRAB (Gated Recall with Attention-Diversity Balancing) selects long-range memory frames using a gated score that combines attention-based relevance with temporal diversity, preserving informative yet diverse historical context under a fixed cache budget. Second, TAME (Trusted Alignment via Memory Editing) lightly edits newly recalled memory tokens by aligning their statistics to a trusted context distribution, reducing the pollution caused by drifted historical features. Built on Self-Forcing, TetherCache consistently improves long-video generation quality on VBench-Long across 30s, 60s, and 240s settings. In particular, for 240s generation, it substantially improves overall and semantic scores while reducing quality drift from 7.84 to 1.33, demonstrating its effectiveness for stable long-horizon autoregressive video diffusion.

Read & Discuss → View Source →
14.
arXiv (CS.LG) 2026-06-19

SEAGAN: domain-Specific and Edge-Aware Graph Attention Network for Dynamic Plant Processes

Authors:
Antriksh Srivastava↗Soumyashree Kar↗

arXiv:2606.19623v1 Announce Type: new Abstract: Graph neural networks (GNNs) provide a flexible framework for learning from scientific data linked through physical, biological, or functional relationships. One promising domain is plant physiology, where measured responses often arise from multiple interacting processes whose exact separation remains difficult even with manual intervention. In plant physiology, a key example is the A-Ci curve, which relates net CO2 assimilation rate (Anet) to leaf intercellular CO2 concentration (Ci) and is used to estimate photosynthetic parameters in leaf and crop-canopy models. However, reliable estimation requires identifying the active biochemical limitation state at each curve point, which remains a major source of uncertainty. Here, we formulate limitation-state identification along A-Ci curves as a graph-based node classification problem, with curve points as nodes. Domain-specific graph representations are created using distance-based k-nearest-neighbor (kNN) and auxiliary-signal-guided (ASG) connectivity, with edge attributes encoding pairwise relations. The framework was evaluated against conventional learning baselines, graph-based architectures, and an automated fitting-based benchmark. Results on a large synthetic dataset with known ground-truth limitation states show that graph-based models improve classification, particularly near biochemical transition regions. The best-performing configuration, SEAGAN (domain-Specific and Edge-Aware Graph Attention Network for Dynamic Plant Processes), integrates process-aware node features, edge attributes, kNN connectivity, and graph attention with weighted cross-entropy loss, achieving an F1-score of 0.857 and an accuracy of 0.882. The results show that representing A-Ci curves as graphs improves biochemical limitation-state analysis, with edge-aware attention over local kNN neighborhoods providing the most effective strategy.

Read & Discuss → View Source →
15.
arXiv (quant-ph) 2026-06-12

Towards Geostrategic Critical Minerals and Materials Resilience: Secure Supply-Chain and Criticality Analyses for Quantum Technologies in Arctic and Space Environments

Authors:
Min-Ha Lee↗Alan J. Hurd↗Jolante Wieke Van Wijk↗Mauritz Kop↗

arXiv:2605.02926v2 Announce Type: replace-cross Abstract: This manuscript maps secure-supply and criticality risks for quantum technologies deployed in extreme environments, linking upstream critical minerals and materials (CMMs) to downstream system performance, continuity of security, and mission assurance. It adopts a reproducible "Critical Level I" screening method to identify materials whose supply concentration, essentiality, and limited mitigatability can create bottlenecks for quantum deployment. The analysis is structured around two use cases: (i) niobium as a key input for superconducting quantum computing and related manufacturing and toolchain dependencies; and (ii) space-qualified superconducting nanowire single-photon detectors (SNSPDs), alongside adjacent single-photon detector platforms such as SPADs, where radiation, thermal cycling, vibration, and electromagnetic interference can degrade device metrics and, in communications settings, threaten continuity of security. The manuscript further situates these dependencies within U.S.-China strategic competition over critical materials, refining capacity, export controls, and overseas mineral acquisitions, while also connecting them to standards-first governance, post-quantum cryptography migration, and the emerging security logic of quantum networking. It argues that static national critical-minerals lists are insufficient for mission-relevant quantum technology and proposes a dedicated Quantum Criticality and Critical Minerals (QCCM) dashboard as a living decision-support tool for tracking concentration, substitutability, qualification bottlenecks, stockpiling gaps, and geopolitical stress signals across quantum platforms. The paper concludes with implications for substitution, diversification, stockpiling, shielding, qualification-by-design, and standards-aligned governance to support secure, sustained, and mission-relevant quantum deployment.

