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
Authors: Day ×
↻ Shuffle
01.
arXiv (CS.AI) 2026-06-25

Agentic Software Engineering: Foundational Pillars and a Research Roadmap

Authors:
Ahmed E. Hassan↗Hao Li↗Dayi Lin↗Bram Adams↗Tse-Hsun Chen↗Yutaro Kashiwa↗Dong Qiu↗

arXiv:2509.06216v3 Announce Type: replace-cross Abstract: Agentic Software Engineering (SE 3.0) represents a new era where intelligent agents are tasked not with simple code generation, but with achieving complex, goal-oriented SE objectives. To harness these new capabilities while ensuring trustworthiness, we must recognize a fundamental duality within the SE field in the Agentic SE era, comprising two symbiotic modalities: SE for Humans and SE for Agents. This duality demands a radical reimagining of the foundational pillars of SE (actors, processes, tools, and artifacts) which manifest differently across each modality. We propose two purpose-built workbenches to support this vision. The Agent Command Environment (ACE) serves as a command center where humans orchestrate and mentor agent teams, handling outputs such as Merge-Readiness Packs (MRPs) and Consultation Request Packs (CRPs). The Agent Execution Environment (AEE) is a digital workspace where agents perform tasks while invoking human expertise when facing ambiguity or complex trade-offs. This bi-directional partnership, which supports agent-initiated human callbacks and handovers, gives rise to new, structured engineering activities (i.e., processes) that redefine human-AI collaboration, elevating the practice from agentic coding to true agentic software engineering. This paper presents the Structured Agentic Software Engineering (SASE) vision, outlining several of the foundational pillars for the future of SE. The paper culminates in a research roadmap that identifies a few key challenges and opportunities while briefly discussing the resulting impact of this future on SE education. Our goal is not to offer a definitive solution, but to provide a conceptual scaffold with structured vocabulary to catalyze a community-wide dialogue, pushing the SE community to think beyond its classic, human-centric tenets toward a disciplined, scalable, and trustworthy agentic future.

Read & Discuss → View Source →
02.
arXiv (CS.AI) 2026-06-16

Odds Law: The Decomposition Algebra On How Intelligence Organizes Itself to Solve Difficult Problems Reliably

Authors:
Hidayet Aksu↗

arXiv:2606.15712v1 Announce Type: cross Abstract: We ask a structural question: given unreliable elementary problem-solvers, what organizations of them solve hard problems reliably, and what are the limits? We develop a $decomposition~algebra$: elementary solvers are morphisms in a stochastic category, and four combinators (sequential composition, parallel ensembling, verification gating, and recursive reduction) generate the space of compound solvers. We equip this algebra with two homomorphisms, a $reliability$ valuation into the ordered monoid $([0,1],\le)$ and a $cost$ valuation into a commutative semiring, and we derive the composition laws that govern how reliability flows through structure. Our central results are (i) a $verification~odds~law$ (the result that names this report), showing that a verification gate multiplies the odds of correctness by the verifier's likelihood ratio $\Lambda$, so that $k$ conditionally independent gates yield geometric amplification; (ii) a $reliability~amplification~theorem$, giving target reliability $1-\delta$ at $O(\log 1/\delta)$ verification depth whenever $\Lambda>1$; and (iii) a $threshold~dichotomy$: above the critical parameters reliability can be driven arbitrarily close to one at logarithmic cost, while at or below them no amplification is possible. We then show that $self-organization$ is the least fixed point of a monotone improvement operator on the complete lattice of strategies, and that this fixed point equalizes marginal log-odds gain per unit cost. Finally, we prove matching limits: an information ceiling bounds per-gate amplification by a divergence quantity; shared error causes create a strictly positive voting floor, so diversity is $necessary$ for unbounded amplification. Reliability, in short, is neither free nor magical: it is bought with independent information, arranged by composition, and bounded by the verifier.

Read & Discuss → View Source →
03.
arXiv (CS.CL) 2026-06-17

Correct When Paired, Wrong When Split: Decoupling and Editing Modality-Specific Neurons in MLLMs

Authors:
Tingchao Fu↗Wenkai Wang↗Fanxiao Li↗Huadong Zhang↗Jinhong Zhang↗Dayang Li↗Yunyun Dong↗Renyang Liu↗Wei Zhou↗

Although Knowledge Editing provides an efficient mechanism for updating the knowledge of Multimodal Large Language Models (MLLMs), we find that current paradigms still suffer from an important yet remain underexplored issue : editing decoupling failure, where entity-related knowledge can be updated when the model is triggered by multimodal inputs (text–image query pairs), however, it often reverts to outdated pre-edit facts when the paired inputs are split into unimodal ones. Our in-depth empirical analysis reveals that the entity knowledge in MLLMs is not stored as a unified representation, but is instead distributed across disentangled modality-specific pathways. As a result, updates biased toward multimodal queries fail to propagate effectively to unimodal circuits. To bridge this gap, we propose DECODE, which explicitly disentangles and localizes modality-specific neuron groups for targeted knowledge. Extensive experiments demonstrate that DECODE consistently achieves effective knowledge updates under different modality triggers, thereby mitigating editing decoupling failures.

