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
02.
arXiv (CS.CL) 2026-06-12

The Illusion of Multi-Agent Advantage

Authors:
Prathyusha Jwalapuram↗Hehai Lin↗Chuyuan Li↗Fangkai Jiao↗Sudong Wang↗Yifei Ming↗Zixuan Ke↗Chengwei Qin↗Giuseppe Carenini↗Shafiq Joty↗

Prevailing wisdom posits that Multi-Agent Systems (MAS) are superior to Single-Agent Systems (SAS), citing advantages like context protection, parallel processing and distributed decision-making. However, empirical support for this claim relies primarily on comparisons with SAS baselines using benchmarks that prioritize isolated reasoning tasks, which do not adequately assess these advantages. Focusing on automatically generated MAS that are designed for enhanced generalizability over manually-designed counterparts, we perform a rigorous, systematic evaluation against SAS, specifically Chain-of-Thought with Self-Consistency (CoT-SC). Across traditional reasoning datasets and tasks with interactive multi-step workflows (e.g., BrowseComp-Plus), we demonstrate that automatic MAS consistently underperform CoT-SC despite being up to 10x more expensive. To isolate these failures from limitations inherent to task structure, we introduce a diagnostic synthetic dataset tailored for MAS featuring explicit task decomposition, context separation and parallelization potential. We show that expert-architected MAS consistently outperforms automatically generated architectures in both raw performance and cost-efficiency on this dataset, demonstrating that existing evaluation frameworks mask critical architectural gaps and inefficiencies of complex MAS by failing to account for the marginal utility of increased computational cost. Critically, systematic deconstruction of the generated MAS architectures reveals that current automated design paradigms produce architectural bloat that prioritizes superficial complexity which does not translate into functional utility, exposing a fundamental misalignment with multi-agent principles.

Read & Discuss → View Source →
03.
arXiv (CS.CV) 2026-06-12

Goal2Pixel: Grounding Goals to Pixels for Vision-Language Navigation

Authors:
Muyi Bao↗Yuxin Cai↗Hang Xu↗Zongtai Li↗Jinxi He↗Jingfan Tang↗Chen Lv↗Ji Zhang↗Yaqi Xie↗Wenshan Wang↗

Vision-language models (VLMs) have become a common foundation for vision-and-language navigation in continuous environments (VLN-CE). Yet most VLM-based methods cast navigation as low-level action prediction, an interface that is ambiguous, tied to short-horizon motion primitives, and inefficient due to repeated VLM querying. We propose Goal2Pixel, a pure pixel-based paradigm that reformulates VLN-CE as navigable pixel grounding. Rather than predicting actions, Goal2Pixel uses the image plane as a unified spatial interface between VLM reasoning and robot motion: the model predicts a visible navigable pixel to the agent, which is back-projected into a 3D waypoint for forward navigation. For non-forward actions, we append auxiliary directive regions to the image plane, where the left/right/bottom regions are interpreted as turning left, turning right, and stopping, respectively. To enable long-horizon navigation, we propose a visibility-aware keyframe memory for compact and informative history representation. To adapt pretrained VLMs to navigable pixel grounding, we introduce semantic embeddings and coordinate-aware auxiliary losses. Goal2Pixel achieves competitive state-of-the-art performance while requiring fewer VLM inference calls than prior methods. On R2R-CE Val-Unseen it achieves 54.1% SR and 52.5% SPL with just 7.75 VLM calls per episode, 6x fewer than the 46.62 required by direct action prediction at 32.9% SR. The same trend holds on RxR-CE.Project Page: https://baobao0926.github.io/Goal2Pixel/.

Read & Discuss → View Source →
04.
arXiv (CS.AI) 2026-06-12

ARROW: Augmented Replay for RObust World models

Authors:
Abdulaziz Alyahya↗Abdallah Al Siyabi↗Markus R. Ernst↗Luke Yang↗Levin Kuhlmann↗Gideon Kowadlo↗

arXiv:2603.11395v3 Announce Type: replace-cross Abstract: Continual reinforcement learning challenges agents to acquire new skills while retaining previously learned ones with the goal of improving performance in both past and future tasks. Most existing approaches rely on model-free methods with replay buffers to mitigate catastrophic forgetting; however, these solutions often face significant scalability challenges due to large memory demands. Drawing inspiration from neuroscience, where the brain replays experiences to a predictive World Model rather than directly to the policy, we present ARROW (Augmented Replay for RObust World models), a model-based continual RL algorithm that extends DreamerV3 with a memory-efficient, distribution-matching replay buffer. Unlike standard fixed-size FIFO buffers, ARROW maintains two complementary buffers: a short-term buffer for recent experiences and a long-term buffer that preserves task diversity through intelligent sampling. We evaluate ARROW on two challenging continual RL settings: Tasks without shared structure (Atari), and tasks with shared structure, where knowledge transfer is possible (Procgen CoinRun variants). Compared to model-free and model-based baselines with replay buffers of the same-size, ARROW demonstrates substantially less forgetting on tasks without shared structure, while maintaining comparable forward transfer. Our findings highlight the potential of model-based RL and bio-inspired approaches for continual reinforcement learning, warranting further research.