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

Estimating Mutual Information between Time Series and Temporal Event Sequences Across Diverse Analysis Tasks

Authors:
Haoji Hu↗Huaqing Mao↗Yijun Lin↗Xiaowei Jia↗Jinwei Zhou↗Minoh Jeong↗Yao-Yi Chiang↗

arXiv:2606.01602v2 Announce Type: replace-cross Abstract: Pairwise dependence measures such as correlation and causality are fundamental to temporal data mining, yet there is still no principled and robust way to quantify dependence between heterogeneous data types, especially between continuous time series and discrete temporal event sequences. Existing approaches rely on ad hoc transformations or mutual-information estimators that are highly sensitive to quantization, repeated values, and event redundancy, leading to biased or unstable results in practice. We propose a nonparametric mutual information estimator that directly measures the dependence between time series and event sequences without data transformation, learning, or ad hoc discretization. Our method models the continuous-discrete duality of real-world time series to handle quantization and repeated-value artifacts and introduces a latent event clustering strategy to mitigate bias from event co-occurrence and redundancy. Together, these yield a robust and unified framework that bridges discrete and continuous mutual information. We evaluate the proposed estimator on four representative tasks: discrete-continuous time-delayed mutual information for causality analysis, global and local temporal repetition discovery, discrete covariate selection for time series forecasting, and continuous feature selection for classification. Experiments on synthetic and real-world datasets show consistent improvements over existing methods in accuracy, robustness, and interpretability, positioning our approach as a general-purpose dependence operator for heterogeneous temporal data, similar to Pearson correlation for homogeneous time series. Code available at: https://github.com/HaojiHu/Multimodal-Temporal-Data-Quantification

Read & Discuss → View Source →
17.
arXiv (CS.AI) 2026-06-11

Robust Instruction Compliance in Cooperative Multi-Agent Reinforcement Learning

Authors:
Wo Wei Lin↗Ethan Rathbun↗Enrico Marchesini↗Xiang Zhi Tan↗

arXiv:2605.12655v3 Announce Type: replace Abstract: Multi-agent reinforcement learning (MARL) in real-world use cases may need to adapt to external natural language instructions that interrupt ongoing behavior and conflict with long-horizon objectives. However, conditioning rewards on instructions introduces a fundamental failure mode as Bellman updates couple value estimates across instruction contexts, leading to inconsistent values when instructions interrupt macro-actions. We propose Macro-Action Value Correction for Instruction Compliance (MAVIC), which corrects Bellman backups at instruction boundaries by correcting the incoming instruction objective and restoring the continuation value under the current objective. Unlike reward shaping, MAVIC modifies the bootstrapping target itself, enabling consistent value estimation under stochastic instruction switching within a unified policy. We provide theoretical analysis and an actor-critic implementation, and show that MAVIC achieves high instruction compliance while preserving base task performance in increasingly complex cooperative multi-agent environments.

Read & Discuss → View Source →
18.
arXiv (CS.CL) 2026-06-12

X-MADAM-RAG: Diagnosing and Handling Chinese-English Evidence Conflict in Retrieval-Augmented Generation

Authors:
Yongqi Kang↗Yu Fu↗Yong Zhao↗

Retrieval-augmented generation (RAG) systems may receive evidence that is not merely noisy but mutually contradictory. This issue becomes particularly salient in multilingual settings, where retrieved Chinese and English evidence may support incompatible answer candidates. We study this problem through X-RAMDocs-ZHEN, a controlled Chinese-English benchmark derived from RAMDocs for diagnosing evidence conflict in RAG. The benchmark contains 300 examples across six balanced conditions, including monolingual support, bilingual agreement, reversed conflict directions, and conflict with optional noise. We further examine X-MADAM-RAG, an interpretable pipeline that decomposes evidence handling into per-document candidate extraction, visible-evidence repair, deterministic candidate grouping, and conflict-aware aggregation. On the original controlled benchmark with Qwen2.5-7B-Instruct, X-MADAM-RAG achieves 0.9667 strict accuracy and 0.9767 conflict-aware success, outperforming an evidence-normalized single-call baseline. However, a zero-call rule-only extractor reaches 1.0000 on the same benchmark, revealing strong template regularity. To probe this limitation, we construct a deterministic naturalized stress test that removes explicit answer templates while preserving candidate strings. On its 100-sample subset, rule-only extraction falls to 0.0000, but X-MADAM-RAG also drops to 0.3000 strict accuracy, below both naive and evidence-normalized baselines. A privileged oracle remains perfect, indicating that document-level extraction is the main bottleneck. These findings position X-RAMDocs-ZHEN and X-MADAM-RAG as diagnostic tools for controlled evidence conflict rather than as evidence of general hallucination detection or robustness to natural retrieval.