Read & Discuss → View Source →
04.
arXiv (CS.CL) 2026-06-24

Policies Permitting LLM Use for Polishing Peer Reviews Are Currently Not Enforceable

Authors:
Rounak Saha↗Gurusha Juneja↗Dayita Chaudhuri↗Naveeja Sajeevan↗Nihar B Shah↗Danish Pruthi↗

A number of scientific conferences and journals have recently enacted policies that prohibit LLM usage by peer reviewers, except for polishing, paraphrasing, and grammar correction of otherwise human-written reviews. But, are these policies enforceable? To answer this question, we assemble a dataset of peer reviews simulating multiple levels of human-AI collaboration, and evaluate five state-of-the-art detectors, including two commercial systems. Our analysis shows that all detectors misclassify a non-trivial fraction of LLM-polished reviews as AI-generated, thereby risking false accusations of academic misconduct. We further investigate whether peer-review-specific signals, including access to the paper manuscript and the constrained domain of scientific writing, can be leveraged to improve detection. While incorporating such signals yields measurable gains in some settings, we identify limitations in each approach and find that none meets the accuracy standards required for identifying AI use in peer reviews. Importantly, our results suggest that recent public estimates of AI use in peer reviews through the use of AI-text detectors should be interpreted with caution, as current detectors misclassify mixed reviews (collaborative human-AI outputs) as fully AI generated, potentially overstating the extent of policy violations.

Read & Discuss → View Source →
05.
arXiv (CS.LG) 2026-06-16

p-PSO: A Penalized Particle Swarm Optimization Technique for Finding D-Optimal Designs with Mixed Factors in Generalized Linear Models

Authors:
Shrabanti Chowdhury↗Abhyuday Mandal↗

arXiv:2606.15962v1 Announce Type: cross Abstract: Finding D-optimal designs for generalized linear models (GLMs) is challenging due to the dependence of the Fisher information matrix on unknown parameters and the lack of closed-form solutions, particularly when input factors include both discrete and continuous variables. Although classical algorithms and recent metaheuristic approaches have offered partial solutions, there remains a need for robust and computationally efficient methods. In this paper, we propose a penalized Particle Swarm Optimization (PSO) approach, named $p$-PSO. Here we introduce a new, general-purpose penalty formulation for constrained optimization and demonstrate its effectiveness in optimal design problems. The formulation is algorithm-agnostic and applicable to a broad class of black-box optimization methods. Results show that the method is highly efficient, with its primary contribution being a penalty formulation that enables the direct use of an off-the-shelf PSO algorithm and extends naturally to more general constrained optimization tasks.

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

Emergent retokenization symmetry in large language models: phenomenology and applications

Authors:
Kanishk Jain↗Matthew Day↗Tankut Can↗

Tokenization introduces representational redundancy: under a fixed token vocabulary, every byte string admits many valid token encodings, or segmentations, that decode to the same surface string. However, given a prompt, most language model tokenizers break this representational symmetry by returning a canonical segmentation. Training only on canonical segmentations should influence inference behavior, and there is little reason to expect models to respect segmentation symmetry on downstream tasks. We find that this symmetry partially emerges during training. Here, we probe this emergent symmetry through experiments testing token compositional understanding, representation diversity, and task focused benchmark performance. We primarily use retokenization – replacing a prompt's canonical tokenization with an alternative segmentation while preserving its bytes exactly. Relative to other prompt perturbations, retokenization is unusually clean because it isolates segmentation effects without changing syntax, semantics or surface form. We use retokenization to study sensitivity and robustness to semantically identical input representations across pretraining and post-training. Moreover, this partial retokenization symmetry suggests a distinct inference-time sampling axis. While temperature sampling generates diverse outputs from the model using its next-token probability distribution, retokenization generates diversity from the model's internal computations through semantically equivalent input representations. We find that while this retokenization sampling strategy can hurt performance on easy problems, it can also recover solutions that conventional sampling does not find. Overall, our work presents retokenization as a simple yet powerful probe of large language models, shedding light on compositional understanding and prompt sensitivity, and offering a novel sampling strategy.

