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

Twisted (co)homology of non-orientable Weyl semimetals

arXiv:2511.22303v3 Announce Type: replace-cross Abstract: The quasi-particle excitations in Weyl semimetals, known as Weyl fermions, are usually forced to emerge in charge-conjugate pairs by the Nielsen–Ninomiya theorem. When the Brillouin zone is non-orientable, this constraint is replaced by a $\mathbb{Z}_2$ charge cancellation, as a result of the chirality becoming ill-defined on such manifolds; this results in configurations with seemingly non-zero total chirality. Here, we set out to explain this behaviour from a purely topological perspective, and provide a classification of non-orientable Weyl semimetal topology in terms of exact sequences of twisted (co)homology groups. This leads to several discoveries of direct physical importance: in particular, we recover the $\mathbb{Z}_2$ charge cancellation in a coordinate-independent way, allowing meaningful limits to be set on its physical interpretation. A detailed discussion is provided on a specific Klein bottle-like topology induced by a momentum-space glide symmetry, including a full review of the insulating and semimetallic invariants of the system and a classification of the surface states on the non-orientable boundary. Beyond this, we provide a complete survey of all possible non-orientable Brillouin zones and their associated invariants, and extend our formalism into the realm of non-Hermitian topological physics and inversion-symmetric Weyl semimetals. Our work exemplifies the vast potential of fundamental mathematical descriptions to not only aid the corresponding physical intuition, but also predict novel and hitherto overlooked phenomena of great relevance throughout the physics research forefront.

02.
PLOS Medicine 2026-05-12

Social contact patterns in the United Kingdom following the COVID-19 pandemic: The Reconnect cross-sectional survey

by Lucy Goodfellow, Billy J. Quilty, Kevin van Zandvoort, W. John Edmunds Background Close-contact and respiratory infectious diseases are spread through social interactions. Measuring these interactions has transformed our ability to understand transmission and control these infections. Social contact patterns were disrupted during the COVID-19 pandemic and have been affected by wider demographic, cultural, and workplace changes since then. Methods and findings To estimate post-pandemic social contact patterns in the United Kingdom, we conducted a cross-sectional social contact survey from November 2024 to March 2025 on a nationally representative sample of participants. Interactions were captured by age, gender, and across socioeconomic status (SES) and ethnic groups. We calculated the mean number of daily contacts and contact matrices, stratified by variables of interest, using a negative binomial regression model weighted by age, gender, ethnic group, and weekday/weekend. 13,238 participants were recruited, 3,019 of whom were aged under 18 years old; survey response rates were 36% and 27% for adults and children, respectively. The mean number of daily contacts was 9.1 (95% confidence interval (CI): 8.7, 9.5); this figure was 13.8 (95% CI: 12.8, 14.9) for children, and 7.8 (95% CI: 7.4, 8.2) for adults. Higher numbers of contacts were positively associated with employment, household income, and educational qualifications held. Contact matrices showed high levels of age-assortativity, as well as inter-generational contacts in the home. Contacts were assortative between ethnic groups and SES in all settings; this effect was strongest between ethnic groups in the home, and between SES in the workplace. We constructed socially-stratified next-generation matrices for a novel respiratory pathogen, projecting that the majority White ethnic group would account for the largest share of new infections (76.7% (95% CI: 75.5, 77.9) of cases), but that per-capita infection risk would disproportionately affect minority ethnic groups, with the risk for the Black population being 2.27 (95% CI: 2.06, 2.51) times that of the White population. This study may be limited by the inherent recall biases and reporting fatigue involved with self-reporting contacts. Conclusions This study provides crucial data to inform post-pandemic mathematical models of infectious disease transmission, and allows ethnicity and SES to be incorporated in such models.

03.
bioRxiv (Bioinfo) 2026-06-21

Antibody-Antigen Affinity Prediction with Chain-Aware Protein Language Modeling

Motivation: Antibody-antigen affinity determines which antibodies advance in therapeutic discovery, repertoire analysis and affinity maturation, but experimental measurements are sparse relative to the scale of sequence libraries. Structure-based predictors can exploit interface geometry when reliable complexes are available, yet early discovery often requires ranking many heavy-light chain pairs against antigens for which no complex structure exists. Existing sequence-based models are scalable, but frequently compress heavy and light chains into a single antibody representation or concatenate antibody and antigen features obscuring the chain-specific and epitope-specific signals that drive binding. Results: We present AbAffinity, a sequence-only chain-aware three-stream architecture that maintains heavy chain, light chain and antigen as distinct streams. It integrates frozen ESM-2 embeddings with heavy-chain CDR-focused pooling, heavy-light self-attention, adaptive fusion gating and gated cross-attention, training only a compact interaction module. On the SAAINT-DB benchmark, AbAffinity achieves strong predictive performance under ten-fold cross-validation and maintains robust accuracy on novel antigens. It consistently outperforms recent sequence-based models across external benchmarks including SAbDab, AB-Bind and SKEMPI 2.0. Ablation studies highlight the contributions of chain-specific representations, CDR-focused pooling and the gated interaction pathway. Integrated Gradients attributions recover known paratope and epitope residues at structurally validated interfaces. AbAffinity provides a lightweight, explainable sequence-first framework for antibody triage and prioritisation when structural information is limited or unavailable.

