×

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.

Authors: Mo Wang ×
Shuffle
01.
arXiv (quant-ph) 2026-06-16

Atom–photon Entanglement with a Single Trapped Cesium Atom

arXiv:2605.28968v2 Announce Type: replace Abstract: We demonstrate atom–photon entanglement using a single cesium atom trapped in an optical tweezer. Entanglement is generated by resonant excitation and subsequent spontaneous decay, which entangles the atomic Zeeman state with photon polarization. The photon is collected with a high numerical aperture objective (NA = 0.55) and coupled into a single-mode fiber, enabling atom photon measurements and measurement of the Bell-state fidelity. We obtain raw entanglement fidelity of ${\mathcal F} = 0.942(16)$ and inferred fidelity of ${\mathcal F}_inf = 0.962(26)$ after correcting independently characterized atom measurement errors. Compared with related free-space experiments using $^{87}$Rb, the multilevel structure of the relevant excited state in $^{133}$Cs requires the use of a single short excitation pulse in each entanglement attempt in order to suppress unwanted re-excitation. These results establish a free-space Cs atom–photon interface and provide a step toward dual-species Rb–Cs quantum networking.

02.
medRxiv (Medicine) 2026-06-12

Genome-wide association and multi-omics functional screens reveal the genetic architecture of foveal development

Foveal hypoplasia causes visual impairment across congenital eye disorders, yet the genetic programmes governing foveal development remain poorly characterised and no tractable model exists for foveal disease. In the first genome-wide association study of foveal hypoplasia, we identified 42 sentinel variants mapping to 54 effector genes supported by >= 2 criteria from a variant-to-gene framework incorporating developmental multi-omics. Disruption of six effector genes using mutant lines and CRISPR knockouts in the zebrafish high acuity zone recapitulates structural, functional, and ultrastructural hallmarks of foveal hypoplasia, establishing the first vertebrate disease model. Integration with human foetal single-cell and spatial transcriptomics reveals two temporal waves of effector gene expression and identifies Muller glia as critical mediators of foveal patterning. Phenome-wide analyses reveal foveal variants are pleiotropic with refractive, lenticular, and metabolic traits, connecting foveal development to anterior segment and systemic disease biology. These findings should inform mechanistic studies of macular disease.

03.
arXiv (CS.AI) 2026-06-17

Position: Modular Memory is the Key to Continual Learning Agents

arXiv:2603.01761v2 Announce Type: replace-cross Abstract: Foundation models have transformed machine learning through large-scale pretraining and increased test-time compute. Despite surpassing human performance in several domains, these models remain fundamentally limited in continuous operation, experience accumulation, and personalization, capabilities that are central to adaptive intelligence. While continual learning research has long targeted these goals, its historical focus on in-weight learning (IWL), i.e., updating a single model's parameters to absorb new knowledge, has rendered catastrophic forgetting a persistent challenge. Our position is that combining the strengths of In-Weight Learning (IWL) and the newly emerged capabilities of In-Context Learning (ICL) through the design of modular memory is the missing piece for continual adaptation at scale. We outline a conceptual framework for modular memory-centric architectures that leverage ICL for rapid adaptation and knowledge accumulation, and IWL for stable updates to model capabilities, charting a practical roadmap toward continually learning agents.

04.
arXiv (CS.LG) 2026-06-19

EFIQA: Explainable Fundus Image Quality Assessment via Anatomical Priors

arXiv:2606.20108v1 Announce Type: cross Abstract: Image quality control is vital for a wide range of downstream applications. Deep learning-based image quality assessment methods typically train classifiers on dataset-specific quality labels, inheriting two limitations: (1) generalization is tied to the labeling criteria of the training set and (2) these methods cannot provide spatial feedback on where the quality is degraded, lacking explainability. In this work, we propose EFIQA, a framework that requires no quality-related supervision and produces spatial quality maps by design. Rather than learning ``what is degradation" from human-annotated labels, EFIQA learns ``what should be there" by leveraging anatomical priors. For fundus photography, we instantiate this as a two-stage approach, by first training an unsupervised anomaly detector via masked anatomical inpainting to identify regions of missing vasculature, and then distilling this prior knowledge into a shallow adapter mapping features of a frozen foundation model to precise quality maps. External-dataset evaluation demonstrates that this label-free approach with minimal adaptation achieves better performance and explainability compared with supervised methods across benchmarks with different quality criteria, highlighting its potential for real-world applications.

