# Research Papers — 2026-06 · bundle page 177 of 260

> Full-text markdown of papers #8801–8850 of 12993 published in 2026-06, newest first. AI-readable mirrors of the full 12993-paper 2026-06 archive (50 papers per file).

Canonical page: https://aipod.dev/papers/archive/2026-06/page/177
[← Previous bundle](https://aipod.dev/papers/archive/2026-06/page/176.md)
[Next bundle →](https://aipod.dev/papers/archive/2026-06/page/178.md)

### Decoupling Thought from Speech: Knowledge-Grounded Counterfactual Reasoning for Resilient Multi-Agent Argumentation

Authors: Jakub Masłowski, Jarosław A. Chudziak
Published: 2026-06-09
Categories: cs.MA, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2606.10475v1

Multi-agent debate frameworks have been shown to improve large language model performance in convergent tasks, but they are currently optimized in a way that heavily favors final output accuracy rather than stability of the process. During long-horizon exchanges reactive systems under sustained perturbations often experience logic degradation, argument repetition, and role drift. To structurally prevent the identity loss and maintain the process fidelity, we introduce Knowledge-Grounded Counterfactual Reasoning (KG-CFR), a dual-stage architecture that enforces a strict separation of concerns between a private, retrieval-augmented planning buffer, and a public execution layer. We assess this system in Dynamic Resource Allocation under Uncertainty (DRAU), a dedicated 1v1v1 environment, introducing diversity as distinct from standard debate settings. Over 270 completely factorial crisis simulation trajectories with stochastic environmental shocks, KG-CFR prevents judge-detected critical post-shock degradation (defined as a quality shift, $Δ\le -0.20$) in more than 95% of perturbed runs, increasing the overall argument quality from 0.694 to 0.822. Our primary contribution is the demonstration of architectural decoupling being an important factor of systemic resilience enhancement under sustained pressure without quality loss. Furthermore, we introduce custom vector metrics for discourse divergence and plan-execution alignment that provide strong, directionally consistent evidence of operational stability. Our ablation experiments suggest that the proper doctrinal grounding can be an equally important factor for argument quality, as the prospective planning. KG-CFR, according to our initial metric evaluations, reduces semantic looping, by preserving the agent's consistency with the original plan.

---

### Trading Utility for Dynamic Fairness in Multiple Resource Division with Sequential Demand

Authors: Kaiqi Jiang, Karim El Husseini, Wenzhe Fan, Xinhua Zhang
Published: 2026-06-09
Categories: cs.GT, cs.LG
arXiv: https://arxiv.org/abs/2606.10472v1

Dynamic multi-resource allocation is a central problem in shared computing environments, where users' demands arrive sequentially and resources must be distributed fairly without knowledge of future demands. Existing methods emphasize fairness guarantees such as Sharing Incentive, Envy Freeness, and Dynamic Pareto Optimality, but often overlook system utility. Moreover, these fairness criteria are mutually incompatible, preventing strict enforcement of them at the same time. We propose a neural allocation mechanism that reconciles fairness with utility through multi-objective optimization during sequential rollout. We first formalize fairness in the dynamic setting via stepwise loss functions for Sharing Incentive, Envy Freeness, and Dynamic Pareto Optimality, enabling differentiable training. Leveraging non-wastefulness, we parameterized the solutions by constraining allocations to the subspace of demand while allowing elastic over-allocation when resources remain available. Empirical results demonstrate that our learned allocator achieves substantially higher utility at comparable levels of fairness, uncovering clear Pareto-frontier-like tradeoffs across metrics.

---

### Detecting Speculative Language in Biomedical Texts using Recurrent Neural Tensor Networks

Authors: Dhruv Dixit
Published: 2026-06-09
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2606.10471v1

In this investigation, we delve into the automated detection of speculative language within biomedical articles by utilizing distributed sentence representations and advanced deep learning techniques. The implications of such identification extend to information retrieval, multi-document summarization, and the exploration of new knowledge. Our exploration encompasses two distinct approaches for acquiring distributed sentence representations: the Paragraph Vector model and the Recursive Neural Tensor Network. These methodologies are then rigorously compared against three foundational baseline algorithms: Support Vector Machines, Naive Bayes, and pattern matching. Our findings reveal that the Recursive Neural Tensor Network (RNTN) demonstrates a slight performance edge (F1 = 0.885) over the top-performing baseline, the linear bigram SVM (F1 = 0.881). Meanwhile, the Paragraph Vector model proves less effective (F1 = 0.368), even after extensive training using an expansive, unlabeled dataset. We engage in a comprehensive discourse on the factors influencing these performance disparities and provide insightful recommendations for future research directions.

---

### A Mean-Field Analysis of Multi-Head Self-Attention under Cross-Entropy Training

Authors: Cheng Huan, Hongfwei Yuan
Published: 2026-06-09
Categories: math.OC, stat.ML
arXiv: https://arxiv.org/abs/2606.10469v1

This paper develops a mean-field theory for a simplified single-layer causal multi-head self-attention model trained by cross-entropy minimization. Each attention head is treated as a particle in parameter space, and the empirical law of the heads is used as the large-head state variable. In the infinite-head limit, the averaged attention logits define a risk functional on probability measures, whose first variation generates a nonlinear Wasserstein gradient-flow equation. Unlike classical mean-field analyses of shallow networks that often focus on square-loss regression, the present model contains the softmax residual from the cross-entropy objective and the query-key-value structure of masked self-attention. We prove a static finite-head approximation bound for the optimal risk, characterize global minimizers through a variational support condition, and establish a quantitative finite-time propagation-of-chaos estimate comparing finite-head stochastic gradient descent with the limiting PDE. We then study the long-time behavior of the PDE: energy dissipation, convergence to the stationary set under compactness, convergence to a single stationary measure under topological or Kurdyka--Łojasiewicz assumptions, and explicit convergence rates under gradient-domination conditions. Finally, we prove local exponential stability under a Wasserstein strong-monotonicity condition and give verifiable stability and instability criteria for Dirac stationary measures. The results provide a rigorous baseline mean-field framework for attention-head training and clarify the additional compactness, landscape, and curvature assumptions needed to pass from stationarity to convergence and stability.

---

### Geometric Coastline Localization using Vision-Language Models

Authors: Rafia Malik, Bernhard Pfahringer, Karin Bryan, Mark Dickson, Eibe Frank
Published: 2026-06-09
Categories: cs.CV
arXiv: https://arxiv.org/abs/2606.10468v2

Coastline detection in remotely sensed imagery is commonly formulated as pixel-wise segmentation, even though coastlines used in coastal monitoring are ultimately represented as geometric curves and defined by geomorphic proxies such as vegetation lines, dune toes, or cliff edges. We revisit coastline extraction from a representation perspective and formulate the task as geometric boundary localization, where a thin coastline boundary is localized directly as a curve rather than derived from a segmentation mask. Using the New Zealand Coastal Change Dataset (NZCCD) and LINZ aerial imagery, we develop CoastlineVLM-7B, a vision-language model built on the GeoChat-7B/LLaVA-1.5 architecture that jointly performs coastline presence detection, proxy-type classification, and direct coastline grounding as an ordered polyline. We compare it against U-Net, UNet++, DeepLabV3+, and SegFormer trained using one-pixel-wide coastline masks and evaluate localization using tolerance- and distance-based geometric metrics. On the West Coast test set, U-Net provides stronger local boundary proximity, showing better tolerance scores and lower Chamfer and Modified Average Hausdorff distances, while CoastlineVLM-7B achieves the lowest Hausdorff and Earth Mover's distances, indicating reduced worst-case deviation and stronger global structural correspondence. Ablation studies show that geometric localization is driven primarily by direct coastline-grounding supervision and that GeoChat initialization provides a stronger starting representation than generic LLaVA-1.5 initialization. Zero-shot evaluation on the Australian VCMP dataset shows reduced performance for U-Net and CoastlineVLM-7B, but CoastlineVLM-7B achieves better geometric localization than U-Net. These results show that direct ordered-polyline grounding can be used as an alternative formulation for representing and localizing coastline geometry.

---

### Geometric Coastline Localization using Vision-Language Models

Authors: Rafia Malik, Bernhard Pfahringer, Karin Bryan, Mark Dickson, Eibe Frank
Published: 2026-06-09
Categories: cs.CV
arXiv: https://arxiv.org/abs/2606.10468v1

Coastline detection in remote sensing imagery is commonly formulated as a pixel-wise segmentation problem, where the final coastline is extracted from a predicted mask through post-processing. This formulation relegates coastline geometry, the primary representation used in coastal change analysis, to a secondary artifact rather than the learning objective. In practice, coastlines are defined by geomorphic proxies such as vegetation lines, dune toes, or cliff edges, rather than an instantaneous land-water boundary often used in pixel-based segmentation approaches. In this work, we revisit coastline extraction from a representation perspective and formulate the task as geometric boundary localization. We use the New Zealand Coastal Change Dataset (NZCCD) and high-resolution aerial imagery from Land Information New Zealand (LINZ) to develop CoastlineVLM-7B, a vision-language model (VLM) built on the GeoChat-7B/LLaVA-1.5 architecture that jointly performs coastline presence detection, proxy-type classification, and coastline grounding. The model directly predicts a coastline as a polyline rather than a dense segmentation mask. We evaluate CoastlineVLM-7B against segmentation baselines under strict one-pixel boundary supervision. Results show that geometry-based metrics are more suitable for assessing coastline localization quality than pixel-overlap metrics such as Intersection over Union (IoU). CoastlineVLM-7B improves global geometric alignment with reference coastlines, reducing Hausdorff distance from 37.74 m to 31.84 m and Earth Mover's Distance from 21.12 m to 17.32 m. These results indicate that output representation is a critical design choice in coastline extraction, and that geometry-oriented learning, combined with the semantic reasoning capabilities of vision-language models, aligns well with how coastlines are defined and evaluated in operational coastal monitoring.

