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.

01.
arXiv (quant-ph) 2026-06-16

Quantum speedup from nonclassical polarization

arXiv:2603.23124v2 Announce Type: replace Abstract: We develop a framework for identifying nonclassical speedups in systems with polarization, likewise spin degrees of freedom. By confining the dynamics to the manifold of angular momentum coherent states, which act as the classical reference in this case, we compute the speed limit that bounds the rate of change of the state achievable without generating quantum coherence. A comparison with the unrestricted quantum speed limit enables the quantitative identification of speedups arising from polarization nonclassicality. We apply this framework to the cross-Kerr interaction, demonstrating a persistent speedup scaling as $\mathcal{O}(\sqrt{N})$ with the photon number $N$ with a parity effect in favour of even photon numbers. The results establish polarization nonclassicality as a genuine dynamical resource, linking quantum coherence to quantum-enhanced evolution speeds in nonlinear photonic systems.

02.
arXiv (CS.LG) 2026-06-15

Temporal Straightening for Latent Planning

arXiv:2603.12231v2 Announce Type: replace Abstract: Learning good representations is essential for latent planning with world models. While pretrained visual encoders produce strong semantic visual features, they are not tailored to planning and contain information irrelevant – or even detrimental – to planning. Inspired by the perceptual straightening hypothesis in human visual processing, we introduce temporal straightening to improve representation learning for latent planning. Using a curvature regularizer that encourages locally straightened latent trajectories, we jointly learn an encoder and a predictor of a Joint-Embedding Predictive Architecture (JEPA) world model. We show that reducing curvature this way makes the Euclidean distance in latent space a better proxy for the geodesic distance and improves the conditioning of the planning objective. We demonstrate empirically that temporal straightening makes gradient-based planning more stable and yields significantly higher success rates across a suite of goal-reaching tasks. Our code is available at https://agenticlearning.ai/temporal-straightening.

03.
arXiv (CS.AI) 2026-06-12

Standardized Methods and Recommendations for Green Federated Learning

arXiv:2602.00343v2 Announce Type: replace-cross Abstract: Federated learning (FL) enables collaborative model training over privacy-sensitive, distributed data, but its environmental impact is difficult to compare across studies due to inconsistent measurement boundaries and heterogeneous reporting. We present a practical carbon-accounting methodology for FL CO2e tracking using NVIDIA NVFlare and CodeCarbon for explicit, phase-aware tasks (initialization, per-round training, evaluation, and idle/coordination). To capture non-compute effects, we additionally estimate communication emissions from transmitted model-update sizes under a network-configurable energy model. We validate the proposed approach on two representative workloads: CIFAR-10 image classification and retinal optic disk segmentation. In CIFAR-10, controlled client-efficiency scenarios show that system-level slowdowns and coordination effects can contribute meaningfully to carbon footprint under an otherwise fixed FL protocol, increasing total CO2e by 8.34x (medium) and 21.73x (low) relative to the high-efficiency baseline. In retinal segmentation, swapping GPU tiers (H100 vs.\ V100) yields a consistent 1.7x runtime gap (290 vs. 503 minutes) while producing non-uniform changes in total energy and CO2e across sites, underscoring the need for per-site and per-round reporting. Overall, our results support a standardized carbon accounting method that acts as a prerequisite for reproducible 'green' FL evaluation. Our code is available at https://github.com/Pediatric-Accelerated-Intelligence-Lab/carbon_footprint.

04.
arXiv (CS.LG) 2026-06-15

Muon$^p$: Muon with Fractional Spectral Powers

arXiv:2606.13867v1 Announce Type: new Abstract: Muon is an increasingly widely used optimizer that replaces a gradient $G=USV^\top$ with its polar factor $UV^\top$, thereby flattening the singular spectrum. However, full flattening discards singular-value information that may matter for adaptation. We introduce Muon$^p$, a Muon-style optimizer that instead uses fractional spectral-power updates $US^pV^\top$ for rational $p\in(0,1)$, interpolating between Muon and gradient descent. To make it practical, we prove that fractional spectral powers cannot be computed by any fixed univariate polynomial iteration, and furthermore derive low-degree odd bivariate recurrences that approximate $US^pV^\top$ using only matrix multiplications, preserving Muon's matrix-multiplication-only structure and compute complexity. We show that Muon$^p$ maximizes the linear improvement in loss under the Schatten $q$-norm for $q=1+\frac{1}{p}$. Empirically, Muon$^p$ is especially effective for finetuning: on billion-scale models, Muon$^p$ improves validation perplexity and downstream task performance. We further analyze when Muon$^p$ is less suitable, through the lens of spectral geometry. Our results reveal important insights on when preserving the singular spectrum can bring significant gains, and introduce a principled way to achieve them.