Read & Discuss → View Source →
07.
bioRxiv (Bioinfo) 2026-06-11

STITCH links cellular morphology and gene expression in spatial transcriptomics

Authors:
Kumar↗Shi↗Vallius↗Day↗C.-P↗Absil↗P.- A↗Srivastava↗Hannenhalli↗Gopalan↗

In situ spatial (ISS) sequencing can uncover co-variation between cellular morphology and gene expression in vivo. However, a principled and interpretable mathematical representation of morphology has not yet been applied in this context. In particular, current deep learning-based representations of cell images confound a cell's shape with its size. We present an interpretable representation of cellular boundary contours, based on tangent principal component analysis (TPCA) in a Kendall shape manifold, that captures size-independent contour shape features. This approach successfully recovers shape-perturbing genes in an RNAi screen than a previous metric geometry-based approach. We build on TPCA to develop STITCH (Shape-TranscriptomIc Correlation and Harmonization), an approach to reveal covariation between cell morphology with gene expression in ISS datasets. In a Xenium dataset, STITCH outperforms a deep learning-based approach in both recovering the layered organization of keratinocytes and a spatial gradient in nuclear eccentricity. Across samples in a melanoma CosMx dataset, STITCH reproducibly associates elongated and triangular fibroblasts with proximity to malignant cells and myofibroblast-like transcriptional program. Finally, STITCH independently recovers a known link between mesenchymal-like malignant cell states and increased cell area in two melanoma cohorts. STITCH can thus yield interpretable morphology-transcriptome relationships across cell types, patients, and spatial transcriptomics platforms.

Read & Discuss → View Source →
08.
arXiv (CS.CL) 2026-06-16

Nemotron 3 Ultra: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoning

Authors:
NVIDIA↗Aaron Blakeman↗Aaron Thomas↗Aastha Jhunjhunwala↗Abhibha Gupta↗Abhinav Khattar↗Adam Rajfer↗Adi Renduchintala↗Adil Asif↗Aditya Vavre↗Adriana Flores Miranda↗Ahmad Bilal↗…

We introduce Nemotron 3 Ultra, a 550 billion total and 55 billion active parameter Mixture-of-Experts Hybrid Mamba-Attention language model. We pre-trained Nemotron 3 Ultra on 20 trillion text tokens, then extended the context length to 1M tokens, and post-trained using Supervised Fine Tuning (SFT), Reinforcement Learning (RL), and Multi-teacher On-Policy Distillation (MOPD). Nemotron 3 Ultra is our most capable model yet, employing multiple key technologies - LatentMoE, Multi Token Prediction (MTP), NVFP4 pre-training, multi-environment RLVR, MOPD, and reasoning budget control. Nemotron 3 Ultra achieves up to ~6x higher inference throughput as compared to state-of-the-art publicly available LLMs while attaining on-par accuracy. The state-of-the-art accuracy, high inference throughput, and 1M token context length make Nemotron 3 Ultra ideal for long-running autonomous agentic tasks. We open-source the base, post-trained, and quantized checkpoints, along with the training data and recipe on HuggingFace.

Read & Discuss → View Source →
09.
arXiv (CS.CL) 2026-06-11

Verifiable Environments Are LEGO Bricks: Recursive Composition for Reasoning Generalization

Authors:
Hao Xiang↗Qiaoyu Tang↗Le Yu↗Yaojie Lu↗Xianpei Han↗Ben He↗Le Sun↗Bowen Yu↗Peng Wang↗Hongyu Lin↗Dayiheng Liu↗

Reinforcement Learning (RL) with verifiable environments has emerged as a powerful approach for enhancing the reasoning capabilities of Large Language Models (LLMs). While prior research demonstrates that scaling environment quantity improves RL performance, existing manual or individual construction methods suffer from linear scaling limits, thereby hindering scalable reasoning generalization. This paper introduces RACES (Recursive Automated Composition for Environment Scaling), a framework that conceptualizes verifiable environments as composable building blocks that can be recursively assembled. The key insight is that when the codomain (output type) of one environment matches the domain (input type) of another, they can be automatically fused into a new verifiable environment, enabling recursive composition. RACES is implemented with 300 individual environments and defines a set of composition operators (\textsc{SEQUENTIAL}, \textsc{PARALLEL}, \textsc{SORT}, and \textsc{SELECT}) that induce diverse reasoning patterns. Extensive experiments show that RL training on these composite environments consistently enhances reasoning generalization. Specifically, RACES improves DeepSeek-R1-Distill-Qwen-14B by an average of 3.1 points (from 48.2 to 51.3) and boosts Qwen3-14B performance from 58.8 to 61.1 on six benchmarks, which are unseen during the construction of training environments. Moreover, RACES achieves performance comparable to training on 300 individual environments using only 50 base environments, demonstrating significant efficiency in environment utilization.

Read & Discuss → View Source →
10.
arXiv (CS.AI) 2026-06-11

Ambient Diffusion Policy: Imitation Learning from Suboptimal Data in Robotics

Authors:
Adam Wei↗Nicholas Pfaff↗Thomas Cohn↗Arif Kerem Day{\i}↗Constantinos Daskalakis↗Giannis Daras↗Russ Tedrake↗