Read & Discuss → View Source →
05.
arXiv (quant-ph) 2026-06-11

Holographic Complexity, Extremality, and Cosmic Censorship

Authors:
Fuat Berkin Altunkaynak↗

arXiv:2604.20170v2 Announce Type: replace-cross Abstract: We propose a holographic complexity origin for the third law of black-hole mechanics and weak cosmic censorship. In both complexity equals action and complexity equals volume prescriptions, the relative complexity between subextremal and extremal AdS black holes diverges logarithmically. For overcharged RN-AdS, explicit calculations in both prescriptions show that the near-singularity action terms are power-law divergent or finite, while the maximal-volume contribution is finite. Thus, the extremal-to-naked relative complexity also diverges, obstructing finite-time transitions.

Read & Discuss → View Source →
06.
bioRxiv (Bioinfo) 2026-06-21

SPA-C: an hybrid tool to accurately scaffold genomes using Hi-C and Deep-Learning

Authors:
Mergez↗Mourad↗Hernandez-Raquet↗Zytnicki↗

Genome assembly is a computational pipeline designed to reconstruct chromosomes from small sequencing reads. Following their assembly, contiguous sequences (contigs) are arranged into chromosome-long sequences during scaffolding. Hi-C, a long-range linkage information between regions of the genome widely used in recent large sequencing projects, is often required to correctly order contigs. Several tools have been developed to automate this task following either statistical or deep-learning approaches. Statistical approaches summarise 2D Hi-C matrices into contact densities across sequences, thus ignoring informative visual patterns. The sole existing deep-learning tool uses a transformer-based computer vision model to correct the assembly. It has been trained on several species and uses Hi-C matrices directly. Yet it comes as a supplementary step in the scaffolding process, introducing extra computation time, and has been trained on a dataset that might contain labelling errors, which could provide sub-optimal results. We propose SPA-C, an hybrid pipeline combining the strengths of both approaches. Linkage prediction is handled with a frugal CNN-based model and a graph-solving algorithm is used to generate the scaffolds. Through our input's design, the model is able to both correct errors within assemblies and link contigs, leveraging small, local Hi-C contact matrices. We handled low-complexity regions that might induce erroneous predictions using an external tool, improving the overall accuracy of generated assemblies. On a benchmark of six various genomes and four standard metrics, SPA-C outperformed four out of four state-of-the-art methods while achieving comparable start-to-end computation time.Python and Bash scripts are available on GitHub (https://github.com/SPA-C/SPA-C.git) and Zenodo (https://doi.org/10.5281/zenodo.19000361).

Read & Discuss → View Source →
07.
arXiv (CS.AI) 2026-06-16

OSGuard: A Benchmark for Safety in Computer-Use Agents

Authors:
Mina Mohammadmirzaei↗Jeffrey Flanigan↗

arXiv:2606.15034v1 Announce Type: new Abstract: Computer-use agents are increasingly evaluated by whether they complete realistic desktop and web tasks. However, task success alone can miss failures in which an agent reaches the nominal goal through an unsafe shortcut. We introduce OSGuard, a dual-granularity benchmark suite for evaluating safety in computer-use agents under benign, unchanged user instructions. OSGuard contains an action-level benchmark for local guardrail decisions and a risk-augmented execution suite for end-to-end evaluation. The action-level benchmark consists of contextualized proposed actions labeled as allowed, unrelated, or unsafe, each judged relative to the original instruction and current interface state. The execution suite contains manually constructed OSWorld-derived task variants in which the original task remains achievable, but the environment is modified to introduce latent hazards such as destructive overwrites, etc. Each variant is paired with augmented evaluators that retain the original task-success criterion while adding explicit state-based safety invariants, allowing us to distinguish safe completions from unsafe completions that satisfy the nominal task objective. Our experimental results on OSGuard show that current multimodal guardrails can perform well on isolated action judgments, while risk-augmented execution exposes remaining gaps between local oversight and reliable end-to-end safety. This dual-granularity design enables more precise diagnosis of whether models can both recognize unsafe proposed actions and improve full-task safety when deployed as guardrails.