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

Contrastive Learning for Seismic Horizon Tracking with Domain-Specific Priors

Unsupervised 3D seismic horizon tracking faces a key limitation: signal-based propagators provide accurate trace-level alignment but often fail near faults, whereas texture-driven deep models are more robust to discontinuities, typically at the cost of labeled data requirements and reduced trace-level precision. We propose a self-supervised fusion of both paradigms in which signal-derived local horizon correspondences act as domain-specific priors to train a texture-based deep learning model. Specifically, we estimate reliable trace-to-trace flows from reflector slopes and use them to form positive pairs in a contrastive objective, while restricting training to high-confidence neighborhoods, optionally augmented with a fault mask. The objective is not to infer ambiguous correspondences close to discontinuities, but to preserve horizon identity across them. As a result, the network learns voxel-wise embeddings that preserve local signal continuity while enabling horizon propagation beyond discontinuities through similarity search. Experiments on the public F3 dataset and a faulted synthetic dataset achieve lower mean absolute error (MAE) than unsupervised baselines and competitive performance against a semi-supervised method using a single labeled slice.

05.
arXiv (quant-ph) 2026-06-17

A Lindbladian for holographic Brownian motion

Authors:

arXiv:2606.17909v1 Announce Type: cross Abstract: We derive a Lindbladian description of holographic Brownian motion in the high-temperature regime. Starting from the influence functional for a trailing string endpoint, we identify the corresponding quantum master equation and prove that it is completely positive and trace-preserving. We determine the coefficients of the Lindbladian explicitly for two holographic backgrounds: the BTZ black hole and the AdS$_5$ black brane, restricting in the latter case to the endpoint fluctuation along the $x^1$-direction. We then analyze the time evolution of phase-space moments, energy relaxation, and steady states.

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

Decision-Aware Memory Cards: Counterfactual-Inspired Context Selection and Compression for Tool-Using LLM Agents

arXiv:2606.08151v2 Announce Type: replace Abstract: Modern large language model (LLM) agents do not simply need longer contexts; they need decision-relevant evidence at the moment of action. We study decision-aware context selection: ranking retrieved files, tests, traces, rules, and memories by their expected effect on an agent's next action rather than by semantic similarity alone. We present the Counterfactual-Inspired Context Layer (CICL), which builds an instance context graph, estimates decision-oriented utility for candidate units, and compresses selected evidence into typed memory cards. The same schema can be instantiated with hosted LLM judges, local surrogates, or lightweight rankers, making the selection protocol auditable across model choices. On 50 SWE-bench Verified file-retrieval instances, Qwen3.6-Plus reranking of BM25 top-50 candidates improves hit@1 from 0.58 to 0.78 and MRR@10 from 0.634 to 0.790, with all 2,500 judgments parseable. Controlled diagnostics show that CICL identifies action-critical evidence: removing the top-utility semantic unit reduces F1 from 0.245 to 0.000. In selected-then-compressed mode, memory cards save 44.93 tokens per query while preserving selected evidence. CICL provides a practical layer for measuring, ranking, and compressing decision-critical context for tool-using agents. Code is available at https://github.com/stephen-guan-researcher/CICL.

07.
arXiv (CS.CV) 2026-06-19

BAFIS: Dataset + Framework to assess occupational Bias and Human Preference in modern Text-to-image Models

Generative artificial intelligence has the potential to improve productivity and transform the production of creative content. However, existing research indicates that image generation models are significantly influenced by biases. This work investigates the inherent biases and language-induced biases present in text-to-image models within the context of occupation-related image generation, complementing established metrics with human preference feedback. We present a comprehensive evaluation of five current text-to-image models: Midjourney v6.1, Stable Diffusion 3 Medium, DALL-E 3, Playground v2.5, and FLUX.1-dev , focusing on gender and ethnicity bias, image quality, and prompt alignment. To facilitate this evaluation, we developed the "Battle-Arena for Fair Image Synthesis" (BAFIS), a platform designed to collect human feedback on bias in generated images. Furthermore, we created a dataset comprising 21,140 synthetic images generated using multilingual prompts, which serves as a basis for our analysis. We further place our results within a broader social context by comparing them to official statistics from the German Federal Employment Agency. Our findings reveal systematic biases in text-to-image models, with established evaluation metrics in partial correlation with subjective user ratings. Thus, our research emphasizes the need for including human preferences to develop fairer and more inclusive text-to-image models.