05.
arXiv (CS.CL) 2026-06-16

P3B3: A Multi-Turn Conversational Benchmark for Measuring European and Brazilian Portuguese Variety Bias in LLMs

As Large Language Models (LLMs) become embedded in everyday communication, capturing regional linguistic variation is essential for reliable and equitable language use. In Portuguese, European (pt-PT) and Brazilian (pt-BR) varieties remain unevenly represented, with pt-BR dominating in data quantity, while LLM preference for Portuguese variants remains underexplored. To address this gap, we introduce P3B3, an expert-curated language variety agnostic benchmark of conversational prompts, along with an evaluation framework for measuring variety bias and controllability. Experiments on several models show that most LLMs exhibit a strong bias toward pt-BR, with variation in controllability across models. These results highlight the need for more balanced multilingual representation across language varieties.

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

Dealing with Annotator Disagreement in Hate Speech Classification

Hate speech detection is a crucial task, especially on social media where harmful content can spread quickly. Collecting social media content (tweets etc.) to train machine learning models is easy, but detecting and categorizing hate speech can be difficult due to the inherently subjective nature. This subjectivity leads to frequent disagreement among annotators, particularly for subtle or borderline content. Traditional approaches either discard non-consensus samples or force a ''gold standard'' through expert adjudication, ignoring valuable information about uncertainty and diverse human perspectives. We examine the largely overlooked problem of annotator disagreement in hate speech classification and evaluate a range of aggregation methods, including majority voting, ordinal strategies (minimum, maximum, and mean), and analyze their impact across binary, 4-class, and 6-class classification tasks. In addition, we leverage annotators' perceived hate speech strength scores to explore regression-based and hybrid modeling approaches. Among others, we show that filtering non-consensus samples results in over-optimistic results and that the perceived strength provides a complementary signal that enhance classification performance. Finally, we establish new state-of-the-art results for hate speech detection in Turkish tweets, and demonstrate that annotator disagreement, when properly modeled, is a valuable resource for building more robust and reliable systems.

07.
arXiv (CS.CL) 2026-06-17

DICE: Diffusion Large Language Models Excel at Generating CUDA Kernels

Diffusion large language models (dLLMs) have emerged as a compelling alternative to autoregressive (AR) LLMs, owing to their capacity for parallel token generation. This paradigm is particularly well-suited for code generation, where holistic structural planning and non-sequential refinement are critical. Despite this potential, tailoring dLLMs for CUDA kernel generation remains challenging, obstructed not only by the high specialization but also by the severe lack of high-quality training data. To address these challenges, we construct CuKe, an augmented supervised fine-tuning dataset optimized for high-performance CUDA kernels. On top of it, we propose a bi-phase curated reinforcement learning (BiC-RL) framework consisting of a CUDA kernel infilling stage and an end-to-end CUDA kernel generation stage. Leveraging this training framework, we introduce DICE, a series of diffusion large language models designed for CUDA kernel generation, spanning three parameter scales, 1.7B, 4B, and 8B. Extensive experiments on KernelBench demonstrate that DICE significantly outperforms both autoregressive and diffusion LLMs of comparable scale, establishing a new state-of-the-art for CUDA kernel generation.

08.
arXiv (quant-ph) 2026-06-11

High-efficiency telecom conversion of heralded atomic biphoton wavepackets

arXiv:2603.09824v2 Announce Type: replace Abstract: We demonstrate high-efficiency telecom frequency conversion of heralded atomic biphoton wavepackets using a diamond-type atomic ensemble. By placing a 2.5 MHz heralded-photon spectrum within the high-efficiency region of the converter response, we achieve a conversion efficiency of 79.4(2.6)% while maintaining strong time-resolved correlations and well-defined temporal wavepackets. For a broader 17.4 MHz input bandwidth, the conversion efficiency is reduced to about 55%, whereas the temporal waveform remains largely preserved. This behavior reflects the nearly flat central response of the converter, which mainly causes spectral-edge loss rather than temporal-mode distortion. These results identify spectral matching as an effective route to efficient and low-distortion telecom conversion of narrowband quantum light from atomic systems.