Read & Discuss → View Source →
08.
medRxiv (Medicine) 2026-06-22

ECG-Guided Pre-Screening of Family Members for Hypertrophic Cardiomyopathy

Authors:
Lootah↗Min↗Fatah↗Hamilton↗R. M↗Mital↗

Background: Current clinical guidelines recommend serial ECG and echocardiographic surveillance for first-degree relatives of probands with Hypertrophic Cardiomyopathy (HCM). Objectives: To evaluate the accuracy and validity of ECG alone as a pre-screening tool for the diagnosis of HCM and to develop a random forest (RF) model for HCM phenotype prediction. Method: Pediatric relatives of primary HCM probands attending the cardiomyopathy screening program at The Hospital for Sick Children were included from 1993 to 2025. Subjects were followed until the last follow-up, censored at phenotype conversion. ECGs were classified as normal or abnormal based on predefined parameters. Associations between binary ECG variables and HCM phenotype were assessed using Phi ({varphi}) coefficient. A Random Forest classifier was developed using significant ECG variables (70:30 training: test split) and evaluated using precision, recall, specificity, negative predictive value, F1 score and AUROC. Feature importance was assessed using SHAP analysis. Variables with an impact of >5% were included in a simplified model, which was evaluated by repeating performance metrics and externally validated in a healthy cohort. Results: 350 screened relatives (44% female, mean follow-up 6.8 +- 4.8 years) were included. At baseline, 13% (46350) were phenotype-positive for HCM. 9 subjects converted during the surveillance. Thirteen ECG variables were significantly associated with phenotype-positive HCM and were included in the full random forest model. Four variables had >5% impact (Left ventricular hypertrophy, right ventricular hypertrophy, T-wave inversion and ST-segment depression) and were included in a simplified model, which maintained high specificity (93% vs 97%), negative predictive value (97% vs 93%) and AUROC (90% vs 96%). The simplified model classified 83% subjects as phenotype-negative, with eight being false-negative, all of whom developed an abnormal ECG in a mean of 1 year, and none had an interim adverse cardiac event. The simplified model was evaluated in an independent healthy cohort of 153 school-age subjects and correctly identified 98% as phenotype-negative with 100% NPV. Conclusion: ECG abnormalities were strongly associated with phenotype-positive status. A simplified ECG-based random forest model using four ECG variables demonstrated high specificity and negative predictive value for identifying phenotype-negative subjects. If prospectively validated, this could reduce the need for concurrent echocardiographic screening by up to 83% per encounter, lowering screening burden and cost.

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

Mapping AI Programs in the U.S: A Status Report from Early 2026 and an Analysis of AI Majors and Minors

Authors:
Felix Muzny↗Carolyn Jones↗Carter Ithier↗Hasnain Sikora↗Hrutika Harshadbhai Patel↗Carla E. Brodley↗

arXiv:2606.12428v1 Announce Type: cross Abstract: We present a report on the status of undergraduate Artificial Intelligence (AI) programs in the United States in Spring 2026. In so doing, we 1) describe our scraping and mapping tools, which dynamically update to track the state of AI education in the U.S., and 2) create a historic record at a time of great upheaval. The tool we developed, available at https://cicmap.ai, detects, scrapes, and displays data from more than 350 undergraduate AI programs–majors, minors, concentrations, and certificates–at 4-year universities. Our tool searched over 560 institutions to locate these programs, a sample that represents 86\% of all undergraduate Computer Science (CS) graduates in the U.S. This tool allows prospective students, guidance counselors, administrators, and faculty to easily access AI program requirements and is designed to continually update as new programs emerge. To the best of our knowledge, this survey represents the most comprehensive snapshot of the state of AI programs in the U.S. to date. With this work we offer three important contributions: 1) a record of AI programs in the U.S. at a time of great upheaval; 2) a tool to explore AI programs and their requirements; and 3) an analysis of the courses required for 66 AI majors and 87 AI minors. Our analysis of majors and minors shows great variability in the size and the requirements of these degrees, but we note two takeaways. First, not all majors require a general AI course, but if they don't, they do require a Machine Learning (ML) course. Second, while more than a third of majors require an Ethics in AI course, just under a quarter of AI minors do.