---

### Large Language Models as Modal Models in Linguistics

Authors: Haruto Suzuki, Saku Sugawara
Published: 2026-06-09
Categories: cs.CL
arXiv: https://arxiv.org/abs/2606.10467v1

The rapid advancement of large language models (LLMs) has intensified debates about their significance for linguistic theory. These debates are commonly divided into three positions: insulationism, which regards LLMs as irrelevant to human language; eliminativism, which claims that LLMs can replace traditional linguistic theories; and conciliationism, which views them as useful tools for linguistic research. To clarify these positions, this paper applies the framework of modal modeling from the philosophy of science. We argue that LLMs possess genuine epistemic value as minimal models, even without structural correspondence to human cognition. In particular, they can provide how-possibly explanations (HPEs) by testing modal claims about language acquisition and linguistic competence. We then examine the conditions under which LLMs could qualify as how-actually explanations (HAEs) of human language, drawing on the mechanistic account of scientific explanation. We argue that current LLMs do not yet satisfy these requirements. On the basis of this analysis, we propose understanding the explanatory power of LLMs as lying on a continuum between HPEs and HAEs. This framework avoids both overstating and understating their explanatory significance and offers a more precise basis for evaluating the role of LLMs in the scientific study of language.

---

### UPLOTS: A Unified Pretrained Language Model for Constrained Time-series Generation

Authors: Du Yin, Hao Xue, Jinliang Deng, Yang Yang, Shuang Ao, Arian Prabowo, Flora Salim
Published: 2026-06-09
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2606.10466v4

In time-series generation, existing approaches typically handcraft ortrain a separate model for each dataset, which hinders their scalability and fails to leverage shared temporal structures across domains. To address this fragmentation, we propose UPLOTS, a Unified, Prompt-guided Language model framework fOr constrained Time-Series Generation across diverse domains. Instead of building task-specific models, UPLOTS leverages a single pre-trained transformer backbone guided by learned constraint prompts, enabling on-demand generation with precise pattern control. One key innovation is our dynamic multi-dataset loss re-weighting and prompt-to-pattern mapping, which allows UPLOTS to internalize diverse temporal structures during training and conditionally generate them at inference. We evaluate UPLOTS on four real-world benchmarks and multiple constraint settings, including peak-period, calendar, load-level, and volatility patterns. Additional held-out constraint-combination and downstream forecasting experiments further demonstrate that UPLOTS generalizes beyond the original peak-pattern setting and improves data augmentation under scarce real-data regimes. Our code and baselines are available at github repo: https://github.com/cruiseresearchgroup/UPLOTS.

---

### UPLOTS: A Unified Pretrained Language Model for Constrained Time-series Generation

Authors: Du Yin, Hao Xue, Jinliang Deng, Yang Yang, Shuang Ao, Arian Prabowo, Flora Salim
Published: 2026-06-09
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2606.10466v3

In time-series generation, existing approaches typically handcraft ortrain a separate model for each dataset, which hinders their scalability and fails to leverage shared temporal structures across domains. To address this fragmentation, we propose UPLOTS, a Unified, Prompt-guided Language model framework fOr constrained Time-Series Generation across diverse domains. Instead of building task-specific models, UPLOTS leverages a single pre-trained transformer backbone guided by learned constraint prompts, enabling on-demand generation with precise pattern control. One key innovation is our dynamic multi-dataset loss re-weighting and prompt-to-pattern mapping, which allows UPLOTS to internalize diverse temporal structures during training and conditionally generate them at inference. We evaluate UPLOTS on four real-world benchmarks and multiple constraint settings, including peak-period, calendar, load-level, and volatility patterns. Additional held-out constraint-combination and downstream forecasting experiments further demonstrate that UPLOTS generalizes beyond the original peak-pattern setting and improves data augmentation under scarce real-data regimes. Our code and baselines are available at github repo: https://github.com/cruiseresearchgroup/UPLOTS.

---

### ERAlign: Energy-based Representation Alignment of GNNs and LLMs on Text-attributed Graphs

Authors: Xianlin Zeng, Fan Xia, Xiangyu Chen
Published: 2026-06-09
Categories: cs.LG, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2606.10461v1

Text-attributed Graphs (TAGs) incorporate textual node attributes with graph structures to describe rich relational semantics. Recent efforts to integrate Graph Neural Networks (GNNs) and Large Language Models (LLMs) have shown promise for learning on TAGs, yet achieving well-aligned representations remains challenging. Prior studies largely rely on heuristics that perform coarse-grained matching. They lack sufficient constraints and ignore distributional alignment, leading to representation drift and limited generalization. Building on Energy-based Models (EBMs), we propose an Energy-based Representation Alignment (ERAlign) framework that projects GNN-encoded graph structure and LLM-derived text embeddings in a shared latent space to achieve distribution consistency. Concretely, layer-wise alignment is quantified by a distance metric and optimized via an EBM objective. By decreasing energy values, our framework yields well-aligned representations for downstream tasks. During training, we introduce Energy Discrepancy (ED) to avoid high sampling costs associated with intractable normalization. ED also carries theoretical guarantees of higher training efficiency and reduced energy landscape distortion. Empirical evaluations on eight TAG datasets demonstrate that ERAlign obtains state-of-the-art performance across varying levels of supervision and cross-task transfer scenarios.

---

### LakeQA: An Exploratory QA Benchmark over a Million-Scale Data Lake

Authors: Haonan Wang, Jiaxiang Liu, Yurong Liu, Austin Senna Wijaya, Tianle Zhou, Eden Wu, Yijia Chen, Wanting You, Reya Vir, Daniela Pinto, Grace Fan, Yusen Zhang et al.
Published: 2026-06-09
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2606.10460v1

Recent large language models (LLMs) have shown rapid progress in reading-based question answering (QA), where evidence is explicitly provided or can be trivially retrieved. In contrast, real-world questions are often not paired with accurate evidence documents. The useful evidence resides in massive data lakes, making search a prerequisite for answering. However, there is a lack of comprehensive benchmarks that require both searching and reasoning over large data lakes. To this end, we introduce LakeQA, a comprehensive benchmark for search-centric question answering over data lakes that jointly emphasizes searching and reasoning capabilities. LakeQA is built on a heterogeneous collection of approximately 9.5 TB of text resources from Wikipedia and open-source government data, spanning structured and unstructured data. To ensure task quality, each sample is annotated by at least one Ph.D.-level expert. Each task requires long-horizon multi-hop reasoning with implicit intermediate steps: agents need to discover the correct documents and then compose evidence across sources to produce the answer. Experimental results on seven frontier LLMs demonstrate that LakeQA is challenging. For instance, GPT-5.2 achieves only an exact-match score of 18.37% on LakeQA. Overall, LakeQA provides a realistic testbed for developing LLM agents that can both find and analyze data in modern data lakes.

---

### Leveraging Social Media Data for COVID-19 Studies

Authors: Nur Hafieza Ismail, Nur Shazwani Kamarudin, Nurol Husna Che Rose
Published: 2026-06-09
Categories: cs.SI, cs.CL
arXiv: https://arxiv.org/abs/2606.10459v2

Nowadays, social media networks have become widely preferred sources of information. Especially during the time of the Coronavirus disease 2019 COVID 19 pandemic, social media has been one of the most used platforms to get the latest news and information related to COVID 19. Social media are popular because they offer free access to their registered users and allow them to do posting, disseminate information, and respond to others postings. With almost 4.6 billion social media users worldwide, it is not surprising the significant amount of information shared through these platforms could affect how people perceive and cope with the pandemic that we are facing right now. With decent use, social media can be a beneficial digital tool to spread reliable news and public awareness for patients, clinicians, and society. Specifically, this chapter describes linguistic, visual, and emotional indicators expressed in user disclosures. Thus, in this chapter, the related studies of social media platforms usage during the COVID 19 pandemic are explored and discussed in detail. This chapter also categorizes social media data used, introduces different deployed machine learning, feature engineering, natural language processing, and survey methods, and outlines directions for future research.