arXiv:2606.12365v1 Announce Type: cross Abstract: We propose Ambient Diffusion Policy, a simple and principled method for imitation learning from suboptimal data in robotics. High-quality, task-specific robot data is expensive and time-consuming to collect, while suboptimal datasets with lower-quality or out-of-distribution demonstrations are abundant. Existing methods that co-train on both data sources in robotics often fail to separate the meaningful and the harmful features in the suboptimal samples. In contrast, our method extracts only the useful features by introducing a new axis to co-training in robotics: noise-dependent data usage. Ambient Diffusion Policy restricts the contribution of suboptimal data during training to only the high and low diffusion times. To rigorously justify our approach, we first observe that robot action data exhibits a spectral power law. This induces two important properties on the optimal Diffusion Policy that we exploit: a global-to-local hierarchy and locality. We theoretically formalize this discussion using a simplified model. Our experiments validate Ambient Diffusion Policy on four types of suboptimal action data (noisy trajectories, sim-to-real gap, task mismatch, and large-scale data mixtures) across six tasks. The results show that it effectively learns from arbitrary sources of suboptimal data. Notably, it outperforms existing co-training baselines by up to 33% when scaled to Open X-Embodiment - a large dataset with heterogeneous data quality and unstructured distribution shifts. Overall, Ambient Diffusion Policy increases the utility of suboptimal demonstrations and expands the set of usable data sources in robotics.

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

DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence

Authors:
DeepSeek-AI↗Anyi Xu↗Bangcai Lin↗Bing Xue↗Bingxuan Wang↗Bingzheng Xu↗Bochao Wu↗Bowei Zhang↗Chaofan Lin↗Chen Dong↗Chenchen Ling↗Chengda Lu↗…

We present a preview version of DeepSeek-V4 series, including two strong Mixture-of-Experts (MoE) language models – DeepSeek-V4-Pro with 1.6T parameters (49B activated) and DeepSeek-V4-Flash with 284B parameters (13B activated) – both supporting a context length of one million tokens. DeepSeek-V4 series incorporate several key upgrades in architecture and optimization: (1) a hybrid attention architecture that combines Compressed Sparse Attention (CSA) and Heavily Compressed Attention (HCA) to improve long-context efficiency; (2) Manifold-Constrained Hyper-Connections (mHC) that enhance conventional residual connections; (3) and the Muon optimizer for faster convergence and greater training stability. We pre-train both models on more than 32T diverse and high-quality tokens, followed by a comprehensive post-training pipeline that unlocks and further enhances their capabilities. DeepSeek-V4-Pro-Max, the maximum reasoning effort mode of DeepSeek-V4-Pro, redefines the state-of-the-art for open models, outperforming its predecessors in core tasks. Meanwhile, DeepSeek-V4 series are highly efficient in long-context scenarios. In the one-million-token context setting, DeepSeek-V4-Pro requires only 27% of single-token inference FLOPs and 10% of KV cache compared with DeepSeek-V3.2. This enables us to routinely support one-million-token contexts, thereby making long-horizon tasks and further test-time scaling more feasible. The model checkpoints are available at https://huggingface.co/collections/deepseek-ai/deepseek-v4.

Read & Discuss → View Source →
12.
medRxiv (Medicine) 2026-06-11

Two modes of aversive control in suicidality: joint computational modelling exposes regime-specific clinical signatures invisible to symptom-based stratification

Authors:
Laessing↗Karvelis↗Rashid-Cocker↗A. S↗Ruocco↗A. C↗Koudys↗J. W↗Kennedy↗J. L↗Zai↗C. C↗…

Suicidal thoughts and behaviours (STBs) are heterogeneous in their proximal dynamics, planning, and stress-sensitivity, yet most subtyping efforts remain symptom-driven and rarely validated across independent datasets. Computational mixture modelling offers a principled alternative: by fitting explicit models of learning and action selection and partitioning individuals by their latent parameter profiles, it can identify mechanistically distinct control strategies invisible to cross-sectional symptom measurement. We applied this approach to aversive Go/NoGo performance, jointly clustering two independently collected STB-enriched samples (N = 50 and N = 184) using tasks with the same structure but different duration, reversal timing, and clinical instrumentation. Two recurrent behavioural regimes emerged: a fast/adaptive regime characterised by rapid policy updating and elevated feedback reactivity, and a slow/perseverative regime characterised by slow updating, high choice determinism, and a pronounced cost following contingency reversal. These regimes were stable across initialisations, recovered more parsimoniously in joint than independent solutions, and were largely orthogonal to symptom-based stratification. Critically, stratification by regime exposed clinical-computational coupling structures substantially attenuated in pooled analyses. Pooled, population-level associations were modest and anchored by a broad affective burden axis. Within the slow/perseverative regime, coupling reorganised around learning dynamics and internalizing burden (depression, hopelessness, and active suicidal ideation) with markedly larger effect sizes. Within the fast/adaptive regime, a dissociation between anxious-compulsive and antisocial-disinhibitory profiles emerged along the same computational axis, invisible at the population level. These findings support a view of suicidality heterogeneity in which clinically similar individuals differ in the control strategies they recruit under aversive uncertainty - variation that symptom measurement alone cannot capture.