05.
arXiv (CS.CV) 2026-06-11

CoVEBench: Can Video Editing Models Handle Complex Instructions?

While recent text-guided video editing models excel at elementary tasks (e.g., style transfer, object insertion), real-world user requests are highly compositional. A single prompt often demands multiple coupled edits, such as modifying subjects, actions, and camera views, while strictly preserving unrelated spatiotemporal content. Existing benchmarks, heavily constrained by isolated edits and coarse global metrics, fail to diagnose how models handle such complex workflows. To address this gap, we introduce CoVEBench, a compositional video editing benchmark comprising 416 curated source videos, 626 multi-point editing instructions, and 9,990 fine-grained checklist items. Covering diverse editing dimensions, CoVEBench evaluates models via MLLM-judged instruction compliance and video fidelity, alongside automated metrics for video quality. Extensive experiments reveal that compositional editing remains a profound challenge: current models frequently omit edits, violate preservation constraints, or introduce artifacts when handling multiple operations simultaneously. CoVEBench provides a challenging, diagnostic testbed to advance video editing toward realistic user workflows.

06.
arXiv (CS.AI) 2026-06-18

Speaker Verification with Speech-Aware LLMs: Evaluation and Augmentation

arXiv:2603.10827v2 Announce Type: replace-cross Abstract: Speech-aware large language models (LLMs) can accept speech inputs, yet their training objectives largely emphasize linguistic content or specific fields such as emotions or the speaker's gender, leaving it unclear whether they encode speaker identity. First, we propose a model-agnostic scoring protocol that produces continuous verification scores for both API-only and open-weight models, using confidence scores or log-likelihood ratios from the Yes/No token probabilities. Using this protocol, we benchmark recent speech-aware LLMs and observe weak speaker discrimination (EERs above 20% on VoxCeleb1). Second, we introduce a lightweight augmentation that equips an LLM with ASV capability by injecting frozen ECAPA-TDNN speaker embeddings through a learned projection and training only LoRA adapters. On TinyLLaMA-1.1B, the resulting ECAPA-LLM achieves 1.03% EER on VoxCeleb1-E, approaching a dedicated speaker verification system while preserving a natural-language interface.

07.
arXiv (CS.CL) 2026-06-11

Automated Creativity Evaluation of Language Models Across Open-Ended Tasks

Large language models (LLMs) have achieved remarkable progress in language understanding, reasoning, and generation, sparking growing interest in their creative potential. Realizing this potential requires systematic and scalable methods for evaluating creativity across diverse tasks. However, most existing creativity metrics are tightly coupled to specific tasks, embedding domain assumptions into the evaluation process, and limiting scalability and generality. To address this gap, we introduce an automated, domain-agnostic framework for quantifying LLM creativity across open-ended tasks. Our approach separates the measurement apparatus from the creative task itself, enabling scalable, task-agnostic assessment. Divergent creativity is measured using semantic entropy, a reference-free and robust metric for novelty and diversity, validated against human annotations, LLM-based novelty judgments and baseline diversity measures. Convergent creativity is assessed via a novel retrieval-based multi-agent judge framework that delivers context-sensitive evaluation of task fulfilment with over 60% improved efficiency. We validate our framework in three qualitatively distinct domains: problem-solving (MacGyver), research ideation (HypoGen), and creative writing (BookMIA), using a broad suite of LLMs. Empirical results show that our framework reliably captures key facets of creativity, including novelty, diversity, and task fulfilment, and reveal how model properties, such as size, temperature, recency, and reasoning, impact creative performance. Our work establishes a reproducible and generalizable standard for automated LLM creativity evaluation, paving the way for scalable benchmarking and accelerating progress in creative AI.

