arXiv:2608.13669v1 Announce Type: new Abstract: Physics-constrained diffusion for high-contrast, sharp-interface multiphase fields faces three coupled difficulties. At coefficient jumps, expanded pointwise strong-form PDE residuals contain singular gradient terms that can penalize physical interfaces. Under extreme contrast, low-magnitude phases may fall below the diffusion noise floor and be erased, misscaled, or generated with negative coefficients, while a global likelihood scale allows high-magnitude phases to dominate supervision. We therefore propose Multiphase-Diff, which makes three corresponding contributions: (i) a conservative flux residual that avoids differentiating discontinuous coefficients and enforces discrete conservation; (ii) an analytic bijective representation that m…

arXiv:2608.13660v1 Announce Type: new Abstract: Medical image segmentation models are typically trained under the assumption that all data are available simultaneously. However, in clinical practice, datasets often arrive sequentially, requiring models to adapt continuously to evolving data distributions. We study this problem in gynecological image segmentation, where substantial heterogeneity across imaging modalities, anatomical structures, and annotation protocols creates a particularly challenging continual learning setting. Under these large distribution shifts, existing continual learning methods struggle to preserve previously learned knowledge, leading to catastrophic forgetting. To better understand forgetting in this setting, we investigate how different encoder--decoder region…

arXiv:2608.13708v1 Announce Type: new Abstract: Automatically generating textbook-grounded assessment items can reduce science teachers' workload, but existing retrieval-augmented generation (RAG) systems rely on flat retrieval, support only single-question generation, lack safeguards against weak evidence, and are ill-suited to low-resource, board-exam-structured curricula. We address these limitations with TeachMateGPT, a multi-agent system contributing four advances to curriculum-grounded science-assessment authoring. (i) COPE, a hierarchical knowledge base replacing token-window chunking with a multi-resolution index that segments documents along syllabus structure and links them at three granularities via a traversable graph-based lineage, matching evidence to each topic's instructio…

arXiv:2608.13706v1 Announce Type: new Abstract: Existing defenses against hallucination in retrieval-augmented and multi-agent pipelines remain partial: evidence is trusted despite modality disagreement, debate verifies an aggregate report rather than individual claims, and such verification occurs only after drafting, leaving inter-agent errors undetected until the final text. To close this gap, we present CLAIR-Fin, a nine-agent framework that decomposes each question into atomic claims maintained in a typed Financial Claim Ledger. Each claim is resolved through Asymmetric Evidence Authority, which conditions evidence trust on claim type rather than treating all modalities as equally reliable; Chain-of-Custody Verification, which checks grounding at the hand-off between drafting and adv…

arXiv:2608.13698v1 Announce Type: new Abstract: Reinforcement Learning with Verifiable Rewards (RLVR), often optimized with Group Relative Policy Optimization (GRPO), has become a central recipe for improving the reasoning capabilities of pretrained language models but current studies remain heavily English-centric. We conduct a large-scale empirical study of multilingual and non-English GRPO across a wide range of base models, training languages, and different reasoning language rewards. We find that training to reason in the native language often leaves only a small gap to training for English reasoning. We further observe strong crosslingual transfer: training in one language often improves performance in many others. However, specific trends are highly model- and language-dependent. I…

arXiv:2608.13624v1 Announce Type: new Abstract: Large Audio Language Models (LALMs) have seen increasing use for audio understanding tasks such as speech recognition and audio question answering, raising concerns about fairness across demographic subgroups. Fairness evaluation in spoken-input settings is challenging due to confounding factors, including semantic variation in spoken content and speaker-specific characteristics. Ignoring these factors can result in misleading conclusions about model bias. We propose a semantic-aware mixed-effects regression framework for fairness evaluation in LALMs that explicitly accounts for these confounders. Our approach incorporates sentence-level semantic embeddings of reference text as covariates and models speaker identity as a random effect. Notab…

arXiv:2608.13588v1 Announce Type: new Abstract: Multi-hop question answering requires complex reasoning across multiple evidence segments, which often overwhelms retrieval-augmented generation systems with lengthy and noisy contexts, thereby undermining both efficiency and accuracy. While existing prompt compression methods attempt to address this issue, they are typically designed for single-turn queries and fail to capture interdependent reasoning steps. We propose IterCOMP, a unified, training-free prompt compression framework that incorporates multi-hop reasoning within an iterative compression loop. IterCOMP decomposes documents into evidence segments, evaluates question answerability, and generates targeted follow-up questions to iteratively integrate essential evidence, producing a…