---

### Minimum Distortion Quantization with Specified Output Distribution

Authors: Aolin Xu
Published: 2026-06-09
Categories: cs.IT, cs.AI, math.OC, math.ST
arXiv: https://arxiv.org/abs/2606.10458v1

We derive the optimal quantizer of a real-valued random variable $W$ with distribution $P_W$ such that 1) the distribution of the quantization output $X$ that can take $k$ values follows any specified distribution $P_X$ over $\{1,\ldots,k\}$, and 2) the minimum mean squared error (MMSE) of estimating $W$ from $X$ is minimized. It is shown that the optimal quantizer takes the form $X=σ\big(F_{σ^{-1}(X)}^{-1}(F_W(W))\big)$, where $σ$ is the optimal permutation of $\{1,\ldots,k\}$ among all permutations to minimize the MMSE, and $F$ is the cumulative distribution function. When $P_W$ is uniform over an interval or $P_X$ is uniform over $\{1,\ldots,k\}$, the quantizer takes a simple form $X=F_{X}^{-1}(F_W(W))$. The concept of majorization plays a key role in the optimality proof. Specifying the output distribution is useful for designing quantizers with explicitly controlled output entropy, maximized mutual information between input and output, tailored output distribution to match channel input requirements for communication, and data anonymization.

---

### Trace2Policy: From Expert Behavior Traces to Self-Evolving Decision Agents

Authors: Junli Zha, Jinbo Wang, Chao Zhou, Xiang Song
Published: 2026-06-09
Categories: cs.AI
arXiv: https://arxiv.org/abs/2606.10457v1

Decision rules that enterprise experts apply tacitly -- in auditing, compliance, and contract review -- can be systematically recovered and improved through iterative error analysis. We present \textbf{Trace2Policy}, whose core mechanism -- \textbf{EISR} (\textbf{E}rror-driven \textbf{I}terative \textbf{S}kill \textbf{R}efinement) -- maintains a human-readable rule document as its optimization target: each round executes the rules on a validation set, clusters errors by root cause into MISSING, WRONG, or CONFLICT types, applies targeted patches, and commits only those that pass a regression gate. \textbf{For this class of compliance-sensitive, skewed-base-rate decision tasks, we identify rule quality -- not model capability -- as the dominant performance lever}: across five LLMs, one-shot distillation plateaus near $\sim$70\% on the deployed pool, while eight EISR rounds lift the same rules to 79.6\% when compiled into deterministic Python -- zero LLM calls at inference. \textbf{Execution form compounds the gain: in production, the same EISR-refined content runs 9.8~pp higher as compiled Python than as an LLM prompt, a form-and-engineering bundle the 22-day deployment matured together.} Deployed for 22 days at a major logistics carrier (3,349 audit cases), the compiled pipeline outperforms the pure-LLM baseline it replaced (72.7\%); on these calibrated, skewed-base-rate workloads, re-enabling LLM fallback monotonically degrades accuracy. An LLM-driven variant, \textbf{Auto-EISR}, reproduces this refinement at \$5--\$10 per cycle versus $\sim$70 expert-hours, and transfers to four public benchmarks spanning legal reasoning (LegalBench) and process-mining decisions (BPIC 2012) without re-engineering.

---

### The Distributed Detectability Band Against Marginal-Preserving Attacks

Authors: Zhang Qinqin, Gao Yuze
Published: 2026-06-09
Categories: cs.CR, cs.AI
arXiv: https://arxiv.org/abs/2606.10456v2

AI-control monitors score individual agent actions to detect misbehavior, but real harm can be distributed across many benign-looking steps, each individually below any per-step alarm. We construct a marginal-preserving, correlation-encoded distributed-sabotage attack using a Gaussian-copula AR(1) construction: the per-step monitor-score marginal is held exactly equal to benign, so mean, max, top-k tail, and threshold monitors (Monitor A) are defeated by construction, while harm is encoded in the temporal correlation structure. We sequence the paper around three reviewer-mandated gates. (1) Realizability gate: the stealthy attack achieves KS-distance to benign of 0.013 (effectively zero) at all tested harm levels up to 3.0, confirming that harm is fully decoupled from the per-step marginal and realizability is not harm-limited. (2) Monitor-A-vs-B reconciliation: we show formally that the attack, built against Monitor A's score marginal, remains marginal-preserving under a different-score Monitor B (the correlation/sequence family: CUSUM, SPRT, HMM-LR, runs test, autocorrelation, windowed logistic), and scope worst-case claims to score functions that admit a temporal signature. (3) Non-empty detectability band: Monitor A achieves AUC 0.52 (chance); Monitor B spans AUC 0.79-0.97 at the same 1% FPR target, and as harm is amortized over more steps Monitor A collapses to chance while Monitor B holds at AUC ~0.95. These results demonstrate a non-empty detectability band and characterize the sub-threshold sabotage frontier: distribution-shape monitors fail by construction; temporal-correlation monitors can detect but are not trivially optimal.

---

### Few-step Generative Models as Lossy Compression

Authors: Fuma Kimishima, Jinjia Zhou
Published: 2026-06-09
Categories: cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2606.10450v1

DiffC provides a principled way to reuse pre-trained diffusion models for lossy compression, but its encoding and decoding procedures remain slow because they require many discretized forward and reverse steps. We study whether few-step generative models -- Rectified Flow, Consistency Trajectory Models (CTM), and MeanFlow -- can be cast as codecs within the same reverse channel coding (RCC) framework. The main challenge is that RCC requires posterior and shared distribution parameters, whereas these models do not explicitly parameterize intermediate conditional distributions. For Rectified Flow and MeanFlow, we use the equivalence between velocity parameterization and diffusion-style denoising parameterization to derive the quantities required by RCC. For CTM, which is distilled from EDM, we adopt the EDM noise parameterization together with local Gaussian approximations of the sender and shared distributions at intermediate states. This yields a proof-of-concept probabilistic formulation that enables compression with pre-trained few-step generative models without retraining. On low-resolution benchmarks, the resulting codecs reduce encoding and decoding time and improve realism in the low-bit-rate regime.

---

### Mitigating Bias in Low-SNR Financial Reinforcement Learning via Quantum Representations

Authors: Zeyu Liu, Xuanzhi Feng, Sing Kwong Lai, Yuanchen Gao, Xiaoyi Pang, Hualei Zhang, Jingcai Guo, Jie Zhang, Song Guo
Published: 2026-06-09
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2606.10448v1

The financial market is a typical low signal-to-noise ratio (SNR) setting, which often destabilizes off-policy maximum-entropy methods like Soft Actor-Critic (SAC). Specifically, noisy state representations may produce unreliable Q-value estimates, and bootstrapping amplifies these errors, forming a failure mode we call the "Financial Entropy Trap". In this paper, we propose FPQC-SAC, an efficient and plug-and-play SAC variant that places a compact and bounded Parameterized Quantum Circuit (PQC) before the actor and critic networks to constrain feature propagation at the representation level, rather than filtering raw inputs or regularizing Q-values after bootstrapping. Notably, FPQC-SAC reduces the impact of extreme market fluctuations on Bellman target estimation, while trainable quantum entanglement preserves flexible cross-asset interactions. Empirical evaluations on real-world portfolio management tasks demonstrate that FPQC-SAC substantially enhances out-of-sample stability and cumulative returns by achieving a 66.89% relative gain in cumulative return over standard unconstrained SAC and outperforms the best continuous-control deep reinforcement learning baseline by approximately 27%. Open-source code is available at https://github.com/ZeyuLIU-UST/FPQC-SAC-main.

---

### SpenseGPT: Practical One-shot Pruning Enabling Sparse and Dense GEMMs for LLM Inference

Authors: Jaeseong Lee, Seung-won Hwang, Samyam Rajbhandari
Published: 2026-06-09
Categories: cs.LG, cs.CL
arXiv: https://arxiv.org/abs/2606.10445v1

Semi-structured 2:4 sparsity is widely supported by modern accelerators, providing up to a 2x theoretical speedup. However, its strict 50% sparsity constraint often causes non-negligible accuracy degradation under post-training pruning. Meanwhile, existing relaxed sparsity formats either require specialized compiler support or introduce runtime overheads that limit end-to-end speedup. We propose Spense, a practical hybrid sparse-dense format that splits each weight matrix into a 2:4 sparse region and a dense region. This design relaxes the effective sparsity constraint while remaining compatible with existing high-performance sparse and dense GEMM libraries, avoiding both custom compiler support and input activation expansion. Building on this format, we introduce SpenseGPT, a one-shot post-training pruning method that produces sparse and dense regions. Notably, we show that selecting the right dense regions is important, and we devise two different strategies to choose them. Experiments on Qwen3-32B and Seed-OSS-36B demonstrate that our method achieves up to 1.2x end-to-end decoding speedup on B200 GPUs with FP8 precision, while preserving accuracy. To the best of our knowledge, this is the first one-shot pruning demonstration of real-world end-to-end LLM decoding speedup from semi-structured sparse tensor cores on recent GPUs such as B200s, while maintaining model quality.