Read & Discuss → View Source →
13.
arXiv (CS.AI) 2026-06-25

Lightweight PCGAE-Net: Parallel CrossGate Attention and Bottleneck AutoEncoder for Efficient 5G Channel Prediction

Authors:
Uma Kishore Godavarti↗K. Giridhar↗Vanani Prince Dharmendrabhai↗Anchit Panday↗Madhan Raj Kanagarathinam↗

arXiv:2606.25401v1 Announce Type: cross Abstract: Accurate channel state information (CSI) prediction is essential for proactive beamforming and resource management in 5G massive MIMO systems, yet the deployment of high-accuracy transformer-based predictors on base-station hardware remains challenging because the most capable models carry upwards of 30\,M parameters. This paper introduces Lightweight PCGAE-Net, which addresses the efficiency problem not by post-hoc compression but by correcting two architectural flaws in the current state of the art. The first is a sequential attention ordering bias: in CS3T-UNet, group-wise temporal attention (GTA) always operates on features that have already been transformed by cross-shaped spatial attention (CSA), distorting what temporal information GTA can capture. We remove this dependency by routing both attention modules to the same layer-normalized input and combining their independent outputs through a learned per-channel sigmoid CrossGate. The second flaw is an uncompressed bottleneck: applying full self-attention at the deepest encoder stage, where channel depth reaches $4C$, is quadratically expensive and carries redundant features. A Bottleneck AutoEncoder (BAE) with $1\times1$ convolutions halves this depth and uses an auxiliary reconstruction loss to prevent information collapse. Wrapping these components inside a shallower encoder-decoder with frequency-domain dimensionality reduction ($N_f\!=\!32$, $C\!=\!48$) produces a model with just 8.54\,M parameters – 58\% fewer than the CS3T-UNet baseline – that outperforms it by up to 3.26\,dB at 5\,km/h and 6.0\,dB at 9\,km/h in single-step prediction on QuaDriGa dataset.

Read & Discuss → View Source →
14.
arXiv (CS.CL) 2026-06-24

Same Lesson, Different Story: Cross-Lingual Reconstruction of Cultural Narratives in Large Language Models

Authors:
Jory Alshaalan↗Haya Albaker↗Abeer Aldayel↗Aljawharah Alabdullatif↗Rehab Alahmadi↗

The evaluation of cultural grounding context becomes complex when multiple cultures convey the same moral lesson. This challenge is particularly relevant to large language models (LLMs), which produce narratives across a wide range of languages and cultural contexts. However, it remains uncertain whether these models preserve culturally grounded meaning when equivalent moral lessons are conveyed through distinct cultural forms. This study introduces a multilingual evaluation narrative framework that integrates a cross-linguistic collection of 414 proverbs spanning 15 languages and uses four LLMs to generate 13k narratives. By employing semantically equivalent proverbs as culturally grounded prompts, the analysis assesses whether models preserve meaning across languages, how cross-lingual conditioning influences narrative realization, and whether different model families converge on similar interpretations. Results indicate that cross-lingual prompting largely preserves proverb-level semantic meaning while systematically redistributing agency, social positioning, and narrative structure. Additionally, strong inter-model convergence is observed in both monolingual and cross-lingual settings, suggesting that multilingual LLMs rely on shared semantic abstractions despite architectural and linguistic differences. These findings shed light on the need for more comprehensive evaluations of cultural grounding. Relying exclusively on semantic similarity in multilingual narrative assessments may overestimate cultural preservation by neglecting culturally meaningful variations in narrative expression.

Read & Discuss → View Source →
15.
arXiv (CS.AI) 2026-06-16

Artificial Intelligence Index Report 2026

Authors:
Sha Sajadieh↗Loredana Fattorini↗Raymond Perrault↗Yolanda Gil↗Vanessa Parli↗Lapo Santarlasci↗Juan Pava↗Nestor Maslej↗Russ Altman↗Erik Brynjolfsson↗Carla Brodley↗Jack Clark↗…

arXiv:2606.15708v1 Announce Type: new Abstract: Welcome to the ninth edition of the AI Index report. As AI continues to advance rapidly, the question becomes whether the systems built around it can keep up. Governance frameworks, evaluation methods, education systems, and the data infrastructure needed to track AI's impact are struggling to match the pace of the technology itself. That gap between what AI can do and how prepared we are to manage it runs through every chapter of this year's report. New in this edition, the report tracks how AI is being tested more ambitiously across reasoning, safety, and real-world task execution, and why those measurements are increasingly difficult to rely on. It also features new estimates of generative AI's economic value alongside emerging evidence of its labor market effects, an analytical framework on AI sovereignty, and a science chapter developed in collaboration with Schmidt Sciences. For the first time, the report features standalone chapters on AI in science and AI in medicine, reflecting AI's growing impact across these two domains.