09.
arXiv (CS.AI) 2026-06-16

From Overload to Convergence: Supporting Multi-Issue Human-AI Negotiation with Bayesian Visualization

arXiv:2603.22766v2 Announce Type: replace-cross Abstract: As AI systems increasingly mediate negotiations, understanding how the number of negotiated issues impacts human performance is crucial for maintaining human agency. We designed a human-AI negotiation case study in a realistic property rental scenario, varying the number of negotiated issues; empirical findings show that without support, performance stays stable up to three issues but declines as additional issues increase cognitive load. To address this, we introduce a novel uncertainty-based visualization driven by Bayesian estimation of agreement probability. It shows how the space of mutually acceptable agreements narrows as negotiation progresses, helping users identify promising options. In a within-subjects experiment (N=32), it improved human outcomes and efficiency, preserved human control, and avoided redistributing value. Our findings surface practical limits on the complexity people can manage in human-AI negotiation, advance theory on human performance in complex negotiations, and offer validated design guidance for interactive systems.

10.
Nature Medicine 2026-06-08

Post-adjuvant chemotherapy in ctDNA-positive patients with resected colorectal cancer: a randomized phase 3 trial

Authors:

Tumor-informed circulating tumor DNA (ctDNA) enables detection of molecular residual disease (MRD) after curative resection of colorectal cancer (CRC), but whether early intervention improves outcomes remains uncertain. ALTAIR was a randomized, double-blind, phase 3 trial embedded in the CIRCULATE-Japan platform evaluating a post-adjuvant ctDNA surveillance strategy with treatment initiation upon molecular recurrence. Patients with resected stage 0–IV CRC who became ctDNA positive after completion of standard-of-care therapy and had no radiological evidence of disease were randomly assigned (1:1) to receive trifluridine/tipiracil (FTD/TPI) or placebo for 6 months. The primary endpoint was investigator-assessed disease-free survival (DFS). Between July 2020 and June 2023, 243 patients were randomized to FTD/TPI (n = 122) or placebo (n = 121). Median DFS was 9.30 months with FTD/TPI and 5.55 months with placebo (hazard ratio = 0.79, 95% confidence interval: 0.60–1.05, P = 0.107), and the primary endpoint was not met. FTD/TPI increased grade 3 or higher hematologic adverse events (73.0% versus 3.3%) without new safety signals. These findings indicate that post-adjuvant intervention with FTD/TPI did not significantly improve DFS in ctDNA-positive patients without radiological disease. ClinicalTrials.gov identifier: NCT04457297 . In the randomized, double-blind phase 3 ALTAIR trial, patients with resected colorectal cancer who became positive for circulating tumor DNA during post-adjuvant surveillance received trifluridine/tipiracil hydrochloride therapy, which did not significantly prolong disease-free survival compared with placebo.

11.
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.

12.
arXiv (CS.AI) 2026-06-17

OmniSapiens: A Foundation Model for Social Behavior Processing via Heterogeneity-Aware Relative Policy Optimization

arXiv:2602.10635v3 Announce Type: replace Abstract: Socially intelligent AI systems must reason across diverse human behavioral tasks and generalize to new social contexts. However, behavioral data is inherently heterogeneous, comprising diverse modalities and prediction targets that produce uneven training signals across samples, creating imbalanced learning dynamics that challenge existing AI models. To address this, we develop Omnisapiens-7B 2.0, a foundation model for social behavior processing that explicitly addresses learning from heterogeneous behavioral data. This is enabled through Heterogeneity-Aware Relative Policy Optimization, a new RL method that rebalances learning signals across samples by approximating each sample's contribution to the policy update and using these estimates to drive geometrically centered, inertially smoothed advantage modulation for stable training. Omnisapiens-7B 2.0 achieves the best and most consistent performance across 10 behavioral tasks, while also attaining the best performance on all five held-out benchmarks, with gains of up to +12.02% and +9.37% respectively. Furthermore, it demonstrates more consistent and interpretable reasoning traces, supporting reliable real-world behavioral applications. Our model is available at https://github.com/MIT-MI/human_behavior_atlas.