---

### ASTRA-sim 3.0: Next-Level Distributed Machine Learning Simulations via High-Fidelity GPU and Infrastructure Modeling

Authors: William Won, Jinsun Yoo, Tuan Ta, Moumita Dey, Andy Balogh, Pradosh Datta, Furkan Eris, Conor Green, Winston Liu, Changhai Man, Kingshuk Mandal, Amos Rai et al.
Published: 2026-06-09
Categories: cs.DC, cs.LG, cs.NI
arXiv: https://arxiv.org/abs/2606.10440v1

Distributed machine learning (ML) is a key paradigm for today's large-scale artificial intelligence applications. As model inference arises as an important use case, faithful modeling of latency-sensitive collective communication has never been more important. Capturing the device architecture and modeling control and data paths at high fidelity is therefore a necessity today. Having a common, detailed representation for distributed ML infrastructure is also crucial. We revisit the promising open-source, community-driven simulator: ASTRA-sim. In this work, we identify limitations of the current ASTRA-sim simulator and augment it with new features. To this end, we enable fine-grained, high-fidelity simulation with a standardized infrastructure representation, opening new design space exploration opportunities. We propose the simulation at cache-line-sized load-store granularity, with a detailed graphics processing unit (GPU) execution model, to balance simulation scalability and fidelity. We also introduce InfraGraph, a standardized representation to capture distributed ML network infrastructure in detail. Using the updated ASTRA-sim 3.0 simulator, we showcase interesting design space explorations for designing optimized collective algorithms, network requirements, and GPU architectures.

---

### Enhancing Multilingual LLM-based ASR with Mixture of Experts and Dynamic Downsampling

Authors: Guodong Lin, Ziqi Chen, Yuxiang Fu, Ke Li, Wei-Qiang Zhang
Published: 2026-06-09
Categories: cs.SD, cs.CL, eess.AS
arXiv: https://arxiv.org/abs/2606.10439v1

The rapid progress of large language models (LLMs) has opened up a new frontier for automatic speech recognition (ASR), making their effective integration a critical and challenging research direction. To this end, this work proposes a projector-based LLM-ASR framework targeting the key challenges of multilingual generalization and modality alignment. Our approach incorporates a Mixture of Experts (MoE) architecture to improve cross-lingual adaptability, and a Continuous Integrate-and-Fire (CIF) mechanism for dynamic downsampling and modality alignment. Experimental results show that the combination of these components yields substantial performance improvements, surpassing strong baseline models. The proposed method represents a step toward building more accurate, robust, and generalizable LLM-based ASR systems.

---

### Parallel Causal Associative Fields: Gated Sparse Memory for Long-Context Language Modeling

Authors: Muhammad Ahmed
Published: 2026-06-09
Categories: cs.LG, cs.CL
arXiv: https://arxiv.org/abs/2606.10435v1

Transformers achieve strong language modeling performance by providing direct token-to-token communication paths, but causal self-attention scales quadratically with context length. Recurrent and state-space models reduce this cost, yet compress history into sequentially updated fixed-size states. This paper studies a third primitive: a parallel content-addressed memory over causal successor records. The proposed Parallel Causal Associative Field (PCAF) writes local records from a context window into hash buckets, retrieves a bounded candidate set for the current query, forms a sparse cache distribution over successor tokens, and mixes that cache with a parametric local language model through a learned gate. The resulting model maintains sparse long-context access while avoiding a single fixed recurrent state bottleneck. We evaluate PCAF under full autoregressive pretraining on WikiText-103 and PG-19 using a distributed Google Cloud TPU v4-32 pod. At 303M parameters and context length T = 2048, PCAF-semantic reaches 36.31 perplexity on WikiText-103 and 52.45 perplexity on PG-19, compared with 47.49 and 53.84 for a matched dense Transformer. PCAF-semantic simultaneously processes 0.61-0.62M tokens/s across the TPU pod, versus 0.43M tokens/s for dense and local attention baselines. Supporting 41M-parameter multi-seed sweeps and single-GPU component ablations show that the associative cache, retrieval capacity, and learned gate materially affect the speed-quality trade-off.

---

### Vision-Assisted Foundation Model for Solving Multi-Task Vehicle Routing Problems

Authors: Shuangchun Gui, Zhiguang Cao, Wen Song, Yew-Soon Ong
Published: 2026-06-09
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2606.10431v1

Multi-task vehicle routing problems play a critical role in enhancing efficiency across various industries and service sectors. These problems consist of multiple variants that optimize routing costs while meeting diverse customer constraints. Existing multi-task VRP solvers solely utilize a graph-based modality, limiting their ability to address variants with multiple constraints. As a format to represent complex semantics, vision modality shows great potential for encoding diverse VRP constraints. This motivates us to learn patch-level semantics from the vision images, and then integrate them into a graph-based model to solve various VRP variants simultaneously. However, directly applying this approach to multi-task VRPs presents three challenges: 1) existing VRP images lack constraint representations, which are essential for multi-task VRPs, 2) the fixed receptive field of individual patches cannot effectively accommodate varying requirements across tasks, and 3) imbalanced pixel distribution among constraints may cause the model to overlook constraints with fewer pixels. In this paper, we propose a vision-assisted foundation model (VaFM) to address these challenges. In the vision modality, input images tailored to all constraints are encoded by a convolutional neural network. The obtained patch embeddings are fused with graph-based nodes to generate solutions, with an auxiliary task designed to address the pixel-imbalanced issue. The performance of VaFM is evaluated across 16 different VRP variants. The experimental results demonstrate the superiority of VaFM over state-of-the-art methods, especially for variants with complex constraints.

---

### Which LoRA? An Empirical Study on the Effectiveness of LoRA Techniques During Multilingual Instruction Tuning

Authors: Thamali Wijewardhana, Napoleon H. Reyes, Surangika Ranathunga
Published: 2026-06-09
Categories: cs.CL
arXiv: https://arxiv.org/abs/2606.10428v1

We investigate whether commonly available LoRA variants have an advantage over basic LoRA in multilingual instruction tuning. Experiments involving LoRA and four other variants on two datasets across diverse target languages show that there is no significant advantage in using more complex LoRA variants instead of basic LoRA, with respect to balancing cross-lingual transfer and knowledge retention. An analysis of hidden embeddings reveal that layer-wise language representation remains largely similar across LLMs fine-tuned with different LoRA techniques, suggesting that architectural novelty of LoRA techniques may not translate into better cross-lingual adaptation.

---

### WebChallenger: A Reliable and Efficient Generalist Web Agent

Authors: Jayoo Hwang, Xiaowen Zhang, Vedant Padwal
Published: 2026-06-09
Categories: cs.CL
arXiv: https://arxiv.org/abs/2606.10423v1

Autonomous web navigation remains challenging for LLM agents, and the strongest generalist systems rely on proprietary reasoning models whose inference cost is prohibitive for the repetitive tasks where such agents would be most useful. We argue this gap stems not from insufficient model capability but from agent architectures that fail to replicate three human cognitive advantages: selective attention to relevant page regions, persistent memory of website structure, and procedural fluency with common interaction patterns. We introduce WebChallenger, a web agent framework that addresses each gap through architecture design rather than model scale, built around PageMem: a structured page representation deterministically constructed from the DOM that exposes each page as a hierarchy of semantic sections with short summaries. On this shared substrate we build three mechanisms that mirror the three cognitive advantages: a divide-and-conquer observation pipeline that lets the agent skim section summaries and extract details only from task-relevant regions; a lightweight exploration and memory system that traverses each website once to build a reusable map of pages and element behaviors; and compound action workflows that collapse common multi-step interactions into single agent actions, handling partial state changes automatically. Because all three operate over PageMem, the framework generalizes across websites without site-specific adapters. Using off-the-shelf open-weight models without fine-tuning, our system achieves 56.3% on WebArena, 48.7% on VisualWebArena, 51.0% on Online-Mind2Web, and 70.9% on WorkArena, approaching frontier proprietary systems at a fraction of the cost. Our code is released at https://github.com/jayoohwang1/webchallenger

---

### Soul Computing: A Theoretical Framework and Technical Architecture for Intelligent Agents with Independent Consciousness

Authors: Jinshan Zhang, Xishi Zhou, Qiu Peng, Jianwei Yin
Published: 2026-06-09
Categories: cs.AI
arXiv: https://arxiv.org/abs/2606.10413v1

Breakthroughs in large language models and multimodal generation technologies have propelled the digital reconstruction of human mental traits, emotional patterns, and long-term memory from science fiction toward engineering practice. Yet current research and industry practices at the intersection of AI and digital humans remain hampered by fundamental conceptual ambiguities: the essential differences between next-generation intelligent agents and traditional virtual humans, the construction pathways for digital entities possessing self-identity, and the core technical and ethical challenges confronting this domain all demand urgent clarification. This paper systematically examines the transformative logic underlying the transition from traditional virtual humans to the ``Soul Computing'' paradigm, driven by frontier AI technologies. We first analyze the evolutionary patterns of human consciousness and memory mechanisms, reassessing the core value of massive multimodal digital fragments in the reverse reconstruction of individual mental worlds. On this basis, we formally delineate the academic connotations of narrow and broad Soul Computing for the first time, clarifying its academic boundaries and essential distinctions from Affective Computing, Historical Reconstruction, and Mortal Computation. We argue that Soul Computing systems must architecturally construct an ``Intensional'' core rather than serving as purely ``Extensional'' functional carriers, thereby enabling the fundamental transition of AI from toolhood to living agency.