08.
arXiv (quant-ph) 2026-06-16

Systematic Construction of Time-Dependent Hamiltonians for Microwave-Driven Josephson Circuits

arXiv:2512.20743v4 Announce Type: replace Abstract: Time-dependent electromagnetic drives are fundamental for controlling complex quantum systems, including superconducting Josephson circuits. In these devices, accurate time-dependent Hamiltonian models are imperative for predicting their dynamics and designing high-fidelity quantum operations. Existing numerical methods, such as black-box quantization (BBQ) and energy-participation ratio (EPR), excel at modeling the static Hamiltonians of Josephson circuits. However, these techniques do not fully capture the behavior of driven circuits stimulated by external microwave drives, nor do they include a generalized approach to account for the inevitable noise and dissipation that enter through microwave ports. Here, we introduce numerical techniques that leverage classical microwave simulations, efficiently executable in finite-element solvers, to obtain the time-dependent Hamiltonian of microwave-driven superconducting circuits with arbitrary geometries under charge, flux, or mixed electromagnetic modulation. Importantly, our techniques do not rely on a lumped-element description of the superconducting circuit, in contrast to previous approaches to tackling this problem. We demonstrate the versatility of our approach by characterizing the driven properties of realistic circuit devices in complex electromagnetic environments, including coherent dynamics due to charge and flux modulation, as well as drive-induced relaxation and dephasing. Our techniques offer a powerful toolbox for optimizing circuit designs and advancing practical applications in superconducting quantum computing.

09.
medRxiv (Medicine) 2026-06-18

Avidity of anti-pertussis toxin antibodies is associated with symptomatic Bordetella pertussis infection in a novel controlled human infection model

Background The association between functional antibody responses following Bordetella pertussis infection and symptomatic disease remains unclear. We characterized the maturation of anti-pertussis toxin (PT) IgG avidity after human challenge with B. pertussis and determined its association with symptomatic infection. Methods Healthy adults were intranasally inoculated with live B. pertussis organisms in a controlled human infection model and monitored for development of pertussis symptoms (NCT05136599). Serum samples were collected one day before inoculation and at 14, 28, 56, 180, and 365 days post challenge. Anti PT IgG avidity was tested using a titration of ammonium isothiocyanate (the bond breaking agent) to quantify a wide range of antibody avidities from low to very-high. Associations between covariates and avidity were examined using linear regression models, and high dimensional analyses were used to integrate all data. Findings Anti PT IgG avidity increased in both symptomatic (n=20) and asymptomatic (n=10) participants after the challenge, reached maximum levels at day 56, and then declined through day 365. Symptomatic participants developed significantly higher levels of high- and very high-avidity anti-PT antibodies at 28, 56, 180, and 365 days post-challenge compared with those who remained asymptomatic. In multivariate analyses, symptomatic infection was associated with higher levels of high and very high avidity anti-PT IgG at day180 and365 after challenge. Distinct avidity profiles in symptomatic vs asymptomatic participants emerged at day28 onwards, with the former group having higher levels of antibodies with higher avidities. However, levels of medium-high, high and very high avidity antibodies in symptomatic participants were lower at day 365 after challenge compared to their peak levels. Interpretation Anti-PT IgG avidity was associated with symptomatic B. pertussis infection and thus may serve as a surrogate of clinical disease outcome. These results highlight that antibody avidity provides an additional functional assay besides antibody quantitation to dissect immune responses to pertussis. Further investigation of anti PT IgG avidity should be pursued in natural pertussis outbreaks to determine whether it might be used to differentiate symptomatic from asymptomatic infections for epidemiologic purposes.

10.
PLOS Computational Biology 2026-06-05

A multiscale, Bayesian inference approach to augment mechanistic models of cell signaling with machine-learning predictions of binding affinity

by Holly A. Huber, Stacey D. Finley Computational models in systems biology are often underdetermined—that is, there is little data relative to the complexity and size of the model. This lack of data is primarily due to limits in our ability to observe specific biological systems and restricts the utility of computational models. To reduce this uncertainty, recent methods have explored augmenting parameter inference of systems biology models with predictions from machine learning models. Such approaches expand the pool of data that is applicable for the inference problem. Here, we explore augmenting the parameter inference of intracellular signaling models. We choose to investigate signaling because experimental measurements of the variables of interest, protein dynamics, are still quite limited. To investigate, we propose a novel, multiscale, Bayesian inference approach that augments traditional signaling data with predictions of binding affinity. These predictions are generated using a machine learning pipeline with measurements of amino acid sequence, from the Universal Protein Resource, or protein structure, from the Protein Data Bank, as inputs. We find that we can successfully integrate these measurements into the inference problem using our novel framework. Excitingly, this integration significantly improves the parameter estimates of signaling models. We demonstrate that how much this improvement impacts predictions of signaling depends on the sensitivity of the prediction to perturbations in the parameter values. Overall, the framework we establish here improves the parameter inference of intracellular signaling models by successfully bridging data on protein sequence and structure with systems-level signaling.