13.
arXiv (CS.AI) 2026-06-18

RippleBench: Capturing Ripple Effects Using Existing Knowledge Repositories

arXiv:2512.04144v2 Announce Type: replace Abstract: Targeted interventions on language models, such as unlearning or model editing, aim to modify specific information, but their effects often propagate to related, unintended areas (e.g., removing virology content may degrade performance on allergies); these side-effects are commonly referred to as the ripple effect. We introduce RippleBench-Maker, an automatic pipeline that retrieves semantic neighbors of any source concept from a knowledge repository and generates multiple-choice questions at varying semantic distances. We instantiate this framework using WikiRAG, an open-source RAG system over English Wikipedia, to construct RippleBench-WMDP-Bio (584 seed topics, 352,961 questions), and evaluate eight unlearning methods on Llama3-8B-Instruct. All eight exhibit accuracy drops that are largest near the unlearned target and decay with semantic distance, each with a distinct propagation profile. We replicate these findings across Mistral-7B, Zephyr-7B, and Yi-34B; cross-model delta curves are nearly identical, suggesting ripple effects are a property of the unlearning method rather than the base model. We validate all major pipeline stages using a four-experiment Mechanical Turk study (5,200+ responses, 61 workers). We release all code, data, and infrastructure.

14.
bioRxiv (Bioinfo) 2026-06-21

Machine learning evaluation of gene expression-based ALS subtypes across brain and blood tissues

The clinical and molecular heterogeneity observed in amyotrophic lateral sclerosis (ALS) presents a challenge for diagnosis, prognosis, and treatment. RNA sequencing of post-mortem brain samples from ALS patients has identified several subtypes with distinct molecular signatures. We sought to evaluate these subtypes across diverse tissues and datasets and assess the feasibility of supervised machine learning models for sample classification. Unsupervised clustering and pathway analysis were performed to confirm the presence of ALS subtypes in motor cortex samples. Three machine learning strategies were then used to create models based on post-mortem motor cortex expression data of 112 people with ALS from the London Neurodegenerative Diseases Brain Bank. These models were subsequently improved through feature selection and evaluated in independent cohorts from motor cortex (n = 257, NYGC ALS Consortium) and blood (n = 96, Macquarie University Neurodegenerative Disease Biobank) samples. Multi-class linear discriminant analysis (LDA) models were then used for subtype classification. Clustering of ALS post-mortem motor cortex samples confirmed the presence of three subtypes: neuroinflammation (ALS-Neu), extracellular matrix organisation and muscle contraction (ALS-OxA), and synaptic and neuropeptide signalling (ALS-SNs). Among all machine learning strategies, random forests produced the most accurate and stable models for binary classification (~93% accuracy across the three subtypes). After feature selection, random forest models were able to classify samples from an independent post-mortem motor cortex cohort in their respective subtypes (AUC of ~0.98 across the three subtypes). When these models were evaluated in blood using LDA, we found consistent clustering patterns, with samples aligning in the same subtype regions of the post-mortem motor cortex samples, with ALS-SNs being the subtype in which samples were classified with the highest confidence (LDA class probability ~86%). Moreover, classification for this subtype improved when blood samples were collected closer to death. Our findings support the presence of three gene expression-based ALS subtypes in motor cortex samples and the utility of machine learning strategies for subtype classification. We also observed that the subtypes identified in the brain partially match those in the blood, with samples from the late stages of the disease more likely to be correctly predicted into the ALS-SNs cluster. This suggests a longitudinal effect in subtype identification that requires further investigation.

15.
arXiv (CS.CL) 2026-06-19

AtomMem: Building Simple and Effective Memory System for LLM Agents via Atomic Facts

Large language models (LLMs) demonstrate strong reasoning and generation abilities, but their fixed context windows limit long-term information accumulation and reuse across multi-session interactions. Existing memory-augmented systems often construct memory in a coarse and unstable manner, relying on inefficient memory representations or unstable unconstrained updates. To address these challenges, we propose AtomMem, a long-term memory system designed for value-dense storage and stable memory evolution. AtomMem introduces a Fact Executor, which selectively extracts high value atomic facts from long form interactions to serve as highly efficient memory representations. Subsequently, AtomMem organizes these facts into hierarchical event structures and temporal profiles, capturing coherent episodic contexts and tracking dynamically evolving user attributes over time. During retrieval, the system activates an associative memory graph to connect fragmented memories. Experiments on the LoCoMo benchmark confirm that AtomMem achieves state-of-the-art performance across various reasoning tasks, offering a scalable and economically viable solution for deploying intelligent personalized agents.