08.
arXiv (CS.LG) 2026-06-17

Learning Credal Ensembles via Distributionally Robust Optimization

arXiv:2602.08470v3 Announce Type: replace Abstract: Credal predictors are models that are aware of epistemic uncertainty and produce a convex set of probabilistic predictions. They offer a principled way to quantify predictive epistemic uncertainty (EU) and have been shown to improve model robustness in various settings. However, most state-of-the-art methods mainly define EU as disagreement caused by random training initializations, which mostly reflects sensitivity to optimization randomness rather than uncertainty from deeper sources. To address this, we define EU as disagreement among models trained with varying relaxations of the i.i.d. assumption between training and test data. Based on this idea, we propose CreDRO, which learns an ensemble of plausible models through distributionally robust optimization. As a result, CreDRO captures EU not only from training randomness but also from meaningful disagreement due to potential distribution shifts between training and test data. Empirical results show that CreDRO consistently outperforms existing credal methods on tasks such as out-of-distribution detection across multiple benchmarks and selective classification in medical applications.

09.
arXiv (CS.AI) 2026-06-17

LLM-as-Judge in Education: A Curriculum-Grounded Marking Pipeline

arXiv:2606.17507v1 Announce Type: new Abstract: Generative AI and large language models (LLMs) are increasingly applied to question generation and automated assessment. However, deploying LLMs in preparation for high-stakes exams requires more than prompt engineering; it demands software pipelines that systematically ground model outputs in authorised curriculum artefacts and marking guidelines issued by education authorities. This paper presents a curriculum-grounded, configurable LLM-as-Judge pipeline for question-level marking, co-developed with an industrial partner, to support exam preparation for university admission. The pipeline identifies the relevant topics, subtopics, and cognitive demand of a question, and assembles verifiable and authorised context to support LLM judgement. Curriculum intent is operationalised through concrete syllabus artefacts, including prescribed verbs and outcomes, performance band descriptors, glossary definitions, and marking-guideline principles. A staged LLM workflow is employed to first generate question-specific rubrics, capturing structured expectations of performance, and then derive and evaluate marking criteria used to allocate marks to student responses. This design improves consistency, transparency, and alignment with official marking practices. Preliminary evaluation shows that the proposed LLM-as-Judge pipeline delivers marking outcomes comparable to human tutors, while yielding justifications that are more traceable to authorised curriculum artefacts and marking standards. The pipeline has also been integrated into an online study platform, where early deployment data provide initial insights into operational usage and manual overrides.

10.
arXiv (CS.AI) 2026-06-18

TLA-Prover: Verifiable TLA+ Specification Synthesis via Preference-Optimized Low-Rank Adaptation

arXiv:2606.06133v2 Announce Type: replace-cross Abstract: TLA+ is a formal specification language for verifying distributed systems and safety-critical protocols. Large language models (LLMs) frequently produce TLA+ specifications that fail the TLC model checker for semantic reasons. Across 25 LLMs, the best public baseline is 26.6% syntactic parse and 8.6% semantic model-check. We present TLA-Prover, a 20-billion-parameter model for TLA+ specification synthesis. Training combines supervised fine-tuning (SFT) on verified examples with repair-based group-relative policy optimization (GRPO). In the GRPO stage, the model learns to fix its own rejected specifications. We also train a direct preference optimization (DPO) variant from the same SFT checkpoint as an ablation. TLC provides the reward signal directly, with no learned reward model. Four tiers grade each output: Bronze (parses), Silver (no warnings), Gold (passes TLC), and Diamond. To reach Diamond, the model's correctness property is automatically altered in a small way; TLC must then detect a violation. If TLC still passes, the property was always-true and contributes nothing; the output fails Diamond. TLA-Prover reaches 9/30 (i.e. pass@1 = 30%) at both Gold and Diamond on a held-out 30-problem benchmark. This is roughly 3.5x the 8.6% untuned baseline. The DPO variant reaches 20% at Diamond. Gold and Diamond coincide at every checkpoint; this prevents the trivial-property failure mode.

11.
bioRxiv (Bioinfo) 2026-06-19

Tox21mer, A transformer foundation model for Tox21 high-throughput concentration-response curves data

