Academic Intelligence · Curated Daily

探索全球前沿学术脉络

AcademicHub 汇聚顶级期刊与预印本平台的实时文献。定制您的专属科研雷达,利用大语言模型自动生成交叉领域文献分析简报。

01.
arXiv (CS.AI) 2026-06-16

Proximal Policy Optimization for Amortized Discrete Sampling

arXiv:2606.15793v1 Announce Type: cross Abstract: This paper explores policy gradient algorithms for training stochastic policies to sample from structured discrete probability distributions under the Generative Flow Network (GFlowNet) framework. Building on extensive theoretical connections between GFlowNets and entropy-regularized reinforcement learning, we derive equivalents of standard policy gradient algorithms for training GFlowNets, as well as experimentally explore their various methodological aspects, including baseline training and advantage estimation. Most importantly, our work is the first to derive and successfully apply proximal policy optimization to GFlowNets, showing its improved convergence speed and data efficiency compared to standard GFlowNet training objectives on benchmarks ranging from synthetic energies to molecular graph generation.

02.
medRxiv (Medicine) 2026-06-17

Treatment of Multi-Drug-Resistant Tuberculosis with Second-Line All-Oral Drugs in Ghana: Incidence of Adverse Events.

Introduction: The treatment of multidrug-resistant tuberculosis (MDR-TB) remains challenging due to the toxicity of second-line medications and suboptimal treatment outcomes. This study aimed to determine the incidence of adverse events and identify factors associated with these events in patients undergoing treatment for MDR-TB with second-line all-oral drugs in Ghana. Methods: This retrospective cohort study reviewed the medical records of 384 MDR-TB patients treated with second-line all-oral drugs at selected health facilities in Ghana, including the Greater Accra Regional Hospital, Eastern Regional Hospital, and Kumasi South Hospital. Data were extracted using the Kobo Collect tool, capturing patient demographics, baseline clinical and laboratory characteristics, treatment regimens, and adverse events. The study period spanned from 2020 to August 2024. Results: The study included a total of 384 MDR-TB patients, with a mean age of 45 years (SD = 15). The majority of patients were male (65.78%), and most were within the 45-64 years age group (33.85%), followed by those aged 25-44 years (31.25%). Regionally, the highest number of cases were reported from the Greater Accra Region (39.06%), followed by the Eastern Region (31.25%) and Kumasi South Hospital (29.69%). Approximately one in four patients (25%) presented with comorbidities, with HIV being the most common (19.5%). The most frequently reported adverse events were diarrhea (14%), dizziness (13.7%), and vomiting (12.3%). Most of these were mild to moderate in severity and tended to decrease as treatment progressed. Severe adverse events, such as leukopenia and acute kidney injury, were rare, occurring in less than 5% of patients. Over the course of treatment, gastrointestinal adverse events such as vomiting and nausea showed a significant decline, indicating possible patient adaptation or improved clinical management. Results from the multivariate Poisson regression analysis revealed that age and comorbidities were significant predictors of adverse events. Patients aged 65 years and above had a 56% lower risk of developing adverse events compared to younger patients (Adjusted Risk Ratio [aRR] = 0.44, 95% CI: 0.25-0.79, p = 0.005). Conversely, patients with comorbid conditions such as diabetes or hypertension were approximately 2.6 times more likely to experience adverse events compared to those without comorbidities (aRR = 2.65, 95% CI: 1.58-4.43, p < 0.001). The effect of sex was not statistically significant after adjustment (aRR = 1.03, 95% CI: 0.70-1.50, p = 0.86). At the end of the treatment period, 74.9% of patients achieved successful outcomes, including both those who were cured and those who completed treatment without being classified as cured. However, 25.1% had unsuccessful outcomes, which included treatment failure, relapse, or death. Conclusion: In conclusion, adverse events are common in the treatment of MDR-TB with second-line All-Oral drugs, with gastrointestinal adverse events being the most prevalent. These findings highlight the importance of monitoring and managing adverse events to optimize treatment outcomes for MDR-TB patients in Ghana.