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

daVinci-kernel: Co-Evolving Skill Selection, Summarization, and Utilization via RL for GPU Kernel Optimization

Authors:
Dayuan Fu↗Mohan Jiang↗Tongyu Wang↗Dian Yang↗Jiarui Hu↗Liming Liu↗Jinlong Hou↗Pengfei Li↗

GPU kernel optimization represents a paradigm where functional correctness is assumed and execution efficiency is the objective. We present daVinci-kernel, a reinforcement learning framework that couples skill discovery with skill exploitation through a dynamically evolving skill library. daVinci-kernel jointly trains three agents sharing one LLM backbone: a Skill Selection Agent that retrieves relevant techniques via BM25 and LLM reranking, a Policy Agent that generates multi-turn CUDA/Triton kernels conditioned on selected skills, and a Skill Summary Agent that distills successful rollouts into reusable skills. Candidate skills are added only after execution-based verification confirms reproducible speedups. All three agents share a single LLM backbone, are initialized via a structured SFT cold start on diversity-filtered data, and are then jointly optimized end-to-end with multi-turn REINFORCE and per-agent advantage estimation. On KernelBench, daVinci-kernel-14B achieves 37.2%, 70.6%, and 32.2% on Level 1, Level 2, and Level 3 under the Fast$_1$ threshold, outperforming the strongest prior RL-trained model, Dr.Kernel-14B.

Read & Discuss → View Source →
17.
arXiv (CS.LG) 2026-06-16

Prediction of Runtime Parameters of Parallel Chemistry Applications via Active and Generative Learning

Authors:
Tanzila Tabassum↗Omer Subasi↗Ajay Panyala↗Epiya Ebiapia↗Gerald Baumgartner↗Erdal Mutlu↗P Sadayappan↗Karol Kowalski↗

arXiv:2606.16226v1 Announce Type: new Abstract: In this work, we develop two main Machine Learning based approaches to predict the runtime parameters of highly scalable parallel chemistry computations.These approaches employ active and generative learning together with the empirically determined gradient boosted regression tree models chosen among a rich suite of machine learning models. When evaluated on Coupled-Cluster with Singles and Doubles computations, our models achieve a mean absolute error percentage (MAPE) as low as 0.023 and a coefficient of determination as high as 99.9%. Furthermore, when combined with active learning to mitigate the lack of large amounts of training data, our models score a MAPE about 0.2 with 20-25% of the original dataset.

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

Physical Atari: A Robust and Accessible Platform for Real-time Reinforcement Learning on Robots

Authors:
Khurram Javed↗Joseph Modayil↗Gloria Kennickell↗Richard S. Sutton↗John Carmack↗

arXiv:2606.19357v1 Announce Type: cross Abstract: We built a robot called the Robotroller that actuates an Atari CX40+ controller and a device called the Atari Devbox that renders the game frame and the reward signal from the Arcade Learning Environment on a screen. The Robotroller and the Atari Devbox, together with an off-the-shelf camera and a desktop computer, constitute a system that can be used to study reinforcement learning algorithms in the physical world. We call the full system Physical Atari. In this paper, we detail the key decisions that make Physical Atari a robust and accessible platform. To make the system robust, we designed the Robotroller so that all movement is done through bearings, which reduces wear. Additionally, we wrote software that monitors the state of the servos at a high frequency and intervenes to limit stress. To make the system accessible, we used affordable off-the-shelf components and parts that can be manufactured using consumer 3D printers. Physical Atari can be built for under $1,000 and has been used for weeks of non-stop reinforcement learning experiments without any mechanical failures. We used it to validate that reinforcement learning algorithms can learn directly on robots and show that even small distribution shifts between learning and deployment can significantly degrade the performance of policies. Our results underscore the importance of on-device adaptation for strong performance on robots.

Read & Discuss → View Source →
19.
arXiv (CS.AI) 2026-06-24

Maestro Order: A Model-Agnostic Orchestration Harness

Authors:
Hidayet Aksu↗

arXiv:2606.23983v1 Announce Type: cross Abstract: A single forward pass of a capable model is a fast, fluent, and unreliable problem-solver: it is right often enough to be useful and wrong often enough to be dangerous; in language models, such confident errors are known as hallucinations. We present Maestro Order, a model-agnostic orchestration harness that turns unreliable solvers into reliable problem-solving systems by composing them according to four structural primitives (decompose, ensemble, verify, and recurse) and a budget-aware controller that decides where to spend compute. The harness treats any model as a black-box base solver behind a uniform interface, layers a verifier ensemble whose discrimination is measured online, and allocates verification and voting to the stages with the highest marginal reliability per unit cost. We give the architecture, the message and state schema, the controller algorithm, and the engineering that makes it deterministic, observable, and fault-tolerant. We then specify an evaluation methodology (reliability at fixed cost, coverage, calibration, and ablations) and report results from a faithful Monte Carlo simulation of the harness over a parameterized solver/verifier model. The simulation reproduces the predicted laws quantitatively: verification amplifies reliability geometrically (e.g. $0.55\to0.98$ with two gates, $\to0.999$ with four), voting helps only above chance and is limited by shared errors, and a budget-aware controller reaches a target reliability at a small fraction of the cost of voting alone by selecting the cheapest mechanism for each regime. We close with failure modes (verifier gaming, correlated errors, and decomposition error compounding) and concrete guidance: build robust checkers, diversify solvers, and let the controller put compute where the information is.