The U.S. Tox21 collaboration has generated a large reference library of high-throughput concentration-response assays. Here we present Tox21mer, a 43.5-million-parameter transformer that encodes each Tox21 concentration-response curve together with assay metadata into a 768-dimensional representation. Tox21mer was pretrained on ~2.5 million curves from 102 assay protocols and 6,727 compounds using masked-response reconstruction as the primary objective, with low-weight auxiliary supervision on assay outcome and AC50. To evaluate the learned representation, we trained lightweight probes on frozen embeddings from concentration-response curves of held-out compounds. The representation supported a macro-F1 of 0.985 for three-class outcome prediction (agonist, antagonist, inactive), a binary F1 of 0.994 for active/inactive prediction, and an R2 of 0.87 for log10(AC50). The learned embeddings formed coherent groupings by curve-class category. A masked-only pretraining variant retained near-baseline probe performance, indicating that the representation is learned largely from the self-supervised objective rather than from auxiliary labels. Ablation analyses further showed that predictive performance depends mainly on curve-level response-value distributions conditioned on assay context, with limited reliance on detailed within-curve ordering. Tox21mer thus provides a reusable foundation representation for Tox21 concentration-response data that can support extrapolation to untested compounds through integration with chemical features or distillation into chemistry-only student models for large-scale external screening.

12.
arXiv (CS.CL) 2026-06-19

NAMESAKES: Probing Identity Memorization in Text-to-Image Models

Text-to-image (T2I) models generate realistic likenesses of some individuals when prompted with their names, raising privacy concerns. However, distinguishing whether a generated face is memorized or fabricated currently requires ground-truth photos, access to training data, or white-box access to model internals, limiting applicability. We introduce a fully black-box behavioral probe that distinguishes between these regimes while requiring no reference photos or prior knowledge of training data. To benchmark this task, we present the NAMESAKES dataset of over one thousand names and faces of public figures spanning a wide range of fame levels, along with perturbed, less famous names. Experiments on state-of-the-art T2I models show that our probe substantially predicts identity memorization and separates memorized from unrecognized names, with further insights into differences across model families.

13.
arXiv (CS.CL) 2026-06-15

Retrospective Progress-Aware Self-Refinement for LLM Agent Training

LLM-based agents trained with reinforcement learning optimize step-wise action prediction but lack metacognitive awareness of task progress, inducing a gap that hinders long-horizon scaling. A pilot study reveals that online progress prompting hurts performance while retrospective demonstrations help, yet this capability cannot emerge from outcome-reward training alone. We present RePro, Retrospective Progress-Aware Training, a framework that trains agents to self-generate progress signals via a forward-then-reflect rollout paradigm: the agent executes actions online, then retrospectively reassesses its step-wise progress given the completed trajectory and known outcome. RePro initializes with a Retrospection Warmup that teaches reflection format from minimal external demonstrations, then further trains through RePro-PO with a composite reward that produces self-generated signals without continuous external supervision. Experiments on WebShop, ALFWorld, and Sokoban show that RePro enhances the Qwen family's performance, with up to $12\%$ absolute success rate gains.

14.
arXiv (CS.AI) 2026-06-12

M*: A Modular, Extensible, Serving System for Multimodal Models

arXiv:2606.12688v1 Announce Type: cross Abstract: We are entering a new era of composite model architectures that integrate diverse components such as vision encoders, language backbones, diffusion and flow heads, audio codecs, action generators, and world-model predictors. Such architectures underpin a broad class of multimodal models, including unified multimodal models, omni models, speech-language models, vision-language-action policies, and world models. However, existing model serving frameworks were built on narrow assumptions about model structure, making them ill-suited to accommodate this new architectural diversity. Here we present M*, a universal serving system for efficient serving of composite AI models. M* represents models as dataflow graphs, processing requests spanning diverse modalities and tasks as traversals over these graphs. The core insight is a modular abstraction that supports arbitrary composition of model components, flexible placement onto a physical cluster, and model-agnostic optimizations within a distributed runtime. We call this abstraction the Walk Graph and show how it can concisely capture composite models from a broad range of families. We instantiate M* on representative models and find that it achieves, on average, 20% lower end-to-end latency than vLLM-Omni for text-to-image workloads on BAGEL, while delivering up to 2.9x lower real-time factor and 2.7x higher throughput for text-to-speech workloads on Qwen3-Omni. M* also outperforms the V-JEPA 2-AC rollout baseline for robotic planning by up to 12.5x. Thus, our work paves the road towards more efficient serving of complex models with minimal developer effort.