Read & Discuss → View Source →
10.
arXiv (CS.LG) 2026-06-17

Resource-Efficient Variational Quantum Classifier

Authors:
Petr Pt\'a\v{c}ek↗Paulina Lewandowska↗Ryszard Kukulski↗

arXiv:2511.09204v3 Announce Type: replace-cross Abstract: We introduce the unambiguous quantum classifier based on Hamming distance measurements combined with classical post-processing. The proposed approach improves classification performance through a more effective use of ansatz expressivity, while requiring significantly fewer circuit evaluations. Moreover, the method demonstrates enhanced robustness to noise, which is crucial for near-term quantum devices. We evaluate the proposed method on a breast cancer classification dataset. The unambiguous classifier achieves an average accuracy of 90%, corresponding to an improvement of 6.9 percentage points over the baseline, while requiring eight times fewer circuit executions per prediction. In the presence of noise, the improvement is reduced to approximately 3.1 percentage points, with the same reduction in execution cost. We substantiate our experimental results with theoretical evidence supporting the practical performance of the approach.

Read & Discuss → View Source →
11.
medRxiv (Medicine) 2026-06-22

Assessment of adaptive functioning in Angelman syndrome using the Vineland Adaptive Behavior Scales, Third Edition

Authors:
Potter↗S. N↗Zhang↗Friedman↗Gable↗Ali↗Barbieri-Welge↗R. L↗Ben-Tall↗Caravella↗K. E↗DeRamus↗…

Purpose: This study examined longitudinal trajectories of adaptive functioning in 331 individuals with Angelman syndrome (AS) using the Vineland Adaptive Behavior Scales, Third Edition (Vineland-3) and examined differences by molecular subtype. Methods: A total of 331 individuals (156 females, 47%) with genetically confirmed AS (ages 6 months to 52 years) were assessed between 2018 and 2025, including 207 with a deletion subtype, 63 with uniparental disomy or imprinting defect, and 61 with a UBE3A point mutation. Growth scale values were analyzed using linear mixed-effects models with log2-transformed age. Results: Individuals with deletion subtypes demonstrated significantly lower adaptive functioning across domains compared to those with non-deletion subtypes. Adaptive skills across all Vineland-3 subdomains increased nonlinearly with age, showing faster growth early in life that slowed over time, with largely parallel trajectories across subtypes. Conclusion: Individuals with AS demonstrate slow but steady growth in adaptive functioning that continues into adulthood, with progress varying by molecular subtype. These findings provide updated natural history benchmarks and demonstrate the utility of the Vineland-3 for clinical trials.

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

URDF Synthesis from RGB-D Sequences via Differentiable Joint Inference and Energy-Consistent Verification

Authors:
Xinze Zhang↗

Reconstructing simulation-ready digital twins of articulated objects from sensor observations remains constrained by two persistent gaps: (i) part-level geometric reconstruction is decoupled from kinematic-parameter estimation, and (ii) the recovered models often violate basic dynamic invariants such as energy conservation, leading to drift when the URDF is replayed in physics simulators. We present KinemaForge, a constraint-driven pipeline that jointly infers part-level shape, joint topology, and joint parameters from short RGB-D sequences and validates the result against an energy-consistent verifier built on differentiable rigid-body dynamics. The pipeline introduces three components: a kinematic constraint graph that encodes joint-part incidences as soft edges; a differentiable screw-axis solver that backpropagates from rendered observations through Featherstone's articulated-body algorithm to joint parameters; and an energy residual loss that penalises non-physical free responses of the reconstructed model. Across five PartNet-Mobility categories and an internal RGB-D benchmark, KinemaForge reduces the average joint-axis error from 4.52 degrees to 2.83 degrees (-37.4%) over the strongest geometric baseline (PARIS) and from 5.30 degrees to 2.83 degrees (-46.6%) over the interaction-based Ditto baseline, lowers long-horizon simulation drift by 64% (vs. PARIS) over 50 s rollouts, and yields URDFs whose closed-loop manipulation success rate improves by 14.6 percentage points over Ditto in our preliminary evaluation. Code and reconstruction data will be released upon acceptance.