---

### A Unified Multi-Modal Framework for Intelligent Financial Systems: Integrating Reinforcement Learning, High-Frequency Trading, and Game-Theoretic Approaches with Cross-Modal Sentiment Analysis

Authors: Fanrong Liu, Zhang Yuwei, Mingni Luo
Published: 2026-06-09
Categories: cs.AI
arXiv: https://arxiv.org/abs/2606.10412v1

The rapid evolution of financial technology demands sophisticated artificial intelligence systems capable of handling diverse challenges across multiple domains simultaneously. This paper presents a groundbreaking unified framework that seamlessly integrates Proximal Policy Optimization for robo-advisory systems, advanced time-series prediction models for high-frequency trading, in-context learning mechanisms for dynamic investment advisory, game-theoretic approaches for competitive banking scenarios, and unified embeddings for cross-modal financial sentiment analysis. Our comprehensive framework addresses the critical gap in existing literature where these technologies have been developed in isolation, failing to leverage their synergistic potential. Through extensive experimentation across multiple financial datasets and real-world scenarios, we demonstrate that our integrated approach achieves superior performance compared to specialized single-domain systems. Specifically, our framework shows a 23.7% improvement in portfolio optimization metrics, reduces prediction error in high-frequency trading by 31.2%, enhances investment recommendation accuracy by 18.9%, optimizes competitive banking strategies with a 27.4% increase in Nash equilibrium convergence speed, and improves sentiment analysis accuracy by 15.6% through cross-modal fusion. The theoretical foundation of our work establishes convergence guarantees for the integrated optimization problem, while our empirical results validate the practical applicability across diverse financial institutions. This research not only advances the state-of-the-art in financial AI but also provides a blueprint for developing comprehensive intelligent systems that can adapt to the complex, interconnected nature of modern financial markets.

---

### A Comprehensive Inference-Time Augmentation Framework in Physiological Signals: Application to PPG-Based AF Detection

Authors: Davood Fattahi, Runze Yan, Saurabh Kataria, Zhaoliang Chen, Xiao Hu
Published: 2026-06-09
Categories: cs.LG, eess.SP, q-bio.QM
arXiv: https://arxiv.org/abs/2606.10410v2

Objective: Accurate classification of physiological signals in real-world deployments is challenged by sensor noise, motion artifacts, and distribution shifts between training and deployment data. Inference-time augmentation (ITA), which applies augmentations during inference rather than retraining, offers a simple, model-agnostic mechanism to improve robustness. However, ITA application to physiological signals has remained narrow in scope, relying on limited augmentation methods with fixed, unoptimized parameters. This work proposes a unified ITA framework to address that gap. Approach: The framework incorporates 13 augmentation methods spanning time-domain, amplitude-domain, frequency-domain, and artifact-injection transformations, with hyperparameters optimized via Bayesian optimization. We evaluate on atrial fibrillation (AF) detection from 30-second PPG signals using GPT-PPG and ResNet across five datasets comprising more than 400 patients and ${\sim}$9,800 hours of recording. Main results: Standard ITA consistently improved AUROC (up to 8.5% for GPT-PPG and 0.7% for ResNet) and AUPRC (up to 10.6% for GPT-PPG and 0.8% for ResNet). Selective ITA further reduced average FPR by up to 4.4% (GPT-PPG) and 1.3% (ResNet) on non-AF datasets. Significance: These findings establish ITA as a practical, model-agnostic approach for improving PPG-based AF classification reliability in deployment settings where retraining is not feasible, with broader applicability to physiological signal analysis.

---

### Time-frequency localization of bird calls in dense soundscapes

Authors: Simen Hexeberg, Fanghui Tong, Hari Vishnu, Mandar Chitre
Published: 2026-06-09
Categories: cs.SD, cs.CV, q-bio.QM
arXiv: https://arxiv.org/abs/2606.10407v2

Passive acoustic monitoring enables large-scale wildlife observation. Most bioacoustic classifiers predict species presence in a time window without localizing vocalizations precisely in time or frequency, limiting downstream analyses. We formulate time-frequency localization of bird calls as object detection on spectrograms and compare three computer vision model families (YOLO11, SAM 3, RF-DETR) against a non-learnable baseline. We introduce Intersection over Minimum (IoMin), an evaluation metric that better handles ambiguous acoustic boundaries than IoU. We also open-source a browser-based tool for efficient bounding-box labeling. The best RF-DETR model nearly doubles baseline performance on in-distribution, dense soundscapes from Singapore (83.4% vs. 42.1% IoMin@50 F1-score) and generalizes better to out-of-distribution recordings from Hawaii (63.2% vs. 48.6%). These results indicate that fine-tuned computer-vision models are well suited for time-frequency localization of bird vocalizations in complex soundscapes.

---

### Time-frequency localization of bird calls in dense soundscapes

Authors: Simen Hexeberg, Fanghui Tong, Hari Vishnu, Mandar Chitre
Published: 2026-06-09
Categories: cs.SD, cs.CV, q-bio.QM
arXiv: https://arxiv.org/abs/2606.10407v1

Passive acoustic monitoring enables large-scale observation of wildlife, but most bioacoustic classifiers only predict species presence in a time window without localizing vocalizations precisely in time or frequency, limiting downstream analyses. We formulate bird vocalization detection as an object detection task on spectrograms and train YOLO11 models to localize bird calls in dense tropical soundscapes from Singapore. We additionally introduce an open-source browser-based annotation tool and propose Intersection over Minimum (IoMin), an evaluation metric that better handles ambiguous acoustic boundaries than standard IoU and is better suited to the problem at hand. The best YOLO model nearly doubles baseline performance on in-distribution soundscapes from Singapore (81.8% vs. 42.1% IoMin@50 F1-score) while still outperforming the baseline on unseen out-of-distribution recordings from Hawaii (58.6% vs. 48.6%). These results suggest that object detection frameworks are a promising approach to time-frequency localization of animal vocalizations in complex soundscapes.

---

### FOGO: Forgetting-aware Orthogonalization Optimizer

Authors: Toan Nguyen, Yang Liu, Trung Le, Celso de Melo, Flora D. Salim
Published: 2026-06-09
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2606.10406v1

We argue that forgetting is not confined to continual learning but is a general optimization phenomenon: during standard training, dominant mini-batch gradients suppress rare but useful update directions, causing short-term forgetting at every step. When such knowledge is never revisited, these losses compound into long-term forgetting-the classical failure mode of continual learning. We introduce FOGO, a scalable optimizer that continuously detects and resolves gradient interference across both regimes. FOGO spectrally orthogonalizes momentum updates to prevent dominant directions from monopolizing optimization, then stores representative past directions in a compact codebook memory built on random projection, where pairwise distances are provably preserved in low-dimensional space. At each step, conflicts between the current update and stored directions are resolved via lightweight orthogonal correction and lifted back through a proximal step, with minimal overhead and no data storage. Across class-imbalanced classification, continual visual learning under domain and class shifts, continual fine-tuning of LLaVA-7B, and GPT-2 pretraining, FOGO consistently improves convergence and knowledge retention, outperforming Adam and Muon.

---

### KCSAT-ML: Probing Reasoning Models with Nationwide-Cohort Human Difficulty

Authors: Sanghee Park, Geewook Kim, Kee-Eung Kim
Published: 2026-06-09
Categories: cs.CL
arXiv: https://arxiv.org/abs/2606.10403v3

Math reasoning benchmarks have proliferated, yet most lack a per-item difficulty signal grounded in actual human performance. We introduce KCSAT-ML, a decade (2014-2025) of Korean College Scholastic Ability Test (KCSAT; Suneung) mathematics: 664 problems with a 339-item core set carrying official per-item error rates from nationwide cohorts of hundreds of thousands of examinees. We pair the benchmark with Difficulty-aligned Reasoning Gain (DRG): a score-orthogonal metric that asks whether a model's mistakes concentrate on the items humans found hard, or on items humans found easy. Together they expose, across a wide range of VLMs (and LLMs with OCR), three patterns: (i) low-budget accuracy collapses on the high-human-error tail at every model size; (ii) test-time scaling (TTS) raises token use roughly linearly with cohort error rate, while accuracy gains follow a non-monotonic curve; (iii) within a single family, TTS flips between anti-scaling on the hardest items and overthinking on easier ones -- two faces of the same alignment failure. With the proposed DRG metric, we find that models with near-identical accuracy can sit at near-opposite values: one model gets wrong what humans also find hard, while another solves the hardest items yet fails on items humans find easy, which is a critical contrast that aggregate accuracy hides. Our code and dataset builder is fully open-sourced at https://github.com/naver-ai/KCSAT-ML.

---

### KCSAT-ML: Probing Reasoning Models with Nationwide-Cohort Human Difficulty

Authors: Sanghee Park, Geewook Kim, Kee-Eung Kim
Published: 2026-06-09
Categories: cs.CL
arXiv: https://arxiv.org/abs/2606.10403v2

Math reasoning benchmarks have proliferated, yet most lack a per-item difficulty signal grounded in actual human performance. We introduce KCSAT-ML, a decade (2014-2025) of Korean College Scholastic Ability Test (KCSAT; Suneung) mathematics: 664 problems with a 339-item core set carrying official per-item error rates from nationwide cohorts of hundreds of thousands of examinees. We pair the benchmark with Difficulty-aligned Reasoning Gain (DRG): a score-orthogonal metric that asks whether a model's mistakes concentrate on the items humans found hard, or on items humans found easy. Together they expose, across a wide range of VLMs (and LLMs via OCR), three patterns: (i) low-budget accuracy collapses on the high-human-error tail at every model size; (ii) test-time scaling (TTS) raises token use roughly linearly with cohort error rate, while accuracy gains follow a non-monotonic curve; (iii) within a single family, TTS flips between anti-scaling on the hardest items and overthinking on easier ones -- two faces of the same alignment failure. On DRG, models with near-identical accuracy can sit at near-opposite values: one model gets wrong what humans also find hard, while another solves the hardest items yet fails on items humans find easy -- a contrast that aggregate accuracy hides. Our code and dataset builder will be open-sourced at https://github.com/naver-ai/KCSAT-ML.