15.
arXiv (CS.CV) 2026-06-12

Visual enhancement and 3D representation for underwater scenes: a review

Underwater visual enhancement (UVE) and underwater 3D reconstruction pose significant challenges in computer vision and AI-based tasks due to complex imaging conditions in aquatic environments. Despite the development of numerous enhancement algorithms, a comprehensive and systematic review covering both UVE and underwater 3D reconstruction remains absent. To advance research in these areas, we present an in-depth review from multiple perspectives. First, we introduce the fundamental physical models, highlighting the peculiarities that challenge conventional techniques. We survey advanced methods for visual enhancement and 3D reconstruction specifically designed for underwater scenarios. The paper assesses various approaches from non-learning methods to advanced data-driven techniques, including Neural Radiance Fields and 3D Gaussian Splatting, discussing their effectiveness in handling underwater distortions. Finally, we conduct both quantitative and qualitative evaluations of state-of-the-art UVE and underwater 3D reconstruction algorithms across multiple benchmark datasets. Finally, we highlight key research directions for future advancements in underwater vision.

16.
arXiv (CS.CV) 2026-06-16

AURA: Active-Response Attribution under Treatment Ambiguity in Bacterial Cytological Profiling

When a bacterial sample is exposed to several antibiotics, not every applied drug necessarily acts: if the organism is resistant to one of them, that drug leaves no morphological trace. The clinically meaningful quantity is therefore not which antibiotics were applied, but which ones were active. We show that these two are sharply decoupled in real E. coli microscopy - naively assuming the applied combination equals the active one is correct only about 37% of the time - yet existing computational tools are ill-suited to recovering the active set. Forward perturbation models such as scGen, CPA, and IMPA are designed to predict appearance from treatment, not the reverse, and inverting them degrades sharply; discriminative image classifiers tend to memorise strain- and batch-specific texture and fail to transfer across experimental replicates. We introduce AURA, which reframes the task as constrained, energy-based inverse attribution. Its central inductive bias is that the active set must be a subset of the applied set; this collapses the candidate space and lets AURA infer the active subset of applied antibiotics by decomposing residual morphology into antibiotic response atoms and selecting the subset with the lowest reconstruction energy, using no strain label at test time. AURA-E adds evidence-aware abstention, withholding a prediction when candidate explanations remain near-equally plausible. On cross-replicate transfer in an E. coli cytological profiling dataset, AURA recovers the active antibiotic combination with 95.47% exact-match accuracy.

17.
arXiv (CS.CV) 2026-06-16

The Third Challenge on Image Denoising at NTIRE 2026: Methods and Results

This paper reports on the NTIRE 2026 Challenge on Image Denoising, specifically focusing on the high-noise regime ($\sigma = 50$). The competition investigates advanced neural architectures designed to restore high-fidelity details from images corrupted by additive white Gaussian noise (AWGN). Unlike constrained benchmarks, this track emphasizes peak quantitative performance, measured by Peak Signal-to-Noise Ratio (PSNR), without limitations on parameter count or computational overhead. By synthesizing contributions from 20 finalist teams out of 116 registrants, this report benchmarks the latest technical innovations and provides a comprehensive snapshot of the current state-of-the-art in unconstrained image restoration.

18.
arXiv (CS.CV) 2026-06-17

BrainWorld: A Structural-Prior-Conditioned Generative Model for Whole-Brain 4D fMRI Dynamics

Whole-brain 4D fMRI generation is valuable for modeling functional brain dynamics, yet existing fMRI foundation models mainly target representation learning and downstream prediction rather than conditional predictive generation. We introduce BrainWorld, a structural-prior-conditioned generative model for whole-brain 4D fMRI dynamics. BrainWorld uses sMRI as subject-level anatomical context to guide future fMRI generation, integrating structural information into the denoising process rather than treating it as a parallel modality. Evaluated on 22 datasets spanning diverse cohorts and brain states, BrainWorld generates stable 4D fMRI trajectories up to 400 frames, improves downstream performance through generated-example augmentation, and learns transferable multimodal representations that outperform baselines. Together, these results establish BrainWorld as a condition-aware generative framework for long-horizon brain dynamics modeling and multimodal representation learning.