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

Training and Evaluating Diffusion Policies with Long Context Lengths

Authors:
Abhinav Agarwal↗Adam Wei↗Taylan Kargin↗Michael Zeng↗Cole Becker↗Arif Kerem Dayi↗Pablo Parrilo↗Asuman Ozdaglar↗Russ Tedrake↗

arXiv:2606.16447v1 Announce Type: cross Abstract: Imitation learning has enabled highly-dexterous robotic manipulation from RGB observations. Policies trained with these methods, however, typically condition robot actions on only a short history of observations. These policies cannot solve tasks that require memory and can get stuck repeatedly executing the same failing motions. In this work, we first benchmark policy performance as context length is incrementally increased from short to long, across a spectrum of tasks with varying local stability and memory requirements, and in multiple data regimes. To our knowledge, this is the first study to investigate context length in imitation learning at this level of detail. Our results challenge prior claims: naively scaling context length is not as brittle as advertised in literature. With an appropriate conditioning method and denoising backbone (UNet+Cross-Attention), single-task policies achieve high success rates on many tasks in the usual data regime even with naive scaling. Next, we propose a training algorithm to jointly train policies at multiple context lengths, further reducing the sample complexity of long-context learning. Finally, we apply our findings to re-evaluate some previously proposed solutions to long-context imitation learning.

Read & Discuss → View Source →
21.
arXiv (CS.CV) 2026-06-17

Qwen-RobotManip Technical Report: Alignment Unlocks Scale for Robotic Manipulation Foundation Models

Authors:
Haoqi Yuan↗Zhixuan Liang↗Anzhe Chen↗Ye Wang↗Haoyang Li↗Pei Lin↗Yiyang Huang↗Zixing Lei↗Tong Zhang↗Jiazhao Zhang↗Jie Zhang↗Jingyang Fan↗…

Foundation models in language and multimodality achieve strong generalization by aligning heterogeneous data under a unified formulation and training at scale. In this report, we investigate whether this scaling recipe can be applied to robotic manipulation to achieve genuine generalization. This is challenging because, unlike text, manipulation data is heterogeneous by nature, expensive to collect, and narrow in diversity, making alignment and scale simultaneously difficult. We present Qwen-RobotManip, a generalizable Vision-Language-Action foundation model built on Qwen-VL. Qwen-RobotManip introduces a unified alignment framework across the representation, motion, and behavioral dimensions of manipulation, making large-scale multi-source training coherent rather than conflicting. This alignment capability in turn enables Qwen-RobotManip to absorb manipulation data at a scale that prior training regimes could not sustain. A human-to-robot synthesis pipeline converts egocentric hand demonstrations into robot trajectories across 15 platforms, and a rigorous curation pipeline harmonizes heterogeneous datasets. Using only open-source datasets and human videos without proprietary data collection, Qwen-RobotManip constructs a ~38,100-hour pretraining corpus and exhibits emergent generalization capabilities, including zero-shot instruction following, robustness to perturbations, reactive error recovery, and cross-embodiment transfer. We find that standard benchmarks fail to capture pretraining quality and instead adopt OOD settings including RoboCasa365, LIBERO-Plus, EBench, RoboTwin-Clean2Rand, RoboTwin-IF, and RoboTwin-XE. Qwen-RobotManip substantially outperforms prior state-of-the-art models, including $\pi$0.5, across all OOD settings, ranks 1st in RoboChallenge with a 20% relative improvement, and is validated on real-robot platforms including AgileX ALOHA, Franka, UR, and ARX.

Read & Discuss → View Source →
22.
arXiv (CS.CL) 2026-06-11

Breaking Entropy Bounds: Accelerating RL Training via MTP with Rejection Sampling

Authors:
Yucheng Li↗Huiqiang Jiang↗Yang Xu↗Jianxin Yang↗Yi Zhang↗Yizhong Cao↗Yuhao Shen↗Fan Zhou↗Rui Men↗Jianwei Zhang↗An Yang↗Bowen Yu↗…

Reinforcement learning (RL) has become a key component in modern large language models, yet the rollout stage remains the key bottleneck in RL training pipelines. Although Multi-Token Prediction (MTP) offers a natural solution to accelerate rollouts through speculative decoding, many studies have observed that MTP acceptance rates degrade significantly during RL training, leading to limited speedup performance. To address this bottleneck, we present Bebop, a systematic study of MTP in LLM post-training, and offer practical recipes to integrate MTP into large-scale RL pipelines. First, we reveal that the MTP acceptance rate is fundamentally bounded by the fluctuation of model entropy, which demonstrates a clear negative linear relationship with the rise of entropy in the RL stage. Second, we show that probabilistic rejection sampling largely alleviates the disturbance introduced by entropy in RL compared to greedy draft sampling. We further identify that the conventional MTP training objectives (cross-entropy or KL) are suboptimal in such settings, and therefore we propose a novel end-to-end TV loss that directly optimizes multi-step rejection sampling acceptance rate, yielding ~10% acceptance rate improvements, achieving up to 95% acceptance rates and up to 25% extra inference throughput gains across mathematical reasoning, code generation, and agentic tasks. Third, we test various online MTP training strategies during RL and show that pre-RL MTP training with e2e TV loss and rejection sampling achieves a consistent acceptance rate and speedup throughout the entire RL, eliminating the need for costly online MTP updating. We provide extensive experiments and analysis that validate our findings. Experimental results show our method achieves up to 1.8x end-to-end acceleration in async RL training of Qwen3.5, Qwen3.6, and Qwen3.7 models.