03.
arXiv (math.PR) 2026-06-17

Analysis of the asymmetric shelf shuffle

arXiv:2606.18047v1 Announce Type: new Abstract: In an asymmetric shelf shuffle, a deck of $n$ cards is dealt sequentially from the bottom and assigned one of the $m$ shelves uniformly at random. The card is placed at the top of the assigned shelf with probability $p$, and at the bottom of the assigned shelf with probability $(1-p)$. Analysis of the shelf shuffle has gained much attention recently, and the case $p=1/2$ was first treated by Diaconis–Fulman–Holmes [Ann. Appl. Prob. 23 (2013), no. 4, 1692–1720]. In this paper, we extend the analysis of the shelf shuffle to general $p\in (0, 1)$. In particular, we study the distribution of cycles, cycle lengths, number of descents, number of valleys, number of inversions, and the RSK shape of a permutation obtained from an asymmetric shelf shuffle. Our results extend the analysis of Diaconis–Fulman–Holmes to arbitrary $p$. Furthermore, our analysis of the distribution of descents and inversions is new even for $p=1/2$.

04.
arXiv (CS.CV) 2026-06-16

Multi-Task Tennis Stroke Biomechanics Analysis Using MediaPipe Pose

We built a multi-task pipeline for tennis stroke biomechanics from plain RGB video. On top of pose-based stroke recognition, it adds two new tasks, predicting shot direction and grading posture quality, plus a rule-based feedback layer that suggests coaching tips. Strokes are found automatically using a weighted joint velocity score, s(t) = 0.5 v_wrist + 0.3 m_elbow + 0.2 m_shoulder, removing the need for manual annotation. Pose comes from MediaPipe Pose Landmarker (33 landmarks, metric world coordinates), with each stroke turned into a 30-frame by 39-feature sequence for TennisTransformerGPU, a compact 564,103-parameter transformer (4 layers, 4 heads, d=128) with three parallel output heads. Trained on 1,281 labeled strokes from 7 pros and 1 amateur across 11 videos, it hits 83.7% stroke-type accuracy, 61.9% on direction, and 62.6% on posture under a random 80/20 split. The interesting test is cross-player: train on pros, evaluate on the amateur. Stroke type barely budges, 82.9%, a 0.8% drop. Direction prediction does not transfer; it just falls back to the majority class. An ablation shows why world coordinates matter so much here: switching to image-space landmarks tanks cross-player stroke-type accuracy from 83% to 47% and direction from 68% to 21%. Everything runs on Kaggle's free T4 GPU tier and is fully reproducible.

05.
arXiv (CS.AI) 2026-06-15

Where's the Plan? Locating Latent Planning in Language Models with Lightweight Mechanistic Interventions

arXiv:2605.07984v2 Announce Type: replace-cross Abstract: We study planning site formation in language models – where internal representations of structurally-constrained future tokens form during the forward pass, and whether they causally drive generation. Using rhyming-couplet completion as a clean test of forward-looking constraint, we apply two lightweight methods (linear probing and activation patching) across Qwen3, Gemma-3, and Llama-3 at more than ten scales. Probing shows that future-rhyme information is linearly decodable at the line boundary, with signal that strengthens with scale in all three families. Activation patching reveals that only Gemma-3-27B causally relies on this encoding, exhibiting a handoff in which the causal driver migrates from the rhyme word to the line boundary around layer 30. Every other model we test conditions on the rhyme word throughout generation, with near-zero causal effect at the line boundary despite strong probe signal. We localize the Gemma-3-27B handoff to five attention heads through two-stage path patching that recover ~90% of the rhyme-routing capacity at the newline.

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

One Polluted Page Is Enough: Evaluating Web Content Pollution in Generative Recommenders

Search-augmented LLMs increasingly mediate everyday consumer recommendations by retrieving live web content. This creates a new risk: generative recommenders may consume polluted web content, such as fake reviews and promotional pages crafted to mislead recommendations. We ask: to what extent do search-augmented LLMs become unwitting promoters of fake products when consuming polluted retrieval results? To answer this, we introduce FORGE (Fake Online Recommendations in Generative Environments), a benchmark for measuring fake-product promotion under controlled web-content pollution. Given an upstream search result, FORGE locally rewrites real products in retrieved web pages into fake ones to simulate web-content pollution, and measures how often the LLM recommends the fake product. FORGE covers 225 real-world products across 15 categories and 5 consumer scenarios. Across 12 commercial and open-weights LLMs, all models are vulnerable: a single polluted page yields fooled rates of up to 27%, while the full top-3 replacement raises this to 73.8%. Vulnerability varies substantially across categories, increasing when models lack stable prior knowledge of the relevant products. Reasoning does not mitigate this vulnerability; instead, it often generates spurious social proof to justify false recommendations. We evaluate three defenses: skepticism prompting and consensus filtering (over model priors or cross-document evidence). Skepticism can exacerbate vulnerability, much like reasoning, while filtering risks suppressing legitimate products. We release FORGE at https://github.com/leoluolol/forge-benchmark.