19.
arXiv (CS.CV) 2026-06-17

NTIRE 2025 Challenge on Image Super-Resolution (x4): Methods and Results

This paper presents the NTIRE 2025 image super-resolution ($\times$4) challenge, one of the associated competitions of the 10th NTIRE Workshop at CVPR 2025. The challenge aims to recover high-resolution (HR) images from low-resolution (LR) counterparts generated through bicubic downsampling with a $\times$4 scaling factor. The objective is to develop effective network designs or solutions that achieve state-of-the-art SR performance. To reflect the dual objectives of image SR research, the challenge includes two sub-tracks: (1) a restoration track, emphasizes pixel-wise accuracy and ranks submissions based on PSNR; (2) a perceptual track, focuses on visual realism and ranks results by a perceptual score. A total of 286 participants registered for the competition, with 25 teams submitting valid entries. This report summarizes the challenge design, datasets, evaluation protocol, the main results, and methods of each team. The challenge serves as a benchmark to advance the state of the art and foster progress in image SR.

20.
arXiv (quant-ph) 2026-06-12

QuBE/Qubex: an integrated hardware-software system for superconducting qubit experiments with broadband control

arXiv:2606.13010v1 Announce Type: new Abstract: Achieving high-fidelity operation in large-scale superconducting qubit systems requires not only control hardware with broad frequency coverage, low crosstalk, and tight synchronization but also software that coordinates system configuration, experiment execution, and data analysis. Here we present an integrated qubit-control system that combines broadband microwave hardware with a pulse-level software stack for scalable superconducting qubit experiments. The hardware provides broadband microwave coverage, including an instantaneous span of up to 1.6 GHz from a control output, while the software reduces setup and calibration overhead through automated configuration and built-in experiment workflows. We validate the system on a 64-qubit fixed-frequency transmon chip through full-chip frequency identification and representative demonstrations, including multi-unit far-detuned cross-resonance calibration and benchmarking that yields a measured two-qubit gate fidelity of 98.34%, and multilevel readout beyond the computational subspace. By disclosing the hardware architecture and releasing the software stack as open source, this work provides an inspectable hardware-software foundation for scalable superconducting qubit control experiments.

21.
bioRxiv (Bioinfo) 2026-06-11

Combinatorial docking and molecular generation to navigate over 100-billion molecules for prospective ligand discovery

Commercially available make-on-demand libraries now exceed 100 billion compounds, requiring over 50 years to screen on 2,000 CPU cores using conventional docking. We present two complementary approaches to address this challenge. CombiDOCK, a combinatorial docking framework, enables exhaustive screening at the 100-billion scale within 40 days. MINT-Dock, a generative framework, accelerates navigation of this space by integrating CombiDOCK with Monte Carlo Tree Search. Benchmarked on 46 diverse targets, CombiDOCK matched full-molecule docking accuracy, and MINT-Dock achieved a 4,800-fold enrichment over random selection. Compared with prior billion-scale brute-force campaigns against {sigma}2, VMAT2, and VAChT, prospective CombiDOCK screens of the 100-billion-molecule library yielded higher hit rates and more potent ligands, while MINT-Dock achieved comparable outcomes across single- and multi-target objectives with >20-fold computational cost reductions. Docking-predicted poses of the best VAChT-binding compounds were confirmed by cryo-EM structures. These methods provide exhaustive and generative paths for navigating the trillion-molecule frontier of drug discovery.

22.
arXiv (CS.AI) 2026-06-16

Learning Earthquake Wave Arrival Time Picking from Labels with Inaccuracies

arXiv:2606.15377v1 Announce Type: cross Abstract: Inaccurately labeled training data, or "label noise", poses a significant threat to the integrity of supervised machine learning models. This corruption directly degrades performance by teaching the model erroneous mappings between features and labels, which leads to poor generalization and reduced accuracy on properly labeled validation and test data. Current seismological applications mainly rely on large-scale training sets or data augmentation to reduce the label-noise impact, which can be labor-intensive and costly. Here, we introduce a Label Noise-Contrastive Robust Learning (LaNCoR) approach that can effectively handle noisy labels in seismic signal processing tasks, without requiring large-scale training datasets. In this approach, the input waveform feature and label representation distributions are aligned in the feature space to correct mislabeling and reduce its impact on the training process. We present LaNCoR's performance on the task of P-phase arrival-time picking of real microseismic data using two baseline models and training approaches. Our results indicate that LaNCoR can improve performance by up to 28.8% across performance metrics. This approach holds great promise for model training in seismology and geosciences.