16.
arXiv (CS.CL) 2026-06-15

Token-Level LLM Collaboration via FusionRoute

Large language models (LLMs) exhibit strengths across diverse domains. However, achieving strong performance across these domains with a single general-purpose model typically requires scaling to sizes that are prohibitively expensive to train and deploy. On the other hand, while smaller domain-specialized models are much more efficient, they struggle to generalize beyond their training distributions. To address this dilemma, we propose FusionRoute, a robust and effective token-level multi-LLM collaboration framework in which a lightweight router simultaneously (i) selects the most suitable expert at each decoding step and (ii) contributes a complementary logit that refines or corrects the selected expert's next-token distribution via logit addition. Unlike existing token-level collaboration methods that rely solely on fixed expert outputs, we provide a theoretical analysis showing that pure expert-only routing is fundamentally limited: unless strong global coverage assumptions hold, it cannot in general realize the optimal decoding policy. By augmenting expert selection with a trainable complementary generator, FusionRoute expands the effective policy class and enables recovery of optimal value functions under mild conditions. Empirically, across both Llama-3 and Gemma-2 families and diverse benchmarks spanning mathematical reasoning, code generation, and instruction following, FusionRoute outperforms both sequence- and token-level collaboration, model merging, and direct fine-tuning, while remaining competitive with domain experts on their respective tasks.

17.
arXiv (CS.LG) 2026-06-15

Shuttling Compiler for Trapped-Ion Quantum Computers Based on Large Language Models

arXiv:2512.18021v3 Announce Type: replace-cross Abstract: We present the first shuttling compiler based on large language models (LLMs) for trapped-ion quantum computers, where qubits are shuttled between segments for gate execution and qubit storage. We fine-tune pre-trained LLMs on examples from linear and branched one-dimensional shuttling architectures. Thus, we obtain a layout-independent compilation strategy that learns the required shuttling operations directly from data. Using benchmark circuits with up to 16 qubits, such fine-tuned LLMs can now generate valid schedules for shuttling architectures. Notably, we also obtain a valid schedule for a previously unseen four-way junction layout. This demonstrates that trained LLMs can generalize to layouts not encountered during training. For various architectures, LLM-based schedules improve upon state-of-the-art baseline compiler results, reducing the shuttling effort by up to 15%.

18.
arXiv (CS.CL) 2026-06-16

PVminerLLM2: Improving Structured Extraction of Patient Voice via Preference Optimization

Motivation: Patient-generated text contains critical information on patients' lived experiences, social context, and care engagement, but remains largely unstructured, limiting its use in patient-centered outcomes research. Prior work introduced the PV-Miner benchmark and PVMinerLLM models for structured extraction. However, supervised fine-tuning (SFT) alone struggles with rare, fine-grained, and unevenly distributed errors, particularly in token-critical structured outputs. Results: We present PVminerLLM2, an improved set of LLMs for structured patient voice extraction that applies preference optimization to address token-critical errors beyond the reach of supervised fine-tuning. Our method introduces (i) a preference objective with token-level gated stabilization term that prevents degradation of absolute token likelihood under preference optimization, and (ii) confusion-aware preference pair construction to better capture low-separation distinctions. We further incorporate token-importance weighting and inverse-frequency reweighing to address token imbalance and class skew. Across multiple model sizes, PVMinerLLM2 consistently outperforms strong baselines, achieving gains of up to 4.43% (Code), 3.50% (Sub-code), and 1.55% (Span), and outperforms baseline LLM trained with existing preference optimization methods. Availability and Implementation: The supplementary material, code, evaluation scripts, and trained models for PVminerLLM2 are publicly available at: https://github.com/Data-Mining-Lab-Yale/PVminerLLM2

19.
arXiv (CS.LG) 2026-06-15

On the Geometry and Optimization of Polynomial Convolutional Networks

arXiv:2410.00722v3 Announce Type: replace Abstract: We study convolutional neural networks with monomial activation functions. Specifically, we prove that their parameterization map is regular and is an isomorphism almost everywhere, up to rescaling the filters. By leveraging on tools from algebraic geometry, we explore the geometric properties of the image in function space of this map - typically referred to as neuromanifold. In particular, we compute the dimension and the degree of the neuromanifold, which measure the expressivity of the model, and describe its singularities. Moreover, for a generic large dataset, we derive an explicit formula that quantifies the number of critical points arising in the optimization of a regression loss.