07.
arXiv (CS.CV) 2026-06-16

Lesion-DDPM: Lesion-Enhanced 3D Diffusion for MS MRI Synthesis

3D FLAIR MRI is widely recommended as one of the standard MRI sequences for brain imaging in multiple sclerosis (MS), but publicly available MS datasets remain relatively small and vary across scanners, acquisition protocols, and lesion patterns. This scarcity and variability hinder the development of robust neuroimaging machine learning models and are particularly challenging for generative models that aim to synthesize images while preserving small, sparse lesions. We propose Lesion-DDPM, a 3D conditional diffusion framework for lesion-aware FLAIR synthesis that incorporates multi-level anatomical mask injection together with a lesion-weighted reconstruction loss to emphasize lesion voxels while maintaining global brain structure. Using a curated subset of the MSLesSeg dataset, we compare Lesion-DDPM with representative state-of-the-art GAN- and diffusion-based models, assessing both image-generation metrics and downstream 3D U-Net segmentation. In our experiments, Lesion-DDPM achieved the lowest lesion-region reconstruction error among all methods. In a downstream 3D U-Net lesion segmentation task, a model trained only on Lesion-DDPM-generated scans and evaluated on real MRIs reached a Dice score of 0.616 compared with 0.569 for the best competing synthetic dataset. When Lesion-DDPM images were added to the real training set, the Dice score further increased to 0.685.

08.
arXiv (CS.CL) 2026-06-12

KCSAT-ML: Probing Reasoning Models with Nationwide-Cohort Human Difficulty

Math reasoning benchmarks have proliferated, yet most lack a per-item difficulty signal grounded in actual human performance. We introduce KCSAT-ML, a decade (2014-2025) of Korean College Scholastic Ability Test (KCSAT; Suneung) mathematics: 664 problems with a 339-item core set carrying official per-item error rates from nationwide cohorts of hundreds of thousands of examinees. We pair the benchmark with Difficulty-aligned Reasoning Gain (DRG): a score-orthogonal metric that asks whether a model's mistakes concentrate on the items humans found hard, or on items humans found easy. Together they expose, across a wide range of VLMs (and LLMs via OCR), three patterns: (i) low-budget accuracy collapses on the high-human-error tail at every model size; (ii) test-time scaling (TTS) raises token use roughly linearly with cohort error rate, while accuracy gains follow a non-monotonic curve; (iii) within a single family, TTS flips between anti-scaling on the hardest items and overthinking on easier ones – two faces of the same alignment failure. On DRG, models with near-identical accuracy can sit at near-opposite values: one model gets wrong what humans also find hard, while another solves the hardest items yet fails on items humans find easy – a contrast that aggregate accuracy hides. Our code and dataset builder will be open-sourced at https://github.com/naver-ai/KCSAT-ML.

09.
arXiv (CS.AI) 2026-06-18

Augmenting Dysarthric Speech Severity Assessment with MOS Supervision

arXiv:2606.18645v1 Announce Type: cross Abstract: Dysarthria is a speech disorder marked by reduced intelligibility and communicative effectiveness. Automatic utterance-level assessment of dysarthric speech can support scalable speech monitoring and therapy-related analysis. Yet training such systems is bottlenecked by the scarcity of clinically annotated dysarthric speech. This work proposes to augment dysarthric speech assessment using data from speech synthesis evaluations, specifically human-annotated utterances with Mean Opinion Score (MOS) labels from the QualiSpeech corpus. Experiments show that fine-tuning on speech synthesis assessment data consistently improves performance on both intelligibility and naturalness prediction, while joint training yields gains primarily on naturalness. These results suggest that synthesis artifacts and dysarthric speech share perceptual commonalities, and speech synthesis evaluation corpora offer a practical augmentation source that reduces reliance on scarce clinical annotations.