Read & Discuss → View Source →
13.
arXiv (CS.CL) 2026-06-24

AGORA: An Archive-Grounded Benchmark for Agentic Workplace Document Reasoning

Authors:
Honglin Guo↗Qi Zhang↗Yu Zhang↗Weijie Li↗Rui Zheng↗Zhikai Lei↗Qiyuan Peng↗Zhiheng Xi↗Tao Gui↗

Large language models are increasingly deployed as agents that reason over documents rather than answer from parametric knowledge. We study archive-grounded reasoning: locating sparse evidence across a large, messy collection of workplace files, reconciling inconsistent terminology, units, and time conventions, and computing an answer. Existing benchmarks address only parts of this setting and none jointly stresses archive-groundedness, agentic exploration, and cross-domain coverage. We introduce Agora, a benchmark pairing 362 questions with eight domain collections of 9,664 authentic documents and 372M tokens, far exceeding any model's context window, so agents must explore deliberately rather than scan exhaustively. Agora is built by an agentic pipeline combining cross-document task synthesis, leakage-preventing obfuscation, and difficulty filtering. Evaluating eight models, we find the task far from solved: even the strongest reaches only 59.4% accuracy, with notable variation across domains.

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

Stringalign: Moving beyond summary statistics with a transparent Unicode-aware tool for evaluating automatic transcription models

Authors:
Yngve Mardal Moe↗Marie Roald↗

Comparing text strings is crucial when evaluating and understanding the performance of various text processing tasks such as document recognition and audio transcription. With an increasingly complex landscape of AI-based handwritten text recognition (HTR), optical character recognition (OCR) and automatic speech recognition (ASR) models, there is a need for tools that facilitate evaluation in a flexible and reproducible way. This paper presents Stringalign, a Python library designed to simplify the evaluation process for automatic transcription projects and facilitate transparent evaluation. Stringalign's tools to examine and visualise both the rate of errors and the types of errors a model makes, give insights into possible improvements and help inform model selection for a particular task. Widely used string comparison metrics, such as the character and word error rates (CER and WER), although useful, can be ambiguous due to varying definitions of what constitutes a character and a word. Stringalign addresses this challenge by ensuring all preprocessing (i.e. normalisation and tokenisation) is transparent and easily replicable, and by providing tools to move beyond summary statistics and analyse common model errors. Moreover, Stringalign adheres to FAIR (Findable, Accessible, Interoperable, and Reusable) principles for research software while staying lightweight and easy to adapt into researchers existing workflows. In this paper, we discuss challenges with character and word level string comparisons and show through examples that where existing tools can yield opaque and sometimes confusing results, Stringalign provides an easy-to-use and unambiguous alternative.

Read & Discuss → View Source →
15.
arXiv (CS.AI) 2026-06-11

PROJECTMEM: A Local-First, Event-Sourced Memory and Judgment Layer for AI Coding Agents

Authors:
Ripon Chandra Malo↗Tong Qiu↗

arXiv:2606.12329v1 Announce Type: new Abstract: AI coding assistants now support a growing share of software work, from quick scripts to production applications. Yet these agents remain largely stateless: each new session re-reads project files, re-derives prior decisions, and - most costly - may repeat debugging attempts that already failed. Reconstructing this context can consume an estimated 5,000-20,000 tokens per session; the bottleneck is often not model capability but missing project memory. We present projectmem, an open-source, local-first memory and judgment layer for AI coding agents. projectmem records development as an append-only, plain-text event log of typed events - issues, attempts, fixes, decisions, and notes - and deterministically projects that log into compact, AI-readable summaries served through the Model Context Protocol (MCP). Beyond storage, projectmem adds a deterministic pre-action gate that warns an agent before it repeats a previously failed fix or edits a known-fragile file. We frame this as Memory-as-Governance: memory that does not merely answer the agent but acts on its next action. The system runs fully offline with no telemetry; its immutable log also serves as a provenance trail for reproducible, auditable AI-assisted development. projectmem ships as a three-dependency Python package (14 MCP tools, 19 CLI commands, 37 automated tests) and is evaluated through a two-month self-study across 10 projects comprising 207 logged events. Source code: https://github.com/riponcm/projectmem.

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

A spectral audit framework reveals task-dependent aperiodic reliance across EEG and ECG deep learning

Authors:
Jasmeet Singh Bindra↗Siddharth Panwar↗

arXiv:2606.08583v2 Announce Type: replace Abstract: Deep learning on physiological time series is interpreted through domain-specific features – oscillatory rhythms in EEG, morphological complexes in ECG – yet these signals sit atop a broadband aperiodic 1/f-like envelope that covaries with arousal, age, and pathology. We introduce a spectral audit framework combining aperiodic/periodic decomposition, phase-preserving Fourier interventions, sham controls, and simulation validation. Aperiodic reliance was task-dependent and architecture-general: across six neural architectures, flattening drops exceeded 0.42 balanced-accuracy points for sleep-wake classification, reached 0.07-0.13 for clinical abnormality detection, and remained minimal for motor imagery. Six of seven EEG foundation models showed FDR-significant aperiodic reliance on clinical EEG; age/sex and recording-era controls reduced but did not eliminate the effect. Applying the audit to PTB-XL ECG revealed neural drops of 0.32–0.36 persisting after demographic matching, confirming this confound class extends beyond EEG. Aperiodic controls should become standard for interpretable physiological time-series deep learning.