arXiv:2608.13580v1 Announce Type: new Abstract: Jais 2 is a family of Arabic-centric large language models developed jointly by MBZUAI, Cerebras, and Inception, designed to advance Arabic-centric language modeling, with strong performance across the Arabic and culturally grounded benchmarks evaluated in this report. The family includes, to our knowledge, the largest open Arabic-centric LLM trained from scratch at 70B parameters, and a competitive 8B-parameter variant among the evaluated open models. A custom Arabic-centric vocabulary enables efficient training and inference. In addition, an optimized architecture and training recipe yield highly compute-efficient training. With a substantially smaller token budget than comparable models, Jais 2 achieves strong Arabic performance on the be…

arXiv:2608.13578v1 Announce Type: new Abstract: Transformer architectures rely on dense self-attention to model long-range dependencies, but this mechanism exhibits quadratic complexity with respect to sequence length. We introduce BCMT (Blockwise Causal Memory Transformer), an architecture for long-context language modeling that decouples local token interactions from global context propagation. Dense causal self-attention is applied independently within local blocks, while each block produces an adaptive summary aggregated through an exponential causal memory. This memory is subsequently injected back into the token representations, enabling efficient propagation of long-range contextual information without relying on explicit global attention. Unlike standard Transformers and recurrent…

arXiv:2608.13571v1 Announce Type: new Abstract: When a language model fails to answer a query on the first attempt, an agentic system retries, consuming additional tokens each time. This retry overhead creates a gap between what a model's per-token price implies and what a full workflow actually costs. We call this gap \emph{token inflation} and define it as the ratio of true workflow cost to single-call cost. Systems like FrugalGPT route based on the latter, which can underestimate real cost by more than $2\times$ on difficult tasks. We address this with InflationAgent, a four-stage router that (1) measures token inflation systematically across model tiers and task types, finding inflation as high as $4.25\times$ for a 7B model on multi-hop question answering; (2) introduces CoT Branchin…

arXiv:2608.13570v1 Announce Type: new Abstract: Latent reasoning has emerged as a powerful alternative to text-based Chain-of-Thought (CoT), offering significant gains in computational efficiency by compressing verbose reasoning into compact embeddings. However, compressing reasoning into the latent space renders the thinking opaque, hindering its interpretability. Current methods present a stark trade-off: they either function as unexplainable ''black boxes'' (e.g., Coconut), where the latent reasoning is not human-readable, or rely on separate post-hoc decoders for explainability (e.g., Heima), introducing architectural overhead and decoupling the explanation from the actual reasoning process. In this work, we present a unified framework for Self-Explainable Latent Reasoning (SELR) that…

arXiv:2608.13568v1 Announce Type: new Abstract: Coding agents spend most of their context budget on retrieval. Lexical retrieval (grep) is universal, instant, and zero-setup, but noisy: it cannot tell a definition from a call from a comment. Semantic retrieval via the Language Server Protocol (LSP) is precise and typed, but needs a running, indexed server and pays a per-symbol round-trip. The claim that semantic retrieval is more token-efficient is, we find, asserted almost everywhere and measured almost nowhere: no public source isolates the LSP-vs-lexical token delta for an agent at equal task-success. This paper formalizes the question with one metric (tokens-to-success), specifies a five-arm ablation isolating semantic retrieval from confounds, maps three pre-stated failure modes onto…

arXiv:2608.13676v1 Announce Type: new Abstract: Objective: Foundation models represent the next advancement in AI for EEG analysis; however current explainable AI techniques provide attribution scores in the time-channel input space, which is mismatched to clinical intuition about EEG. Thus, there is a critical need for a universal method that can extend the interpretability of any foundation model to alternative and physiologically relevant domains without modifying or retraining the underlying model. Methods: EEG-PRISM leverages linear transformations and established backpropagation rules to map time-channel attribution scores into alternative domains. We derive mappings to the frequency domain via an invertible DFT and to the source domain via an approximately invertible EEG generative…

arXiv:2608.13675v1 Announce Type: new Abstract: Between October 2018 and July 2026 AI models progressed from simple systems like BERT to massive agents that solve complex math and write software. The ability to resolve real coding issues improved by nearly six times per year since late 2024. During this time costs dropped sharply with OpenAIs budget model GPT 5 point 6 Luna matching flagship capabilities for just one to six dollars per million tokens beating older versions at a fraction of the price. Top performance is now split across specialized models as Claude Opus 5 leads in frontend coding Claude Fable 5 excels at repository level coding and GPT 5 point 6 Sol dominates terminal tasks. In a grade school math test using the Qwen 2 point 5 model basic methods solved 58 of 100 problems…