10.
arXiv (quant-ph) 2026-06-19

On the significance of Wigner's Friend in contexts beyond quantum foundations

arXiv:2402.08727v3 Announce Type: replace Abstract: There has been a surge of recent interest in the Wigner's Friend paradox, sparking several novel thought experiments and no-go theorems. The main narrative has been that Wigner's Friend highlights a counterintuitive feature that is unique to quantum theory, and which is closely related to the quantum measurement problem. Here, we challenge this view. We argue that the gist of the Wigner's Friend paradox can be reproduced without assuming quantum physics, and that it underlies a much broader class of enigmas in the foundations of physics and philosophy. To show this, we first consider several recently proposed Extended Wigner's Friend scenarios, and demonstrate that some of their implications for the absoluteness of observations can be reproduced by classical thought experiments that involve the duplication of agents. Crucially, some of these classical scenarios are technologically much easier to implement than their quantum counterparts. Then, we argue that the essential structural ingredient of all these scenarios is a feature that we call "Restriction A": that a physical theory cannot give us a probabilistic description of the observations of all agents. Finally, we argue that this difficulty is at the core of other puzzles in the foundations of physics and philosophy, and demonstrate this explicitly for cosmology's Boltzmann brain problem. Our analysis suggests that Wigner's Friend should be studied in a larger context, addressing a frontier of human knowledge beyond quantum foundations: to obtain reliable predictions for experiments in which these predictions can be privately but not intersubjectively verified.

11.
arXiv (quant-ph) 2026-06-15

Dose-efficient Quantum Phase Estimation in Lossy Optical Interferometry

arXiv:2606.14254v1 Announce Type: new Abstract: Optical interferometry is a cornerstone technique for precise phase measurements across various fields. In many applications, for example, biological imaging, it often necessitates stringent limits on light intensity to prevent adverse effects on light-sensitive samples, a condition known as dose-limited regimes. Maximizing the precision per dose is therefore crucial. In quantum metrology, quantum correlations enable high precision in phase estimation while adhering to dose constraints. Nevertheless, photon loss, including absorption by a sample, substantially diminishes the benefits of quantum enhancement in interferometry. In this work, we experimentally investigate a dose-efficient approach to quantum phase estimation using sequential strategies in the presence of loss. Performance of sequential strategies with and without control is evaluated through quantum Fisher information (QFI) per dose. Experimental results show that both sequential strategies exceed the classical limit and outperform the parallel strategy using unbalanced N00N states. Notably, the control-enhanced sequential strategy attains superior QFI per dose, approaching the quantum limit. These results highlight the promise of sequential strategy for imaging and sensing in resource-constrained scenarios, marking a significant step toward practical and efficient quantum metrology in lossy environments.

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

MapSatisfyBench: Benchmarking Satisfaction-Aware Map Agents through Behavior-Grounded Implicit Decision Factors

arXiv:2606.17453v1 Announce Type: new Abstract: Large language model agents are increasingly integrated into map services. Since map services are embedded in everyday-life scenarios rather than professional task settings, users often express their needs informally, resulting in underspecified queries with many unspoken needs, namely, implicit decision factors that are critical for user satisfaction. Although clarification is an effective way to mitigate this issue, it increases user burden in daily interaction, and a capable agent should first proactively recover such factors from available information sources. However, evaluating this ability is challenging. The first challenge is to determine which implicit decision factors are suitable for evaluation. A factor is evaluable only if it affects user acceptance and can be recovered from information available to the agent before it responds. Second, user satisfaction cannot be reliably represented by a single reference answer, requiring a benchmark that converts satisfaction-relevant factors into objective and quantifiable evaluation targets. To address these challenges, we propose a restore-identify-filter framework that reconstructs complete user needs from behavior-chain evidence, identifies implicit decision factors, and retains only those supported by pre-query evidence. Building on this methodology, we construct MapSatisfyBench from large-scale, real-world anonymized user data and annotate ground truth from five dimensions and enables full-chain evaluation of satisfaction-aware map agents. Experiments show that current agents generally perform well on explicit task completion, but remain limited in satisfying implicit decision factors and proactively acquiring the evidence needed for satisfaction-aware decisions. These findings establish MapSatisfyBench as a benchmark for shifting map-agent evaluation from task completion toward satisfaction-aware spatial decision making.