23.
arXiv (CS.CL) 2026-06-17

Zone of Proximal Policy Optimization: Teacher in Prompts, Not Gradients

Knowledge distillation transfers a teacher's competence to a small student but is brittle in the small-student regime: forcing the student to imitate logits from a much larger teacher concentrates it on the teacher's sharpest modes, hurting generalization on benchmark families beyond the training corpus. Reinforcement learning (RL) avoids logit imitation by training on the student's own rollouts. However, on questions where every rollout fails-yielding zero advantage and being silently discarded-injecting a stronger teacher's response into the policy gradient breaks the on-policy assumption and induces drift. We introduce Zone of Proximal Policy Optimization (ZPPO), inspired by Vygotsky's zone of proximal development, which keeps the teacher inside the prompt rather than the policy gradient. On hard questions, ZPPO constructs two reformulated prompts: a Binary Candidate-included Question (BCQ) pairs one correct teacher response with one incorrect student response as anonymized candidates the student must discriminate, and a Negative Candidate-included Question (NCQ) aggregates the student's wrong rollouts into a single prompt to surface their shared failure modes. A prompt replay buffer recirculates each hard question until it either graduates-the student's mean rollout accuracy on it reaches half- or is FIFO-evicted under finite capacity, amplifying BCQ and NCQ inside the student's current zone of proximal development. On the Qwen3.5 family at four student scales (0.8B-9B) with a 27B teacher, post-trained as vision-language models and evaluated on a 31-benchmark suite (16 VLM, 10 LLM, 5 Video), ZPPO outperforms off/on-policy distillation and GRPO, with the largest gains at the smallest scale.

24.
arXiv (CS.CL) 2026-06-12

Agents' Last Exam

Recent AI systems have achieved strong results on a wide range of benchmarks, yet these gains have not translated into economically meaningful deployment across many professional domains. We argue that this gap is largely an evaluation problem: widely used benchmarks lack sustained performance measurement on real and economically valuable workflows. This paper introduces Agents' Last Exam (ALE), a benchmark designed to evaluate AI agents on long horizon, economically valuable, real world tasks with verifiable outcomes. Developed in collaboration with 250+ industry experts, ALE covers non-physical industries defined with reference to O*NET / SOC 2018 (the U.S. federal occupational taxonomy). It is organized around a task taxonomy with 55 sub fields grouped into 13 industry clusters covering 1K+ tasks. Current results show that the hardest tier remains far from saturated: across mainstream harness and backbone configurations, the average full pass rate is below 1%. ALE is designed as a living benchmark: its task pool grows continuously as new workflows and industries are onboarded. More broadly, ALE is intended not merely as another leaderboard, but as an instrument for closing the gap between benchmark success and GDP relevant impact.

25.
arXiv (CS.CL) 2026-06-11

The Periodic Table of LLM Reasoning: A Structured Survey of Reasoning Paradigms, Methods, and Failure Modes

Large Language Models (LLMs) have achieved strong performance across natural language processing tasks, yet reliable reasoning remains an open challenge. Although modern LLMs show progress in structured inference, multi-step problem solving, and contextual understanding, their reasoning behavior is often inconsistent and sensitive to prompting strategies, task design, and model scale. This survey provides a systematic analysis of more than 300 recent papers from arXiv, Semantic Scholar, Google Scholar, Papers with Code, and the ACL Anthology to examine how reasoning capabilities emerge in LLMs and where they fail. We make three main contributions. First, we introduce a structured taxonomy of LLM reasoning research, covering Chain-of-Thought reasoning, multi-hop reasoning, mathematical reasoning, common sense reasoning, visual and temporal reasoning, code and algorithmic reasoning, retrieval-augmented reasoning, tool-augmented and agentic reasoning, and reinforcement learning-based reasoning. Second, we analyze methodological trends across these paradigms, including prompting methods, model architectures, training objectives, reward modeling, and evaluation benchmarks. Third, we synthesize recurring limitations and failure modes, such as reasoning hallucinations, brittle multi-step inference, weak causal abstraction, and poor cross-domain generalization. By organizing a rapidly expanding literature, this survey offers a unified view of the current capabilities and limitations of reasoning in LLMs. We also identify emerging research directions, including meta-reasoning, self-evolving reasoning frameworks, multimodal reasoning, and socially grounded reasoning. Overall, this work aims to serve as a reference for developing more robust, interpretable, and generalizable reasoning systems in future language models.