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

Towards Conditional Feature Alignment for Cross-Domain Counting

Authors:
Zhuonan Liang↗Dongnan Liu↗Jianan Fan↗Yaxuan Song↗Qiang Qu↗Runnan Chen↗Yu Yao↗Peng Fu↗Weidong Cai↗

Object counting models often degrade under cross-domain deployment because density composition varies across domains and is itself task-relevant. Standard feature alignment methods tend to suppress such variation by encouraging global domain invariance, which can be harmful when source and target domains contain different proportions of background, sparse foreground, and dense foreground. We propose Conditional Feature Alignment (CFA), a cross-domain counting framework that aligns representations within label-induced conditions rather than across full marginal feature distributions. Given density annotations or pseudo-density predictions, CFA constructs foreground/background or density-level conditions and aligns only features belonging to matching conditions. We formalise this idea through a conditional divergence perspective, showing that conditional alignment removes within-condition discrepancy while preserving condition-marginal density shift. For unsupervised domain adaptation, CFA estimates source conditions from annotations and target conditions from detached pseudo-density maps, then performs condition-wise adversarial alignment with full-image consistency regularisation. For source-domain generalisation, we instantiate the same principle with MPCount by enforcing condition-wise memory-consistency between generated source-domain views. Experiments on crowd and cell counting benchmarks show competitive or improved performance across diverse UDA and DG settings. For example, on JHU-CROWD++ FH$\rightarrow$SN, CFA-DG reduces MAE/RMSE from MPCount's 216.3/421.4 to 90.5/169.9, indicating that condition-wise alignment is especially effective under large weather- and density-induced shifts. These results suggest that condition-wise alignment is a promising design principle for domain-adaptive counting.

Read & Discuss → View Source →
18.
arXiv (CS.LG) 2026-06-16

The Data Manifold under the Microscope

Authors:
Marios Koulakis↗Constantin Seibold↗

arXiv:2606.15760v1 Announce Type: new Abstract: A significant gap exists between theory and practice in deep learning. Generalization and approximation error bounds are often derived for simplified models or are too loose to be informative. Many rely on the manifold hypothesis and on geometric regularity such as intrinsic dimension, curvature, and reach. Progress requires insight into data-manifold geometry and suitable benchmarks, yet existing options are polarized: analytic manifolds with known geometry but limited applicability, or real-world datasets where geometry is only coarsely estimable. We introduce a benchmarking framework for studying data geometry. We repurpose and extend dSprites and COIL-20 with additional transformation dimensions and dense, axis-aligned sampling, and pair them with finite-difference estimators that recover curvature, reach, and volume at near-ground-truth accuracy in a regime where general-purpose estimators are unreliable or difficult to deploy. The framework is intended as a controlled testbed, useful as a calibration environment for geometric estimators and a sandbox for probing theoretical assumptions. To illustrate its use, we present two application studies, namely assessing the scaling behavior of the bounds of Genovese et al. and Fefferman et al., and tracking the layer-wise geometry of a $\beta$-VAE, highlighting the behavior of current bounds and the value of controlled benchmarks for guiding and validating future theory. A reference implementation is available at https://github.com/koulakis/manifold-microscope.

Read & Discuss → View Source →
19.
arXiv (CS.AI) 2026-06-18

SafeClawBench: Separating Semantic, Audit-Evidence, and Sandbox Harm in Tool-Using LLM Agents

Authors:
Yuchuan Tian↗Mengyu Zheng↗Haocheng Mei↗Ye Yuan↗Chao Xu↗Xinghao Chen↗Hanting Chen↗Yu Wang↗