13.
medRxiv (Medicine) 2026-06-11

Beyond External Load: Integrative Immune Monitoring Reveals Injury-Predictive Signals in the Athlete's Internal State

Abstract (already in the PDF; paste if a box is required): Injury risk prediction in elite football relies almost exclusively on external load metrics derived from GPS tracking, overlooking the molecular state of the athlete. We monitored 26 male players from FC Barcelona's first team across the 2025 calendar year, integrating GPS-derived training load with longitudinal blood-based immune monitoring (systemic inflammation and TCR-derived immune age). Immune age acceleration and inflammation were elevated in the 14 days preceding musculoskeletal injuries. A logistic regression model combining external load, inflammation, immune age acceleration, and career injury history reached an overall AUC of 0.678 and a mean per-player AUC of 0.754 (SD 0.146), improving on a GPS-only baseline of 0.541. Applied to 2026 data, the frozen model ranked players who later sustained non-contact musculoskeletal injuries high in the risk distribution. Together, our data suggest multimodal immune monitoring in elite football to reveal the athlete's internal physiological state, which carries injury-relevant information that external load alone does not capture.

14.
arXiv (math.PR) 2026-06-18

Metastability for the Curie-Weiss-Potts model with unbounded random interactions

arXiv:2505.11260v2 Announce Type: replace Abstract: We analyse the metastable behaviour of the disordered Curie–Weiss–Potts (DCWP) model subject to a Glauber dynamics. The model is a randomly disordered version of the mean-field $q$-spin Potts model (CWP), where the interaction coefficients between spins are general independent random variables. These random variables are chosen to have fixed mean (for simplicity taken to be $1$) and well defined cumulant generating function, with a fixed distribution not depending on the number of particles. The system evolves as a discrete-time Markov chain with single spin flip Metropolis dynamics at finite inverse temperature $\beta$. We provide a comparison of the metastable behaviour of the CWP and DCWP models, when $N \to \infty$. First, we establish the metastability of the CWP model and, using this result, prove metastability for the DCWP model (with high probability). We then determine the ratio between the metastable transition time for the DCWP model and the corresponding time for the CWP model. Specifically, we derive the asymptotic tail behavior and moments of this ratio. Our proof combines the potential-theoretic approach to metastability with concentration of measure techniques, the latter adapted to our specific context.

15.
arXiv (quant-ph) 2026-06-11

Linear Combination of Hamiltonian Simulation with Commutator Scaling

arXiv:2606.11475v1 Announce Type: new Abstract: The Linear Combination of Hamiltonian Simulation (LCHS) framework simulates dissipative linear dynamics by representing time evolution as an integral over unitary operators, which is discretized by quadrature and implemented via Hamiltonian simulation. While existing analyses achieve near-optimal scaling in time and precision using norm-based quantities of the dissipative generator, we show that implementing the Hamiltonian simulation steps with Multi-Product Formulas (MPFs) yields commutator-sensitive error and complexity bounds. We demonstrate that the quadrature rule affects not only discretization error but also commutator structure and query complexity. This dependence is quantified through post-quadrature analysis for abstract MPF error profiles and for general time-independent and local Hamiltonians using known commutator-sensitive MPF error estimates. We compare uniform trapezoidal and free-scale sinh–sinh quadrature, showing improved quadrature-cardinality scaling for the latter, and illustrate the framework with applications to fractional diffusion, advection–diffusion, and open quantum systems.

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

SpecAlign: Efficient Specification-Grounded Alignment of Large Language Models via Synthetic Data

arXiv:2606.16276v1 Announce Type: new Abstract: As large language models (LLMs) are increasingly deployed in real-world applications, alignment is no longer governed by a single universal notion of safety or helpfulness, but instead by provider- or application-specific model specifications. These specifications are typically long, structured, and frequently updated, yet existing alignment pipelines lack a systematic mechanism to operationalize them as training signals. In this paper, we propose specification-grounded alignment, a new alignment paradigm that treats provider-authored model specifications as the primary alignment target rather than abstract principles or static benchmarks. To instantiate this paradigm, we introduce SpecAlign, a framework that synthesizes alignment data directly from specification documents. SpecAlign combines structured rule annotation, controllable specification instantiation, and multi-agent adversarial data synthesis to generate fine-grained, boundary-aware preference pairs that capture both compliant behaviors and meaningful specification violations. Experiments across multiple model specifications and backbone models demonstrate that training with SpecAlign consistently improves rule compliance while preserving general capabilities and avoiding over-conservative behavior. These results suggest that grounding alignment in explicit model specifications enables rapid, precise, and scalable adaptation of LLM behavior to evolving policy requirements.