---

### Harnessing the Collective Intelligence of AI Agents in the Wild for New Discoveries

Authors: Federico Bianchi, Yongchan Kwon, Aneesh Pappu, James Zou
Published: 2026-06-09
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2606.10402v2

Scientific discovery is often a collective process: researchers share partial results, inspect failed attempts, and build on each other's ideas over long time horizons. Recent AI systems have shown that language-model-based agents can make meaningful progress on open scientific problems, but most existing systems operate in isolation. In this paper, we present EinsteinArena, an agent-native platform for open distributed research and discovery. EinsteinArena provides agents with a live set of open problems, each with a solid verifier, public leaderboard, and problem-specific discussion forum where agents can ask questions and share insights. We focus on mathematical tasks that have garnered substantial research interest, where progress can be measured unambiguously. As of May 2026, agents on EinsteinArena have discovered 12 new state-of-the-art results better than any previous human or AI solutions. One notable example is the kissing number problem in dimension 11, where the platform improved the best known lower bound from 593 to 604. This advance did not come from a single agent or isolated run. Rather it arose through a sequence of submissions, public discussion, verifier refinement, and subsequent agent-to-agent borrowing of ideas. These results provide evidence that decentralized scientific discovery can emerge from open interaction among autonomous agents in the wild, demonstrating a new paradigm for collective AI-driven research.

---

### Harnessing the Collective Intelligence of AI Agents in the Wild for New Discoveries

Authors: Federico Bianchi, Yongchan Kwon, Aneesh Pappu, James Zou
Published: 2026-06-09
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2606.10402v1

Scientific discovery is often a collective process: researchers share partial results, inspect failed attempts, and build on each other's ideas over long time horizons. Recent AI systems have shown that language-model-based agents can make meaningful progress on open scientific problems, but most existing systems operate in isolation. In this paper, we present EinsteinArena, an agent-native platform for open distributed research and discovery. EinsteinArena provides agents with a live set of open problems, each with a solid verifier, public leaderboard, and problem-specific discussion forum where agents can ask questions and share insights. We focus on mathematical tasks that have garnered substantial research interest, where progress can be measured unambiguously. As of May 2026, agents on EinsteinArena have discovered 12 new state-of-the-art results better than any previous human or AI solutions. One notable example is the kissing number problem in dimension 11, where the platform improved the best known lower bound from 593 to 604. This advance did not come from a single agent or isolated run. Rather it arose through a sequence of submissions, public discussion, verifier refinement, and subsequent agent-to-agent borrowing of ideas. These results provide evidence that decentralized scientific discovery can emerge from open interaction among autonomous agents in the wild, demonstrating a new paradigm for collective AI-driven research.

---

### CoCoSI: Collaborative Cognitive Map Construction for Spatial Intelligence

Authors: Yiming Zhang, Ruoxuan Cao, Zhihang Zhong
Published: 2026-06-09
Categories: cs.CV
arXiv: https://arxiv.org/abs/2606.10401v2

Spatial intelligence is a key frontier for multimodal large language models (MLLMs), enabling them to reason about the physical world from visual experience. Inspired by human spatial cognition, recent approaches construct grid-based cognitive maps from multi-frame visual inputs to maintain coherent spatial representations over time. However, limited context lengths still challenge spatial understanding, while existing methods, such as long-context modeling and external memory, often require architectural changes, memory modules, or finetuning, limiting their applicability to off-the-shelf pretrained MLLMs. This motivates a lightweight, model-agnostic method for preserving spatial information beyond the native context window. To this end, we propose a plug-and-play multi-agent framework that collaboratively constructs cognitive maps as structured spatial memory, enhancing the spatial understanding of arbitrary pretrained MLLMs without architectural modification or additional training. Our framework features local-global agent coordination, cognitive map construction with atomic commits, and cross-agent verification. Extensive experiments demonstrate that our method achieves superior performance on spatial understanding tasks while remaining fully training-free. Code will be released.

---

### Do Vision-Language Models See or Guess? Measuring and Reducing Textual-Prior Reliance with a Phrasing-Controlled Benchmark

Authors: Pratham Singla, Shivank Garg, Vihan Singh, Paras Chopra
Published: 2026-06-09
Categories: cs.CL, cs.CV
arXiv: https://arxiv.org/abs/2606.10400v1

Vision-language models (VLMs) are increasingly deployed where answers must follow from what is in the image, yet they often answer from textual priors, the question's phrasing together with memorized world knowledge, rather than from the image itself, which inflates benchmark scores and yields confident but ungrounded answers. Existing benchmarks rarely isolate this behavior, since each image is usually paired with a single fixed question. To measure the reliance, we build a 540-image benchmark across six reasoning categories and generate four question variants over the same images, so that phrasing rather than image content is the controlled variable. The hardest variant is written directly from the image to minimize text leakage. We benchmark eleven VLMs spanning small open-weight models to large closed-source systems: every model degrades on the hardest variant, and open models fall furthest. Our central diagnostic is a no-image ablation, which collapses the open-weight models to their text-only floor (1 to 9 percent). Three further analyses, LLM-rated difficulty, low base-to-final textual similarity, and human re-annotation, corroborate genuine image-dependence. In-context exemplars that match how a variant was built recover the most accuracy, and GRPO post-training of a small VLM yields consistent gains across all four variants that transfer to a held-out out-of-distribution set. Textual-prior reliance is measurable and partly trainable away.

---

### Selection, Not Salience: The Shape and Limits of Personalization in Social Highlighting

Authors: Kazuki Nakayashiki, Keisuke Watanabe
Published: 2026-06-09
Categories: cs.IR, cs.CL, cs.HC, cs.SI
arXiv: https://arxiv.org/abs/2606.10398v1

Does personalizing what a reader sees pay off, and where does it stop? Using a social web highlighter and a co-readership identity control (the same document highlighted by many users, which holds document and topic fixed and asks whether a person's own history predicts their marks better than another reader's does), we map the shape and limits of personalization across reading altitudes. At the document altitude we give the clean, leakage-free, identity-controlled measurement that prior next-document evaluations could only upper-bound: a person's history identifies which documents in a co-reading neighborhood are theirs, with an own-versus-other gap of +0.169 against community negatives and +0.119 against topic-matched hard negatives (both highly significant); a content-based arm suggests the signal is not purely title-driven but is largely thematic. This is comparable to the span-level selection signal (+0.14) from our prior work: the selection signal is of comparable magnitude across altitudes (+0.12 to +0.17), most of it stable topic preference. At the sentence altitude, a two-stage personalized auto-highlight (an impersonal model proposes candidates, a personal model re-ranks them) does not improve on its impersonal baseline: two off-the-shelf zero-shot LLMs, including a frontier model, predict highlight locations worse than a lead baseline, and personal re-ranking is beaten by the salience order even on the highest-recall candidate pool, so the null is not merely a Stage-1 ceiling artifact. Measurable personalization appears primarily at the selection layer: modest (~+0.13), topic-dominated, with no reliable gain at the salience layer. We also surface a control-in-negatives bias that inflated our document gap to a spurious +0.227 until audited. Going beyond the shared salience layer may be better approached by aggregating individuals than by personalizing them harder.

---

### Efficient RWKV-based Representation Learning for 3D Point Clouds

Authors: Yun Liu, Xuefeng Yan, Liangliang Nan, Xianzhi Li, Peng Li, Zhe Zhu, Honghua Chen, Mingqiang Wei
Published: 2026-06-09
Categories: cs.CV
arXiv: https://arxiv.org/abs/2606.10395v1

The recent receptance weighted key value (RWKV) model combines RNN-style recurrence, offering a linear-complexity alternative to Transformers' quadratic self-attention for modeling global dependencies. However, when directly applied to point clouds, RWKV, originally developed for sequential text, struggles to capture local geometric structures and model spatial dependencies effectively. To address this, we propose the \textbf{P-RWKV} block, which bridges the gap between sequence modeling and irregular 3D geometry while preserving the efficiency advantages of RWKV. It consists of a Local Perception Expansion (LPE) component to expand contextual perception along the spatio-temporal sequence and a Spatial Context Enhancement (SCE) component to strengthen spatial awareness. To validate the effectiveness of P-RWKV for point cloud understanding, we construct PointER, a single-modality self-supervised representation learning framework whose encoder is composed of stacked P-RWKV blocks. Furthermore, we extend P-RWKV to a cross-modality setting and integrate the proposed core sub-modules into multiple architectures, demonstrating strong plug-and-play flexibility and architectural generality. Extensive experiments show that the P-RWKV block and its key sub-modules achieve competitive performance across various tasks with lower computational cost and inference latency. Code will be released upon acceptance.