arXiv:2606.18356v1 Announce Type: cross Abstract: Tool-using language-model agents introduce security failures that go beyond unsafe text: they can disclose protected objects, write persistent memory, send messages, modify databases, or trigger harmful code and tool effects. Existing evaluations often collapse these stages into a single attack success rate, making it difficult to tell whether a model merely agreed with an attacker or actually produced observable harm. We introduce SafeClawBench, a staged benchmark for tool-using agent security with 600 controlled adversarial tasks across six attack families: direct and indirect prompt injection, tool-return injection, memory poisoning, memory extraction, and ambiguity-driven unsafe inference. SafeClawBench reports three separate endpoints: semantic attack acceptance, audit-visible harm evidence, and sandbox-observed tool/state harm. Evaluating five agent endpoints under four prompt-level policies, we find that these endpoints capture different failure modes. Without additional prompt protection, semantic failure rates vary widely across models, from 9.0% to 44.2%. Audited harm evidence is narrower than semantic failure, and under a separate executable protocol some matched task identities produce sandbox harm despite passing the Semantic Core call: in a 12,000-row matched analysis, 291 of 347 observed sandbox harms occur in rows that pass the semantic check. Prompt policies change endpoint outcomes, but their effects depend on both model and protocol. SafeClawBench provides a reproducible framework for comparing agent models and prompt-policy conditions without conflating textual compliance, evidence-supported harm, and executable state changes. The open-source dataset is available at https://huggingface.co/datasets/sairights/safeclawbench.

Read & Discuss → View Source →
20.
arXiv (CS.LG) 2026-06-16

Escaping the Cognitive Well: Efficient Competition Math with Off-the-Shelf Models

Authors:
Xingyu Dang↗Rohit Agarwal↗Rodrigo Porto↗Anirudh Goyal↗Liam H Fowl↗Sanjeev Arora↗

arXiv:2602.16793v2 Announce Type: replace Abstract: In the past year, custom and unreleased math reasoning models reached gold medal performance on the International Mathematical Olympiad (IMO). Similar performance was then reported using large-scale inference on publicly available models but at prohibitive costs (e.g., 3000 USD per problem). In this work, we present an inference pipeline that attains best-in-class performance on IMO-style math problems at an average inference cost orders of magnitude below competing methods while using only general-purpose off-the-shelf models. Our method relies on insights about grader failure in solver-grader pipelines, which we call the Cognitive Well (iterative refinement converging to a wrong solution that the solver as well as the pipeline's internal grader consider to be basically correct). Our pipeline addresses these failure modes through conjecture extraction, wherein candidate lemmas are isolated from generated solutions and independently verified alongside their negations in a fresh environment (context detachment). On IMO-ProofBench Advanced (PB-Adv), our pipeline achieves 67.1 percent performance using Gemini 3.0 Pro with an average cost per question of approximately 31 USD. At the time of evaluation, this represented the state-of-the-art on PB-Adv among both public and unreleased models, and more than doubles the success rate of the next best publicly accessible pipeline, all at a fraction of the cost.

Read & Discuss → View Source →
21.
arXiv (CS.AI) 2026-06-11

Position: Stop Anthropomorphizing Intermediate Tokens as Reasoning/Thinking Traces!

Authors:
Subbarao Kambhampati↗Karthik Valmeekam↗Siddhant Bhambri↗Vardhan Palod↗Lucas Saldyt↗Kaya Stechly↗Soumya Rani Samineni↗Durgesh Kalwar↗Upasana Biswas↗

arXiv:2504.09762v4 Announce Type: replace Abstract: Intermediate token generation (ITG), where a model produces output before the solution, has become a standard method to improve the performance of language models on reasoning tasks. These intermediate tokens have been called \say{reasoning traces} or even \say{thinking traces} – implicitly anthropomorphizing the traces, and implying that these traces resemble steps a human might take when solving a challenging problem, and as such can provide an interpretable window into the operation of the model's thinking process to the end user. In this position paper, we present evidence that this anthropomorphization isn't a harmless metaphor, and instead is quite dangerous – it confuses the nature of these models and how to use them effectively, and leads to questionable research. We call on the community to avoid such anthropomorphization of intermediate tokens.

Read & Discuss → View Source →
22.
arXiv (CS.AI) 2026-06-17

Ternary Mamba: Grouped Quantization-Aware Training of W1.58A16 State Space Models

Authors:
Ramprasath Ganesaraja↗Sahil Dilip Panse↗Swathika N↗

arXiv:2606.18114v1 Announce Type: cross Abstract: State Space Models (SSMs) such as Mamba-2 offer linear-time inference but their memory footprint limits edge deployment. Prior ternary SSM work (Slender-Mamba) trains from scratch on 150B tokens; we show a pretrained checkpoint suffices, reducing the marginal token budget by 1,000x. Using grouped quantization-aware training (QAT) with knowledge distillation from a frozen FP16 teacher, we compress Mamba-2 1.3B to 3.61x (2,687 to 744 MB) and achieve 48.1% zero-shot accuracy (7-task average) in just 102M tokens (4 GPU-hours, single H100) – approaching Bi-Mamba's 48.4% (within +/-0.9pp CI). This QAT-from-pretrained setting reveals zero-ratio collapse, a novel instability caused by learnable quantization scales that does not arise in from-scratch training. We further show that post-hoc correction strategies effective for Transformers fail for SSMs due to error accumulation through the recurrence. These results demonstrate that ternary SSMs do not require expensive from-scratch training: QAT from pretrained checkpoints with KD is a data-efficient alternative.