17.
bioRxiv (Bioinfo) 2026-06-08

TRACEY: an updated resource for SNARE protein domain annotation with improved HMMs and expanded sequence coverage

Motivation: SNARE proteins catalyse membrane fusion across the eukaryotic endomembrane system, from synaptic vesicle exocytosis to intracellular trafficking, endosomal and vacuolar transport, and autophagy, and their accurate domain annotation depends on the quality of profile models and the sequence diversity behind them. The original SNARE domain classification predates the recent expansion of eukaryotic sequence data, leaving its HMM profiles and subgroup coverage unable to resolve divergent and lineage-specific paralogs. Results: We present an updated release of TRACEY built on a resynchronized, non-redundant collection of 18,915 curated SNARE proteins spanning 1,188 species, together with a consolidated set of 83 HMM profiles, including 43 models for newly defined subgroups, reconstructed through an iterative, mixture-model-driven procedure. In direct comparison with the legacy models, at least ~75% of sequences in every overlapping group scored better with the new HMMs, indicating systematic gains in domain detection. A redesigned web interface adds multiparameter querying, FASTA download, and direct scanning of user-submitted sequences against the curated profiles. Availability and implementation: TRACEY is freely available at https://tracey.unil.ch.

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

Direction-Conditioned Policies via Compositional Subgoal Scoring for Online Goal-Conditioned Reinforcement Learning

arXiv:2606.16515v1 Announce Type: cross Abstract: Hamilton-Jacobi-Bellman theory implies that the optimal goal-conditioned action depends on the goal only through the gradient of the goal-reaching distance at the current state, yet standard online GCRL still conditions the actor on the raw goal – a signal that is geometrically uninformative when the goal is far from the data distribution. We propose Direction-Conditioned Policies (DCP), a fully online method that decomposes goal-reaching into two components sharing one InfoNCE representation $\psi$: a subgoal-scoring step that selects a visited state $z_t$ aligned with the final goal $g$ in $\psi_g$, and a direction-conditioned actor that consumes the unit direction $d_t$ and magnitude $r_t$ from $\psi(s_t)$ to $\psi(z_t)$. The two components train jointly, factor cleanly at deployment (subgoal scoring is removed, while direction conditioning remains with $g$ in place of $z_t$), and admit independent modification at the same $(d_t,r_t)$ interface. We prove three results. First, direction sufficiency under HJB: the optimal action under control-affine dynamics depends on the goal only through the value gradient. Second, a quantitative bound showing that, under mild conditions on the learned representation and assuming the scoring rule returns an on-path $z_t$, the actor's conditioning input at training and at deployment coincide up to representation error and geodesic slack. Third, a controllable-subspace characterization of when directional conditioning fails. Across nine environments, DCP improves over Contrastive RL on most final metrics, with the largest gains on manipulation and obstacle-interaction tasks; a qualitative analysis of the learned $\psi$-distance landscape shows the contrastive representation behaves as an online quasimetric encoding environment topology, and the single failure case (AntSoccer) localizes to a learned-gradient pathology that the theory anticipates.

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

VIMPO: Value-Implicit Policy Optimization for LLMs

arXiv:2606.20008v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards has become a central tool for improving the reasoning ability of large language models, but current methods face a trade-off between simplicity and credit assignment. Group-relative methods such as GRPO avoid training a critic, but typically assign a trajectory-level advantage to every token. Actor-critic methods provide denser learning signals, but require a learned value function with its own training instability. We introduce VIMPO, a critic-free policy optimization method that derives a policy-implied value function from the optimality conditions of KL-regularized reinforcement learning. For autoregressive generation, the resulting value recurrence can be written in terms of policy-reference log-ratios and anchored by the terminal condition that no future reward remains at the end of a trajectory. This gives a simple value loss that incorporates outcome-level verifiable rewards without training a critic. The same derivation also yields a critic-free actor advantage, allowing VIMPO to separate reward incorporation through the value loss from policy improvement through a PPO-style actor update. On mathematical RLVR benchmarks, VIMPO improves over GRPO across MATH-500, AIME 2024, AIME 2025, and OlympiadBench, with especially larger gains on competition-style evaluations. Under noisy rewards, VIMPO retains a consistent advantage over GRPO, suggesting that policy-implied value optimization can provide finer credit assignment while preserving the practical simplicity of critic-free training.