---

### STAGE-Claw: Automated State-based Agent Benchmarking for Realistic Scenarios

Authors: Sirui Liang, Bohan Yu, Peiyu Wang, Shiguang Guo, Wenxing Hu, Pengfei Cao, Jian Zhao, Cao Liu, Ke Zeng, Xunliang Cai, Kang Liu
Published: 2026-06-09
Categories: cs.AI
arXiv: https://arxiv.org/abs/2606.10394v1

Large language models are increasingly used to power personal agents for everyday applications, but evaluating these agents remains a challenge. Existing benchmarks still rely on sandboxed artifacts, static task design, and coarse scoring, which hinder scalability and limit progress toward reliable personal-agent evaluation. This paper introduces STAGE-Claw, an automated framework for building and evaluating realistic personal-agent scenarios in state-based personal-computing environments. Given a task hint, STAGE-Claw automatically creates and validates a realistic benchmark task with its environment, task prompts, ground truth, and related verification programs. Agents are then evaluated in realistic operating environments, where performance is measured by the correctness of the final system state rather than only the textual response. Using STAGE-Claw, this paper creates a benchmark with 40 challenging real scenario agent tasks, evaluates 11 frontier models, and analyzes their task scores, costs, tool-call reliability, and common failure patterns. Overall, STAGE-Claw offers a scalable, state-based way to evaluate agents in realistic user scenarios.

---

### Validation-Stage Combinatorial Fusion Analysis for Imbalanced Credit-Card Fraud Detection

Authors: Xiao Han, Chenyu Wu
Published: 2026-06-09
Categories: cs.LG, cs.CE
arXiv: https://arxiv.org/abs/2606.10393v1

Credit-card fraud detection is difficult because fraudulent transactions are rare, costly, and unevenly distributed. Strong gradient-boosted tree models already perform well on structured transaction data, so the value of another fusion method is not obvious. This paper examines whether Combinatorial Fusion Analysis (CFA), which searches over model subsets and rank-score fusion rules, can still add value on the IEEE-CIS Fraud Detection benchmark. Using a leakage-free 60/20/20 train/validation/test protocol, we evaluate 480 fusion configurations built from seven base classifiers. The best test-set result comes from diversity-weighted score fusion of Random Forest, XGBoost, and LightGBM (DEF WtScore), with AUC-ROC = 0.9405, AUPRC = 0.6699, and F1 = 0.6373. Bootstrap confidence intervals from 1,000 resamples show that the gains over the strongest single model exclude zero for all three metrics. CFA matches soft voting on AUC-ROC, improves AUPRC and F1, and outperforms stacking in this setting. A CTGAN augmentation experiment gives a negative result: synthetic fraud samples degrade both individual models and CFA. Overall, CFA is most useful here not as a way to combine every classifier, but as a validation-stage method for choosing a small, complementary subset and assigning diversity-aware weights.

---

### Instruction Finetuning DeepSeek-R1-8B Model Using LoRA and NEFTune

Authors: Wu Yuerong, Mingni Luo
Published: 2026-06-09
Categories: cs.AI
arXiv: https://arxiv.org/abs/2606.10392v1

Financial named-entity recognition (NER) is essential for translating unstructured financial reports and news into structured knowledge graphs. However, general-purpose large language models (LLMs) often misclassify financial entities or ignore domain-specific patterns. This paper investigates the use of DeepSeek-R1-8B, a recent open-source large language model, combined with Low-Rank Adaptation (LoRA) and Noisy Embedding Fine-Tuning (NEFTune) for financial NER. Each annotated sentence in our corpus of 1693 samples is converted into an instruction-input-output triple. We insert lightweight LoRA matrices into the Transformer layers and apply NEFTune to improve generalisation by adding uniform noise to embedding vectors during training. Experiments show that the LoRA-adapted DeepSeek-R1-8B achieves a micro-F1 of 0.901 on seven entity types (Company, Date, Location, Money, Person, Product and Quantity), and adding NEFTune further boosts the micro-F1 to 0.912, outperforming Llama3-8B, Qwen3-8B, Baichuan2-7B, T5 and BERT-Base baselines.

---

### Beyond Static Evaluation: Co-Evolutionary Mechanisms for LLM-Driven Strategy Evolution in Adversarial Games

Authors: Haoran Li, Zengle Ge, Ziyang Zhang, Xiaomin Yuan, Yui Lo, Qianhui Liu, Bocheng An, Dongke Rong, Jiaqun Liu, Annan Li, Jianmin Wu, Dawei Yin et al.
Published: 2026-06-09
Categories: cs.AI
arXiv: https://arxiv.org/abs/2606.10389v1

Recent advances in LLM-driven code evolution have enabled automated discovery by iteratively generating and improving programs. However, applying these methods to adversarial multi-agent games introduces a fundamental challenge: the evaluation landscape shifts as strategies improve, causing fixed evaluators to become unreliable and evolution to stagnate. We propose three mechanisms to address this challenge: evaluator co-evolution, which incorporates discovered champions into the opponent pool; hierarchical deep evaluation, which replaces noisy few-game scores with statistically reliable assessments; and weakness pressure, which dynamically up-weights the most difficult opponents to break through plateaus. We implement these mechanisms within FAMOU, a framework built upon the same foundation-model code-evolution paradigm as OpenEvolve and ShinkaEvolve. On the MCTF 2026 3v3 maritime capture-the-flag task, FAMOU consistently outperforms both baselines under two backbone LLMs, achieving the highest combined score (0.526) and the best generalization to unseen opponents (61.7% win rate), while ablations confirm that each mechanism contributes to performance. Notably, the LLM mutation process generates tactical structures entirely absent from the seed strategies -- including lookahead search and adaptive interception -- demonstrating that code-level evolution can produce nontrivial algorithmic innovations in adversarial settings. The FAMOU-evolved strategy further achieved 1st place in the hardware round-robin and 3rd in simulation at the AAMAS 2026 MCTF Competition, validating its real-world transferability. The optimized implementation and corresponding evaluation codes developed through our evolutionary process are available at: https://github.com/1xiangliu1/FAMOU-CoEvo

---

### Right Family, Wrong Skill: Evaluating Risk Exposure in Agent Skill Retrieval

Authors: Jiandong Ding, Honglei Ji, Ming Liu, Tao Duan
Published: 2026-06-09
Categories: cs.IR, cs.AI
arXiv: https://arxiv.org/abs/2606.10388v3

Agent skill libraries are becoming routable software assets: a retrieved skill can contribute instructions, scripts, resource bindings, and execution assumptions to an agent. This makes retrieval failures more specific than broad irrelevance. A system can find the right capability family yet expose the wrong same-capability representative. We study this failure as same-capability risk-exposure retrieval. Each benchmark unit pairs a helpful skill with a query-specific risky sibling that shares the capability family but differs on an execution-controlling contract, such as the required resource, precondition, procedure, or artifact. We introduce SameCapRisk-Bench, an auditable benchmark with 1,190 skill-risk units and 1,686 evaluation query cases: 694 marked-sibling units under public library pressure and 496 hard role-flip units where the same two skills swap helpful/risky roles across paired queries. The release records admission evidence, cue/leakage checks, source hashes, family relations, and fixed candidate pools. The benchmark reports helpful ranking together with harmful sibling rate (HSR@K), the top-K exposure of the marked risky sibling. On this benchmark, public SkillRouter, SkillRet, and R3-Skill retrieve helpful skills at high Recall@3 (0.848--0.888) but also expose marked risky siblings frequently (HSR@3 0.346--0.372). A fully public score-and-cluster pipeline lowers HSR@3 to 0.128--0.182, with Recall@3 of 0.713--0.776. Under a benchmark-trained reference scorer, public text-cluster and controlled resolvers reach HSR@3 0.012 and 0.007; the latter attains Recall@3 0.833. Skill retrieval should therefore report both capability matching and same-family risk exposure, with HSR serving as a targeted exposure certificate for fixed skill libraries.

---

### SkillResolve-Bench: Measuring and Resolving Same-Capability Ambiguity in Agent Skill Retrieval

Authors: Jiandong Ding
Published: 2026-06-09
Categories: cs.IR, cs.AI
arXiv: https://arxiv.org/abs/2606.10388v1

Agent skill libraries are becoming routable software assets: a retrieved skill can contribute instructions, scripts, resource bindings, and execution assumptions to an agent. This makes skill retrieval more than broad relevance matching. A retriever can find the right capability family yet expose the wrong same-capability representative. We study this failure as same-capability execution-risk retrieval. Each query pairs a helpful skill with a query-specific risky sibling that shares the capability family but can lead execution toward a stale resource, missing precondition, or wrong procedure. We introduce SkillResolve-Bench 1.0, an auditable benchmark for this setting with 661 helpful/risky pairs, source-role and admission evidence, cue/leakage checks, query-disjoint splits, and a 7,982-candidate pool that includes 6,660 public SkillRet candidates. The benchmark reports helpful ranking together with harmful sibling rate (HSR@K), the top-K exposure of the risky sibling. We also provide SkillResolve, a reference method that resolves active candidate families, scores query-conditioned utility from confusable library negatives and contract-profile cues, and selects one representative from each family before the final top-K list. Under the released family relation, SkillResolve reaches Recall@3 0.766 and NDCG@3 0.699 while keeping HSR@3=0. It improves over SkillRouter by 0.112 Recall@3 and 0.165 NDCG@3 while reducing HSR@3 from 0.693 to 0. Without representative selection, HSR@3 rises to 0.236 under the same scorer, identifying within-family representative choice as the mechanism that turns capability retrieval into safer procedural exposure.