Read & Discuss → View Source →
19.
arXiv (CS.AI) 2026-06-11

Sample-Efficient Hypergradient Estimation for Decentralized Bi-Level Reinforcement Learning

Authors:
Mikoto Kudo↗Takumi Tanabe↗Akifumi Wachi↗Youhei Akimoto↗

arXiv:2603.14867v4 Announce Type: replace-cross Abstract: Many strategic decision-making problems, such as environment design for warehouse robots, can be naturally formulated as bi-level reinforcement learning (RL), where a leader agent optimizes its objective while a follower solves a Markov decision process (MDP) conditioned on the leader's decisions. In many situations, a fundamental challenge arises when the leader cannot intervene in the follower's optimization process; it can only observe the optimization outcome. We address this decentralized setting by deriving the hypergradient of the leader's objective, i.e., the gradient of the leader's strategy that accounts for changes in the follower's optimal policy. Unlike prior hypergradient-based methods that require extensive data for repeated state visits or rely on gradient estimators whose complexity can increase substantially with the high-dimensional leader's decision space, we leverage the Boltzmann covariance trick to derive an alternative hypergradient formulation. This enables efficient hypergradient estimation solely from interaction samples, even when the leader's decision space is high-dimensional. Additionally, to our knowledge, this is the first method that enables hypergradient-based optimization for 2-player Markov games in decentralized settings. Experiments highlight the impact of hypergradient updates and demonstrate our method's effectiveness in both discrete and continuous state tasks.

Read & Discuss → View Source →
20.
medRxiv (Medicine) 2026-06-23

Social networks and their association with quality of life among older adults in rural Burkina Faso

Authors:
Welgama↗Goodman-Palmer↗Harling↗G. P↗Agyapong-Badu↗Greig↗Inghels↗Witham↗Ouermi↗Coulibaly↗HIrschhorn↗L. R↗…

Objective: This study aimed to identify the types of social networks present among older adults in a rural, low-income country setting and describe their association with quality of life (QoL). Methods: A population-representative, cross-sectional survey was conducted in 60 villages around Nouna in Burkina Faso from July to August 2021. Data were collected from resident adults aged 40 years and older. Variables captured were sociodemographic status; social network characteristics (using the Practitioner Assessment of Network Typology (PANT)); quality of life (using the EuroHIS-8 tool); presence of non-communicable diseases, mental health conditions, and disability. Additionally, social networks were broadly categorised as aggregated integrated and aggregated less-integrated groups. Social network types and the groups were described separately, and a multivariable linear regression model was used to understand the association between social network types and QoL, adjusted for sociodemographic and morbidity factors. Results: Among the 2390 respondents, median age was 55 yrs (IQR: 47-64 yrs) and 55.8% were female. Locally Integrated (35.4%) or Family Dependent (30.3%) were the most common PANT social network types, followed by a mixed group (having characteristics of two or more social network types) (30.5%). Private Restricted (2.1%), Locally Self-Contained (1.2%), and Wider Community-Focussed (0.4%) types were uncommon. Adults with aggregated integrated network groups (36.1%) and aggregated less-integrated group (36.0%) were near equal, while others were non-aggregable. Although Wider Community-Focused type showed a significantly better QoL ({beta}= 8.69, 95%CI: 4.10 to 13.27), the association between social networks and QoL were subdued when controlled for morbidity factors, and hence no significant associations were observed between other types or the aggregated groups. Conclusion: Although having integrated social networks lead to a better QoL, morbidity has a greater effect on the QoL among older adults in Nouna and hence, investing more on improving the physical and mental health needs appears more beneficial.

Read & Discuss → View Source →
21.
arXiv (quant-ph) 2026-06-12

SAT, MaxSAT, and SMT for QLDPC Distance Computation: A Large-Scale Empirical Study

Authors:
Yu-Fang Chen↗Seyed Mohammad Reza Jafari↗Ching-Yi Lai↗

arXiv:2606.12445v1 Announce Type: new Abstract: Exact distance computation for quantum LDPC (QLDPC) codes plays a central role in validating candidate fault-tolerant quantum-code constructions, yet the computational structure of this problem remains poorly understood. Despite substantial recent progress in QLDPC design, it remains unclear which algorithmic principles govern the practical scalability of exact distance computation and which classes of exact solvers are best suited to this task. To address these questions, we conduct a systematic study of SAT- and MaxSAT-based formulations for exact QLDPC distance computation across representative codes. We further compare these formulations against several established exact-distance approaches in order to better understand the algorithmic landscape of exact QLDPC distance computation. Our study challenges and refines several prevailing intuitions about exact QLDPC distance computation. First, despite the XOR-rich structure of QLDPC parity checks, practical scalability appears to be governed more by the handling of cardinality constraints and optimization bounds than by parity reasoning alone. Accordingly, XOR-aware reasoning does not provide a systematic advantage across our benchmark suite. Second, Brouwer-Zimmermann-style search, long regarded as the benchmark paradigm for exact distance computation in sparse classical codes, no longer maintains its traditional scalability advantage in the QLDPC setting. This finding challenges the expectation that techniques successful for sparse classical codes remain dominant for QLDPC codes. Third, substantial qualitative differences arise even among MaxSAT solvers themselves. Branch-and-bound MaxSAT significantly outperforms unsat-core-based MaxSAT on challenging benchmarks, demonstrating that solver architecture and optimization strategy play a decisive role in practical scalability.