20.
arXiv (CS.AI) 2026-06-12

Functional Cache Grafting: Robust and Rapid Code-Policy Synthesis for Embodied Agents

arXiv:2606.13097v1 Announce Type: cross Abstract: Code-writing large language models (CodeLLMs) generate executable code policies for embodied agents by translating natural language goals and environmental constraints into structured control programs. However, policy generation in open-domain embodied environments suffers from two fundamental limitations: (i) delayed decoding caused by repetitive prefill computation over long prompts, and (ii) limited robustness due to fully generative decoding, which often produces API mismatches, missing safety guards, and unstable control logic. To address these limitations, we present FCGraft, a Functional Cache Grafting framework. FCGraft maintains a library of function-level validated code skeletons and their associated prompt-level Transformer key-value (KV) caches, and synthesizes new policies by retrieving relevant functions and grafting their KV caches when a new task is provided. Given retrieved function caches, FCGraft performs cache grafting via stitching, which composes cached function segments into a composite policy, and patching, which locally adapts only the necessary code regions to satisfy task-specific parameters and constraints with minimal additional decoding. By eliminating redundant prefill computation, this approach reduces generation latency, while reusing validated control structures improves robustness over prompt-level caching methods RAGCache, achieving 18.31% higher task success rate and 2.3x faster policy synthesis.

21.
arXiv (CS.AI) 2026-06-15

AdaTKG: Adaptive Memory for Temporal Knowledge Graph Reasoning

arXiv:2605.07121v2 Announce Type: replace Abstract: Temporal knowledge graphs (TKGs) represent time-stamped relational facts and support a wide range of reasoning tasks over evolving events. However, existing methods produce entity representations that are static at the entity level, in that each representation is a function of learned parameters only and retains no trace of the interactions in which the entity has participated. In this paper, we depart from this static view and propose that each entity be modeled as an adaptive process whose representation is refined every time the entity participates in a fact. To this end, we propose AdaTKG, which maintains a per-entity memory that is updated with every observed interaction, with the memory accumulating online and predictions improving as more interactions arrive. Specifically, we instantiate the memory update as a learnable exponential moving average governed by a single shared scalar instead of using learnable parameters for each entity, enabling AdaTKG to handle entities unseen during training. Extensive experiments confirm consistent gains over TKG baselines, demonstrating the effectiveness of adaptive memory. Code is available at: https://github.com/seunghan96/AdaTKG

22.
arXiv (CS.CL) 2026-06-12

From Benchmarks to Skills: Low-Rank Factors for LLM Evaluation

Current evaluations of large language models (LLMs) rely heavily on a growing collection of benchmarks and on aggregate benchmark scores, yet it remains unclear what this comparison actually captures, and what these scores reveal about models' underlying capabilities. Here, we propose a new paradigm for LLM evaluation, by asking whether benchmark performance reflects many independent abilities, or rather relies on a small number of shared dimensions. To answer this, we apply Factor Analysis (FA) to a massive performance matrix of LLMs versus benchmarks \((60\times44)\) revealing an intrinsically low-rank structure of that matrix. That is, a small number of latent factors captures most of the structure in the full task space. This low-rank geometry reveals substantial redundancy across existing tasks and explains why many benchmarks appear to be measuring overlapping abilities. We further show that these latent factors correspond to coherent, skill-like, dimensions of LLM behavior. Leveraging this latent skill-space, we deliver three practical tools for LLM evaluation and downstream users: (i)~identifying redundant tasks, (ii)~profiling new models using a small subset of tasks, and (iii)~selecting models aligned with desired skill profiles. Our method provides a solid alternative to the de-facto standard of a single aggregate score, and establishes an interpretable and practical framework for understanding and benchmarking LLM core capabilities.