Read & Discuss → View Source →
23.
arXiv (CS.CV) 2026-06-17

Fluently Lying: Adversarial Robustness Can Be Substrate-Dependent

Authors:
Daye Kang↗Hyeongboo Baek↗

The primary tools used to monitor and defend object detectors under adversarial attack assume that when accuracy degrades, detection count drops in tandem. This coupling was assumed, not measured. We report a counterexample observed on a single model: under standard PGD, EMS-YOLO, a spiking neural network (SNN) object detector, retains more than 70% of its detections while mAP collapses from 0.528 to 0.042. We term this count-preserving accuracy collapse Quality Corruption (QC), to distinguish it from the suppression that dominates untargeted evaluation. Across four SNN architectures and two threat models (l-infinity and l-2), QC appears only in one of the four detectors tested (EMS-YOLO). On this model, all five standard defense components fail to detect or mitigate QC, suggesting the defense ecosystem may rely on a shared assumption calibrated on a single substrate. These results provide, to our knowledge, the first evidence that adversarial failure modes can be substrate-dependent.

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

LoMime: Query-Efficient Membership Inference using Model Extraction in Label-Only Settings

Authors:
Abdullah Caglar Oksuz↗Anisa Halimi↗Erman Ayday↗

arXiv:2602.18934v2 Announce Type: replace Abstract: Membership inference attacks (MIAs) threaten the privacy of machine learning models by revealing whether a specific data point was used during training. Existing MIAs often rely on impractical assumptions, such as access to public datasets, shadow models, confidence scores, or knowledge of the training data distribution, making them vulnerable to defenses like confidence masking and adversarial regularization. Label-only MIAs, even under strict constraints, suffer from high query requirements per sample. We propose a cost-effective label-only MIA framework based on transferability and model extraction. By querying the target model $M$ using active sampling, perturbation-based selection, and synthetic data, we extract a functionally similar surrogate model $S$ on which membership inference is performed. This shifts the query overhead to a one-time extraction phase, eliminating repeated queries to $M$. Our method matches the performance of state-of-the-art label-only MIAs while significantly reducing query costs and operating under strict black-box constraints. On benchmark tabular datasets, we show that a query budget equivalent to testing the membership of approximately $1%$ of the training samples is sufficient to extract $S$ and achieve membership inference accuracy within $\pm 1%$ of that obtained when attacking $M$ directly. We also evaluate the effectiveness of standard defenses, including DP-SGD and regularization, proposed for label-only MIAs against our attack. Finally, we present preliminary results extending our framework to deep neural networks trained on image datasets, demonstrating promising transferability and membership inference performance under label-only access while highlighting directions for further optimization.

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

Auditing Machine Unlearning: A Systematic Research on Whether Models Truly Forget

Authors:
Dayong Ye↗Tianqing Zhu↗Ruiding Huang↗Xinbo Fu↗Jiayang Li↗Bo Liu↗Huan Huo↗Wanlei Zhou↗

arXiv:2606.16110v1 Announce Type: new Abstract: Machine unlearning has been extensively studied in response to growing privacy concerns and regulatory requirements. However, auditing whether unlearning algorithms have truly erased the influence of specific data remains an open challenge. The lack of reliable and practical auditing mechanisms can lead to critical privacy risks, such as residual information leakage. This paper initiates a systematic investigation into whether existing unlearning algorithms can truly forget the designated data. We propose the first practical and general-purpose auditing framework for machine unlearning, inspired by the concept of proof of ignorance. Our framework addresses the key practicality limitations of existing methods by eliminating the need for retraining-from-scratch baselines, avoiding the training of large numbers of shadow models, and requiring no intrusive intervention in the original training process. To evaluate the effectiveness of our framework, we first conduct validation experiments to verify its soundness and completeness. We then perform comprehensive experiments across six datasets and ten representative unlearning methods. The results demonstrate that our framework reliably distinguishes between successful and failed unlearning. In particular, we observe that retraining-based and fine-tuning-based methods can achieve effective unlearning, even when the target data remain in the original dataset. In contrast, de-optimization-based methods fail to achieve true unlearning and instead degrade the model's performance. Fisher/Hessian-based methods also fail to unlearn requested data, even formal certification is provided. Moreover, we show that our framework is robust against fake unlearning attempts and generalizes well to large language models.

Read & Discuss → View Source →