20.
arXiv (CS.LG) 2026-06-11

Multi-agent rendezvous in fluid flows via reinforcement learning

arXiv:2606.11274v1 Announce Type: cross Abstract: Rendezvous is a critical task for multi-agent systems, requiring agents to coordinate to meet at an unspecified location. However, achieving this in fluid environments presents a challenge, as it remains unclear how agents can exploit underlying fluid kinematics to facilitate convergence. In this study, we adopt a multi-agent reinforcement learning (MARL) approach to develop physics-informed rendezvous strategies in vortical flows. Compared to a naive strategy, where agents navigate toward their counterparts, MARL strategies significantly improve the rendezvous rate. MARL strategies also show transferability across varying vortex intensities, vortex scales, and swarm sizes. By breaking the symmetry of the state-action map, MARL strategy leverages a non-intuitive mechanism that prevents agents from becoming trapped in separate vortices, thereby enhancing rendezvous success. Additionally, a heuristic strategy is extracted from the learned strategy and also outperforms the naive strategy. Furthermore, a theoretical analysis demonstrates that fluid deformation impedes the rendezvous process. Large finite-time Lyapunov exponents identify where fluid effects separate adjacent agents, suggesting that targets should be planned in weak-deformation regions. Our findings reveal the important role that agent-fluid interactions play in multi-agent tasks and highlight the MARL capability to explore swarm intelligence in complex flow environments.

21.
arXiv (CS.CL) 2026-06-19

LedgerAgent: Structured State for Policy-Adherent Tool-Calling Agents

Policy-adherent tool-calling agents in customer-service domains must maintain task states across turns while calling tools and obeying domain policies. Task states consist of relevant facts, identifiers, constraints, and conditions observed through user interaction and tool calls. In standard agents, task states are not represented separately. Observations, tool returns, and policy instructions are placed in the prompt, leaving agents to reconstruct the relevant states from the prompt each time they decide what to do next. This design makes state management implicit, creating two common failure modes. An agent may retrieve the right facts but later ground its decision in stale, missing, or incorrect information; and a syntactically valid tool call may still violate a domain policy that depends on the current task state. We introduce \textsc{LedgerAgent}, an inference-time method for tool-calling agents that maintains observed task states in a separate ledger and renders the states into the prompt. The ledger is also used to check state-dependent policy constraints before environment-changing tool calls are executed, blocking policy violations. Across four customer-service domains and a mixed panel of open- and closed-weight models, \textsc{LedgerAgent} improves average pass\textasciicircum{}k over a standard prompt-based tool-calling approach, with the largest gains under stricter multi-trial consistency metrics.

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

Bayesian Inference and Decision Audits for Public Archives of Frontier AI Evaluations

Authors:

arXiv:2606.17005v1 Announce Type: new Abstract: Public AI evaluations are often read as terminal leaderboards, yet the underlying evidence is a selective time series shaped by reporting rules, benchmark revisions, and missingness. Repeated public archives for LiveBench and Open LLM Leaderboard v2 serve as the primary longitudinal record; LMArena provides a preference stress test; and GAIA and tau-bench contribute limited agentic pilots. Together, these archives instantiate a Bayesian inference problem: under a fixed reporting convention, one constructed terminal-only example over $1{,}000$ systems is compatible with two pre-terminal histories, yielding times of $23.03$ or $75.13$ to reach within $0.05$ of the ceiling under the same terminal-tail model. In synthetic posterior comparisons, action-facing diagnostics differ across observation regimes. The candidate selection-aware frontier model fails synthetic recovery, objective-archive prediction, preference transfer, and uncertainty calibration; correspondingly, fixed audit gates reject its stronger claims. An archive-and-adjudication protocol reconstructs public evaluation histories, isolates a verified timing boundary, and falsifies unsupported frontier claims.