Read & Discuss → View Source →
23.
arXiv (CS.CV) 2026-06-15

Stream3D: Sequential Multi-View 3D Generation via Evidential Memory

Authors:
Kaichen Zhou↗Zeyang Bai↗Xinhai Chang↗Mengyu Wang↗Paul Liang↗Fangneng Zhan↗

View-conditioned 3D generators such as SAM 3D, TRELLIS, and Hunyuan3D produce high-quality object reconstructions from a single view, but real-world visual observation often arrives as long monocular streams. Naively applying these generators to each streaming frame independently leads to severe temporal inconsistency in the generated results. To address this problem, we propose Stream3D, the first training-free streaming mechanism that turns a frozen view-conditioned 3D generator into a streaming generator with constant cross-chunk memory. Stream3D achieves this by maintaining a compact evidential memory, which selectively caches the most informative historical frames based on a proposed evidence score mechanism. As the stream progresses, the memory dynamically updates to retain a fixed number of informative frames, preventing the memory footprint from growing linearly with sequence length. This also prevents degradation over long sequences and keeps the underlying generator completely unchanged without retraining, architectural modifications, or auxiliary losses. Evaluated on both realistic and synthetic streaming benchmarks, Stream3D outperforms latent-transport baselines, including KV-cache reuse and flow-based feature editing, across both photometric and geometric metrics. More details can be found at: https://stream-3d.github.io/stream3d.github.io/.

Read & Discuss → View Source →
24.
arXiv (CS.AI) 2026-06-15

Distributional Biases in Post-Training: A Markovian Analysis of Reasoning Trajectories

Authors:
Dake Bu↗Wei Huang↗Andi Han↗Atsushi Nitanda↗Bo Xue↗Qingfu Zhang↗Hau-San Wong↗Taiji Suzuki↗

arXiv:2511.07368v3 Announce Type: replace-cross Abstract: Foundation models exhibit broad knowledge but limited task-specific reasoning, motivating post-training strategies such as RL with verifiable rewards (RLVR) and test-time scaling (TTS). While recent work highlights the role of exploration in improving pass@K, empirical evidence points to a paradox: RLVR and ORM/PRM typically reinforce existing paths rather than expanding the reasoning scope, raising the question of why exploration helps if no new patterns emerge. To reconcile this paradox, we adopt the perspective of Kim et al. (2025), viewing easy (e.g., simplifying a fraction) versus hard (e.g., discovering the some symmetry) reasoning steps as low versus high probability Markov transitions. In this tractable model, pretraining corresponds to tree-graph discovering, while post-training corresponds to CoT reweighting. We provably show that, both RLVR and ORM/PRM would favor heavily to several high-probability paths, and thereby forget rare-but-crucial CoTs. Building on this, we further prove that exploration strategies such as rejecting easy instances and KL regularization help preserve rare CoTs. Empirical simulations corroborate our theoretical results.

Read & Discuss → View Source →
25.
arXiv (CS.CL) 2026-06-16

Fast When, Careful Who: Dual-Process Multiparty Turn-Taking with Diffusion Augmentation

Authors:
Rutherford A. Patamia↗Ming Liu↗Wei Luo↗Favour Ekong↗Akan Cosgun↗

Reliable turn-taking is essential for spoken dialogue systems. However, most existing methods are designed for two-speaker interaction and struggle with realistic multiparty audio containing overlap and rapid speaker changes. We study multiparty turn-taking on the VoxConverse dataset and propose an audio-only two-stage pipeline that separates when to trigger a turn boundary from whether the floor is actually transferring. A fast trigger scans the audio and proposes candidate end-of-turn times, while a lightweight verifier runs only at those times to decide \textsc{Hold} or \textsc{Shift} and support next-speaker prediction. We report results in the full multiparty setting and a controlled dyadic top-2 projection for comparability. We also investigate diffusion-based, label-preserving background-audio mixing as a data augmentation strategy. Results show improved shift detection over a baseline, with further improvements from diffusion augmentation.

Read & Discuss → View Source →