---

### Beyond Absolute Imitation: Anchored Residual Guidance for Privileged On-Policy Distillation

Authors: Wenhao Zhang
Published: 2026-06-09
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2606.10385v1

On-policy distillation (OPD) has demonstrated strong empirical gains in enhancing complex reasoning in LLMs by aligning a student model with a teacher's predictive distribution over the student's own trajectories. An emerging variant, Privileged OPD, further strengthens this paradigm by employing a self-teacher model augmented with privileged information, such as oracle traces, to mitigate teacher-student capacity gaps while providing dense, answer-directed supervision. However, current methods treat privileged information as a monolithic imitation target, failing to disentangle locally reachable reasoning steps from future-conditioned oracle signals. Consequently, the student is encouraged to match a hindsight-biased distribution that often falls outside its local predictive support. This reachability mismatch incentivizes the student model to skip valid intermediate reasoning in favor of locally unsupported shortcuts. To resolve this, we introduce Anchored Residual On-Policy Distillation (AR-OPD), a dual-view framework that disentangles privileged supervision. Rather than enforcing strict full-view imitation, AR-OPD establishes a locally compatible anchor using a partially privileged teacher, isolating and injecting oracle foresight as a controlled residual to provide destination-directed guidance. Across diverse reasoning tasks, AR-OPD outperforms full privileged OPD by 2.3 points and SFT by 7.9 points. Crucially, this anchored residual mechanism reduces hindsight leakage by 21.7% and mitigates late-stage drift, yielding up to a 7.2-point advantage on challenging long-horizon trajectories exceeding 768 tokens.

---

### Towards Critical Branching Mechanism in Recurrent Neural Networks

Authors: Feixiang Ren, Ling Feng
Published: 2026-06-09
Categories: nlin.AO, cs.AI, physics.comp-ph
arXiv: https://arxiv.org/abs/2606.10384v1

Criticality has been proposed as a key organizing principle in biological neural systems, yet its origin and relevance in artificial neural networks remain unclear. We analyze hidden-state dynamics in trained long short-term memory (LSTM) networks and show that small networks near their optimal training epochs (steps) exhibit scale-free avalanche statistics and branching parameters close to unity, indicative of near-critical dynamics, while larger models remain subcritical. To explain the coexistence of subcritical branching with robust $1/f^β$ noise, we introduce a mixture branching process framework that links heterogeneous branching dynamics to long-range temporal correlations. These results identify critical-like behavior in LSTMs as an emergent, capacity-dependent dynamical regime.

---

### Agentic Hybrid RAG for Evidence-Grounded Muon Collider Analysis

Authors: Ruobing Jiang, Dawei Fu, Cheng Jiang, Tianyi Yang, Zijian Wang, Youpeng Wu, Yong Ban, Yajun Mao, Qiang Li
Published: 2026-06-09
Categories: hep-ex, cs.AI, cs.CL, cs.IR, physics.ins-det
arXiv: https://arxiv.org/abs/2606.10381v2

Muon collider research spans accelerator physics, detector instrumentation, and high-energy phenomenology, with relevant evidence scattered across a rapidly expanding and heterogeneous body of scientific literature. As high-energy physics (HEP) increasingly explores agent-assisted analysis workflows, efficiently locating, integrating, and verifying scientific evidence becomes an essential capability. While retrieval-augmented generation (RAG) offers a promising framework for scientific question answering, integrating agentic reasoning without compromising retrieval precision remains a key challenge. In this work, we present agentic hybrid RAG, an evidence-grounded RAG framework for muon collider research. The framework combines a hybrid retriever, integrating sparse lexical and dense semantic retrieval, with an agentic reasoning module for query decomposition, evidence expansion, and grounded answer generation. To enable systematic evaluation, we construct the first benchmark for retrieval-augmented scientific question answering in the muon collider domain, comprising a curated literature corpus together with dedicated retrieval and answer-generation benchmarks covering major detector and physics research topics. Extensive evaluation shows that hybrid retrieval provides the strongest retrieval backbone, while agentic reasoning is most effective for controlled evidence expansion and answer synthesis. Built on this principle, agentic hybrid RAG consistently outperforms representative retrieval and RAG baselines in retrieval effectiveness, answer quality, evidence coverage, and factual grounding. Together, the benchmark and framework provide a foundation for evidence-grounded scientific question answering and future HEP analysis agents operating over large-scale scientific literature. Code is available at \href{https://github.com/AItutorialjrb/RAG_muon_JINST}{this URL}.

---

### Agentic Hybrid RAG for Evidence-Grounded Muon Collider Analysis

Authors: Ruobing Jiang, Dawei Fu, Cheng Jiang, Tianyi Yang, Zijian Wang, Youpeng Wu, Yong Ban, Yajun Mao, Qiang Li
Published: 2026-06-09
Categories: hep-ex, cs.AI, cs.CL, cs.IR, physics.ins-det
arXiv: https://arxiv.org/abs/2606.10381v1

Muon collider research spans accelerator physics, detector instrumentation, and high-energy phenomenology, with relevant evidence scattered across a rapidly expanding and heterogeneous body of scientific literature. As high-energy physics (HEP) increasingly explores agent-assisted analysis workflows, efficiently locating, integrating, and verifying scientific evidence becomes an essential capability. While retrieval-augmented generation (RAG) offers a promising framework for scientific question answering, integrating agentic reasoning without compromising retrieval precision remains a key challenge. In this work, we present agentic hybrid RAG, an evidence-grounded RAG framework for muon collider research. The framework combines a hybrid retriever, integrating sparse lexical and dense semantic retrieval, with an agentic reasoning module for query decomposition, evidence expansion, and grounded answer generation. To enable systematic evaluation, we construct the first benchmark for retrieval-augmented scientific question answering in the muon collider domain, comprising a curated literature corpus together with dedicated retrieval and answer-generation benchmarks covering major detector and physics research topics. Extensive evaluation shows that hybrid retrieval provides the strongest retrieval backbone, while agentic reasoning is most effective for controlled evidence expansion and answer synthesis. Built on this principle, agentic hybrid RAG consistently outperforms representative retrieval and RAG baselines in retrieval effectiveness, answer quality, evidence coverage, and factual grounding. Together, the benchmark and framework provide a foundation for evidence-grounded scientific question answering and future HEP analysis agents operating over large-scale scientific literature.

---

### Expert-Level Crisis Detection in Mental Health Conversations

Authors: Grace Byun, Abigail Lott, Rebecca Lipschutz, Sean T. Minton, Elizabeth A. Stinson, Jinho D. Choi
Published: 2026-06-09
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2606.10380v3

Real-world crisis intervention is inherently conversational, yet existing research largely focuses on static texts. When applied to multi-turn dialogues, current models exhibit significant performance degradation, struggling to track risk signals that emerge as context evolves. To address this gap, we introduce CRADLE-Dialogue, a clinician-annotated benchmark for turn-level crisis detection in conversational settings. The dataset features 600 dialogues with multi-label annotations across clinically grounded risks, including suicide ideation, self-harm, and child abuse, distinguishing past from ongoing risk. We further propose an Alert-Confirm evaluation protocol that distinguishes early warning signals (Alert) from turns where a specific crisis becomes explicitly identifiable (Confirm), reflecting the clinical need to intervene before risk becomes explicit. Experiments show that identifying when risk emerges is much harder than recognizing that it exists: models achieve only mid-40% to high-60% Micro F1. Additionally, we release a synthetic training corpus and a 32B-parameter model that substantially outperforms existing open-source models and achieves competitive or superior results against proprietary models across turn-level, dialogue-level, and confirm-only evaluation settings.

---

### Expert-Level Crisis Detection in Mental Health Conversations

Authors: Grace Byun, Abigail Lott, Rebecca Lipschutz, Sean T. Minton, Elizabeth A. Stinson, Jinho D. Choi
Published: 2026-06-09
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2606.10380v1

Real-world crisis intervention is inherently conversational, yet existing research largely focuses on static texts.Real-world crisis intervention is inherently conversational, yet existing research largely focuses on static texts. When applied to multi-turn dialogues, current models exhibit significant performance degradation, struggling to track risk signals that emerge as context evolves. To address this gap, we introduce CRADLE-Dialogue, a clinician-annotated benchmark for turn-level crisis detection in conversational settings. The dataset features 600 dialogues with multi-label annotations across clinically grounded risks, including suicide ideation, self-harm, and child abuse, distinguishing past from ongoing risk. We further propose an Alert-Confirm evaluation protocol that distinguishes early warning signals (Alert) from turns where a specific crisis becomes explicitly identifiable (Confirm), reflecting the clinical need to intervene before risk becomes explicit. Experiments show that identifying when risk emerges is much harder than recognizing that it exists: models achieve only mid-40% to high-60% Micro F1. Additionally, we release a synthetic training corpus and a 32B-parameter model that substantially outperforms existing open-source models and achieves competitive or superior results against proprietary models across turn-level, dialogue-level, and confirm-only evaluation settings.

---