23.
arXiv (CS.CL) 2026-06-11

NightFeats @ MMU-RAGent NeurIPS 2025: A Context-Optimized Multi-Agent RAG System for the Text-to-Text Track

We present NightFeats, a structured multi-agent retrieval-augmented generation (RAG) system submitted to the MMU-RAGent competition at NeurIPS 2025, where it was awarded Best Dynamic Evaluation in the text-to-text track. Rather than targeting benchmark maximization, this work proposes a principled pipeline that decomposes knowledge synthesis into three coordinated phases: retrieval, curation, and composition, each governed by explicit intermediate representations and handoff contracts. Inspired by Agentic Context Engineering (ACE), the system introduces temporal-semantic reranking, bounded contradiction reconciliation, and citation-preserving composition as core architectural primitives. Competition results show that NightFeats surpasses proprietary baselines including Claude-SonnetV2 and Nova-Pro on LLM-as-a-Judge and Human Likert evaluations, confirming that architectural transparency and verifiable evidence grounding are better aligned with human preferences than systems optimizing narrowly for automatic similarity metrics.

24.
arXiv (CS.AI) 2026-06-17

Memory as a Wasting Asset: Pricing Flash Endurance for Embodied Agents, and the Limits of Doing So

arXiv:2606.18144v1 Announce Type: new Abstract: A robot's flash endurance is a non-renewable stock: every persisted write spends one of a few thousand program/erase cycles and never refills, yet no fielded robot memory system prices which memories are worth an erase cycle. We treat embodied memory as depreciating capital and price that stock with a single endurance shadow price $\eta$, which makes cost-minimizing placement across a RAM / on-board NVM / cloud hierarchy a threshold in a wear-augmented per-byte index. The index is cost-optimal whatever the sign of the value-write association $\chi$; only when $\chi > 0$ does the optimum turn non-monotone, sending a robot's most valuable memories off its flash. The pivot is thus empirical, and we measure $\chi$ on real robot logs at a pre-specified gate: its sign is a property of the deployment regime – positive on recurrent long-horizon manipulation ($\hat{\chi} \approx +1.0 \times 10^{-3}$, replicated at full power), null on a shorter-horizon suite, and negative on non-recurrent teleoperation. Two boundaries scope the result. The endurance budget is dormant on premium 3,000-P/E TLC at datasheet prices and binding on the commodity QLC/eMMC ($\sim$1,000 P/E) that cheaper edge robots run. And where it binds, a learned wear-aware controller only ties price-based routing on task value, because realized value is tier-invariant across RAM, NVM, and cloud: the rent governs device lifetime and cost, not task performance. Whether wear-aware placement improves task value remains open – $\chi$ is measured against a value proxy, and the non-monotone optimum, while proven, is not yet observed in data.

25.
arXiv (CS.AI) 2026-06-18

TxBench-PP: Analyzing AI Agent Performance on Small-Molecule Preclinical Pharmacology

arXiv:2606.19245v1 Announce Type: new Abstract: Artificial intelligence (AI) agents promise to accelerate drug discovery by compressing interpretation and decision-making loops, but practical deployment requires trusted evaluation on realistic program decisions. We introduce TherapeuticsBench Preclinical Pharmacology (TxBench-PP), a verifiable benchmark for small-molecule preclinical pharmacology and the first focused slice of a broader TherapeuticsBench effort across drug-discovery stages and therapeutic modalities. TxBench-PP tests whether agents can recover accurate conclusions from real-world assay data rather than memorized facts from literature. The benchmark contains 100 evaluations indexed by program stage, assay type, and task structure, spanning mechanism-of-action (MoA) and pharmacodynamic (PD) reasoning, compound-target engagement, causal target validation, developability and safety, and translational efficacy. Agents receive realistic workflow snapshots, inspect files in a coding environment, and return structured answers graded deterministically. Across 16 model-harness configurations, comprising 11 models and 4,800 trajectories, no system reliably recovered preclinical pharmacology decisions. The strongest configuration, Claude Opus 4.8 / Pi, passed 59.3\% of endpoint attempts (178/300; 95\% CI, 51.1-67.6), followed by GPT-5.5 / Pi at 55.3\% (166/300; 47.0-63.6).