arXiv:2608.13668v1 Announce Type: new Abstract: Linear attention keeps a state of fixed size. At long context, many stored items share this state, and interference between them degrades retrieval. Gated DeltaNet-2 (GDN-2), like every delta-rule model before it, derives its erase vector from the key of the current token. However, the interference in its reads is measured through the query, and the erase step cannot reach it. We introduce the Query-derived Erase Direction (QED). QED adds a second erase direction derived from the query and orthogonal to the key. In the fast-weight view, a key-directed delta edit cannot change the key-orthogonal part of a read. It uses the editable part to cancel old-state content measured along the query. It also improves retrieval at every length past the t…

arXiv:2608.13652v1 Announce Type: new Abstract: Generic event-level anomaly detection for collider physics has two recurring problems: anomaly scores are hard to interpret, and they correlate strongly with energy scale and object multiplicity. We present Organized Representation via Contrastive learning for Anomaly detection (ORCA), a two-stage framework that first learns an embedding space via supervised contrastive learning across a diverse set of physics processes, then runs a standard autoencoder in that space to generate event-level anomaly scores. On a simulated dataset consistent with conditions at the High-Luminosity Large Hadron Collider, ORCA delivers significant gains in both breadth and depth of sensitivity to new physics signals with respect to a baseline autoencoder architec…

This arXiv study tests whether uncertainty sampling in active learning fails under label noise because it acquires more corrupted labels or because errors concentrated in difficult regions are especially harmful. Comparing margin-based uncertainty sampling with random sampling on three tabular datasets, it finds that uncertainty sampling is label-efficient, but its apparent robustness depends on dataset, budget, noise structure, and evaluation metric.

L-FNO is a stochastic neural operator that combines an FNO-style covariate path, Lorentzian spectral kernels, and a likelihood-based training objective to model rare, bursty, self-exciting events. Across eight synthetic point-process benchmarks and three real-world datasets, it improves event likelihood, calibration, and rare-event detection over neural operator baselines.

This arXiv study presents a one-year production trace of LLM serving from Chutes, capturing full production behavior across many models and users. The analysis spans aggregate, temporal, model-level, and user-level perspectives, revealing workload evolution and user-model structure hidden behind aggregate views. The full trace will be released with the paper.

A new arXiv study systematically analyzes layer-wise sensitivity of the Qwen3.6-35B-A3B Mixture-of-Experts model using magnitude-based expert masking on the XLCoST code translation benchmark. The authors find that late MoE layers, especially layers 35-39, tolerate aggressive masking far better than early and middle layers, enabling large expert reductions with relatively little quality loss. The results point toward depth-aware compression strategies and practical techniques such as physical weight surgery, activation-based expert scoring, and training-based recovery.

This paper presents RubricForge, which automatically induces human-readable judging rubrics from a small set of ground-truth-labeled agent trajectories. In evaluations with a frozen 7B model on tau-bench and WebShop, it reduces false-pass rates (e.g., 0.115 vs 0.173 on tau-bench) and improves ranking faithfulness relative to a generic G-Eval judge, while keeping verdicts attributable to named criteria. Its aggregate agreement gain is not statistically significant, and absolute-score calibration is slightly worse.

Discussion | Link

OpenAI funds 14 independent projects exploring new AI policy ideas to expand economic opportunity and strengthen societal resilience in the Intelligence Age.

A Level1Techs forum post alleges Google illegally retains customer data in violation of GDPR and announces legal action, with the community unable to disprove the claim.

Microsoft says AI-powered vulnerability hunting is creating a backlog of extra work that is delaying Exchange Server SE Cumulative Update 1, with no release date yet.

Discussion | Link

BlockArena is an AI-generated neon voxel FPS built with Puter AI Builder. It features desktop-only mouse-and-keyboard controls, P2P multiplayer with sign-in, offline bot practice, and classic FPS combat mechanics.

okf is a Go CLI toolkit for the Open Knowledge Format, designed to be driven by AI agents. It outputs JSON, provides trust tiers, provenance, lifecycle, and attested computations, and serves as a vendor-neutral alternative to Google's reference implementation.

We ran 904 DeepSWE rollouts on DeepSeek V4 Pro 0813 and Claude Fable 5. Fable leads pass@1 at 90x the cost; Pro wins pass@4, and a Pro-first cascade hits 82.7%.

Shadow traffic proves a candidate is operationally sound. It can't tell you if users like it better. Run the split at the endpoint instead of in your app code.