23.
arXiv (CS.AI) 2026-06-18

The Long Delay to Arithmetic Generalization: When Learned Representations Outrun Behavior

arXiv:2604.13082v2 Announce Type: replace-cross Abstract: Grokking in transformers trained on algorithmic tasks is characterized by a long delay between training-set fit and abrupt generalization, but the source of that delay remains poorly understood. In encoder-decoder arithmetic models, we argue that this delay reflects limited access to already learned structure rather than failure to acquire that structure in the first place. We study one-step Collatz prediction and find that the encoder organizes parity and residue structure within the first few thousand training steps, while output accuracy remains near chance for tens of thousands more. Causal interventions support the decoder bottleneck hypothesis. Transplanting a trained encoder into a fresh model accelerates grokking by 2.75 times, while transplanting a trained decoder actively hurts. Freezing a converged encoder and retraining only the decoder eliminates the plateau entirely and yields 97.6% accuracy, compared to 86.1% for joint training. What makes the decoder's job harder or easier depends on numeral representation. Across 15 bases, those whose factorization aligns with the Collatz map's arithmetic (e.g., base 24) reach 99.8% accuracy, while binary fails completely because its representations collapse and never recover. The choice of base acts as an inductive bias that controls how much local digit structure the decoder can exploit, producing large differences in learnability from the same underlying task.

24.
arXiv (CS.CL) 2026-06-11

Vector Quantized Latent Concepts: A Scalable Alternative to Clustering-Based Concept Discovery

Large language models (LLMs) encode rich semantic information in their hidden states, yet it remains difficult to understand what information these internal representations capture. Latent concepts extracted from hidden states offer a promising direction for interpreting LLMs, but existing clustering-based methods face a trade-off: hierarchical clustering produces coherent concepts but is limited to small datasets due to its quadratic memory cost, while K-Means scales efficiently but may yield less semantically coherent concepts. We propose Vector Quantized Latent Concept (VQLC), a discrete concept learning framework that learns a codebook of latent concepts on frozen hidden states. Across 12 dataset-model settings, VQLC stays close to K-Means in computational cost, scales better than hierarchical clustering, and remains competitive in faithfulness, with the clearest gains on decoder-only models. LLMs-based evaluation, qualitative analysis, and a Sparse Autoencoder (SAE) comparison demonstrate that the learned concepts are interpretable and task-relevant.

25.
Nature (Science) 2026-06-10

Mutation-dependent responses to sleep and exercise in clonal haematopoiesis

Clonal haematopoiesis (CH) activates inflammation and increases the risk of atherosclerosis1,2. Whether lifestyle alters CH clone expansion or the phenotypic programming of CH mutant cells, thereby affecting atherosclerosis, is unknown. Here, in humans and mice and across mutations in Jak2, Tet2, Trp53 and Dnmt3a, we demonstrate mutation-dependent responses to sleep and exercise in CH and show that mutant cells are uniquely sensitive to lifestyle. In two human datasets, moderate-to-vigorous physical activity was associated with lower prevalence of non-DNMT3A-driven CH. In atherogenic mice with Jak2V617F or Tet2 loss of function (LOF), but not Trp53 LOF or Dnmt3aR878H CH, uninterrupted sleep or exercise curtails clone expansion. In CH with the Jak2V617F mutation, sleep and exercise reduces clone expansion by selectively reprogramming mutant, but not cohabitant wild type, haematopoietic progenitor cells towards antiproliferative and metabolically healthy phenotypes by tempering bone marrow macrophage–haematopoietic progenitor cell IL-1β signalling. Sleep or exercise also lessens Jak2V617F-driven, Tet2 LOF-driven and Trp53 LOF-driven, but not Dnmt3aR878H-driven, atherosclerosis by locally reprogramming mutant vascular macrophages, independent of peripheral clone dynamics. In Jak2V617F, but not adjacent wild type, aortic macrophages, uninterrupted sleep blunts CLEC4E-dependent inflammasome activation, consequently diminishing lesions. Exercise, meanwhile, activates PAC1+ neurons in the locus coeruleus, raising the levels of peripheral noradrenaline, which signals through adrenergic receptor β2 (ADRβ2) whose expression is preserved by exercise in Jak2V617F, but not cohabitant wild type, aortic macrophages, selectively repressing their inflammatory programming and atherosclerosis. Our findings establish that healthy lifestyles gene-specifically diminish CH and selectively reprogram mutant haematopoietic progenitor cells and macrophages to maintain cardiovascular health. Sleep and exercise can slow clonal haematopoiesis and limit mutant cell-driven atherosclerosis.