Read & Discuss → View Source →
23.
medRxiv (Medicine) 2026-06-17

Deep learning for interactive and automated inner retinal layer segmentation in OCT images of patients with retinitis pigmentosa using limited training data

Authors:
Laurence↗D. S↗Schilling↗Grimm↗N.-A↗Mace↗Bemme↗Pape↗

Purpose: New therapeutic strategies such as optogenetics have created a need for accurate tracking of inner retina degeneration in Retinitis pigmentosa (RP) patients. We introduce two tailored deep learning models to segment the RNFL (retinal nerve fibre layer), GCIPL (ganglion cell inner plexiform layer), INL (inner nuclear layer), CFT (central foveal thickness) and RPE (retinal pigment epithelium) in RP: The first is based on a Segment Anything Model (SAM), the second on nnU-Net. To our knowledge, SAM has not yet been applied to retinal layers in OCT data. Methods: SD-OCT images of a retrospective cohort of 37 RP patients were included. Data for four training cycles were prepared semi-automatically in MATLAB, then assessed and corrected by three expert graders. 1,700 segmented B-Scans from two open datasets were used for pretraining. For post-processing, semantic retinal boundary detection was developed. The final models, OCT-SAM and nnU-Net, were trained on 228 annotated RP scans. Detected layer thicknesses were validated against manual segmentation at 90 random points in 30 OCT B-Scans. Finally, OCT-SAM was tested on three RP cases with retrospective, longitudinal OCT data. Results: nnU-Net achieved a precision, recall and F-1 score of 0.96 while OCT-SAM performance resulted in slightly lower values of 0.93, 0.8 and 0.85, respectively. OCT-SAM measurements had low bias and good agreement with manual annotations, confirming reliability. Conclusions: OCT-SAM enabled fast data annotation and tool integration, whereas nnU-Net provided the best segmentation performance. OCT-SAM demonstrated longitudinal reproducibility and detected RP-characteristic pathologies and degenerative changes. Future work will extend OCT-SAM to 3D OCT segmentation.

Read & Discuss → View Source →
24.
arXiv (CS.LG) 2026-06-17

Sum-of-Squares Degree Barriers for the Reweighted-Hinge Method in Robust Halfspace Learning: A Christoffel-Function Characterization

Authors:
Xiaoyu Li↗

arXiv:2606.17215v1 Announce Type: new Abstract: A certificate that removes outliers sees the data only through its low-degree moments, and an adversary exploits exactly this, hiding corruption where the clean data already looks typical, in the blind spot no bounded-degree test resolves. That blind spot turns out to have an exact size: the Christoffel function of the clean marginal, the very quantity modern data analysis thresholds to detect outliers, here read from the adversary's side as the corruption a bounded-degree certificate cannot remove. We turn this inversion into the organizing principle of the reweighted-hinge approach to robustly learning $\gamma$-margin halfspaces under malicious noise (Shen, 2025; Zeng and Shen, 2025): the governing resource is the Sum-of-Squares degree of the outlier-removal certificate, and the resolution principle states that the maximal corruption mass which can hide at a center $c$ from a degree-$2t$ certificate is exactly the Christoffel function $\lambda_{t+1}(c)$ of the clean marginal. Three consequences follow, all against the certificate method (not information-theoretic). A margin-degree tradeoff: certifying the dense pancake to error $\epsilon$ costs SoS degree $\Omega(\log(1/\epsilon))$ or margin $\Omega(\sqrt{\log(1/\epsilon)}/\sqrt{d})$, explaining why the $\log(1/\epsilon)$ margin Shen (2025) records is forced, with a weighted-Chebyshev reduction making the threshold $2t=\Theta((|c|/s)^2)$ tight modulo one classical weighted-extremal estimate. A degree-$2$ outlier barrier: the resolution principle realized as an explicit instance on which degree $2$ is stuck at $\eta^{1/2}$ while degree $4$ escapes, locating the method's small breakdown rate in the degree, not the analysis. And a degree-$2t$ algorithm tracing the frontier $\eta^{1-1/2t}$ (recovering Shen (2025) at $t=1$), whose gain is an explicit constant, capped by the pancake density and shown unimprovable by the degree-$2$ barrier.

Read & Discuss → View Source →