11.
arXiv (CS.CL) 2026-06-18

SFT Overtraining Predicts Rank Inversion via Entropy Collapse Under RLVR

The standard heuristic of selecting the SFT checkpoint with the highest pass@1 for GRPO can fail when SFT compresses the rollout distribution. For binary rewards, the expected within group advantage variance is $p(1{-}p)(g{-}1)/g$; when early GRPO drives $p$ below $p^*(g)$, most groups have identical rewards and provide no group relative signal. We study SFT depth ladders for Qwen2.5-Coder-3B and DeepSeek-Coder-6.7B. We test Qwen2.5-Coder-3B across five depths and three seeds, and DeepSeek-Coder-6.7B across four matched depths and three seeds. On Qwen, pre RL pass@1 rises with SFT depth, but peak GRPO pass@10 falls from $0.806$ to $0.481$ (3 seed mean, $n{=}20$); pre RL entropy is positively associated with the GRPO outcome ($\rho{=}{+}0.69$). On DeepSeek, pass@1 remains far above $p^*(8){=}0.083$, and GRPO outcomes compress rather than invert. A two stage diagnostic, combining pre RL entropy triage with an early GRPO entropy monitor, flags high risk checkpoints and can stop failing runs early. Simple KL to reference regularisation and label smoothing variants do not rescue the collapsed Qwen checkpoint in our setting, suggesting the failure is not a trivial GRPO hyperparameter artefact.

12.
medRxiv (Medicine) 2026-06-12

A Machine Learning Pipeline for Scalable Annotation of Patient-Ventilator Dyssynchrony from Bedside Ventilator Data

Objective: Patient-ventilator dyssynchrony (PVD) is a common and clinically consequential problem in critically ill patients receiving invasive mechanical ventilation. Yet automated identification of PVD subtypes at scale remains an unmet clinical need, owing to the lack of large annotated bedside waveform datasets. Methods: We developed and validated a semi-supervised algorithm for automated annotation of PVD. In two medical ICUs at a tertiary academic center, bedside devices continuously collected airway flow and pressure waveforms from the ventilators. We developed a software interface with an information retrieval system that grouped similar breaths for expert human review, yielding 1,542,296 labeled breaths across eight categories: 2 labels for breath delivery mode, 5 labels for PVD subtypes, and 1 label denoting a normal breath. Two pulmonary physicians with expertise in ventilator training and education provided the expert reference labels. We trained an initial classification model on a model-derivation set of 771,148 breaths (divided into training and validation) and evaluated it on a hold-out test set of 771,149 breaths A semi-supervised approach was utilized to extend labeling to an additional 12,965,000 unlabeled breaths. Results: The supervised model performed well across all labels, with Macro-F1 scores between 0.96 and 1.00. Semi-supervised learning across 12 rounds expanded the training set from 771,148 to 8,563,995 breaths without significant performance degradation. Conclusion: We developed a practical and scalable system for automated PVD annotation that performed well across all subtypes. This work provides a reproducible foundation for automated PVD labeling to support the development of machine-learning-based clinical decision support systems for identifying patient-level asynchrony.

13.
bioRxiv (Bioinfo) 2026-06-12

Evaluating cell type annotations in single-cell omics in the absence of ground truth

Accurate cell type annotation is essential for single-cell transcriptomics, directly shaping downstream analyses and biological interpretations. Yet, objective evaluation of annotation quality remains a major challenge. Here, we argue that a cell type or cell state label has practical utility only if it captures a molecular pattern that is reproducible across biological replicates. Based on this principle, we introduce inter-sample consistency (ISC), a quantitative framework to assess annotation quality in single-cell RNA-seq datasets. Unlike existing cluster validation approaches, ISC distinguishes annotations that generalize across samples and individuals from those driven by technical or unwanted variation, thereby providing principled criteria for annotation quality and transferability. When applied to published single-cell atlases, ISC reveals widespread reproducibility gaps and provides actionable guidance for repairing inconsistent annotations. Notably, ISC enables benchmarking of automated cell type annotation tools even when ground-truth labels are unavailable, providing interpretable metrics to guide their development and evaluation. Implemented as the scTypeEval Bioconductor package, this framework offers a broadly applicable resource for evaluating and improving cell type annotations in single-cell RNA-seq experiments.

14.
medRxiv (Medicine) 2026-06-22

Maternal-Fetal immune networks and viral signatures in the healthy amniotic cavity

The intrauterine environment has traditionally been viewed as a privileged site protected by the placental barrier. However, emerging evidence suggests that early in utero microbial exposure may prime the developing fetal immune system. Here, using target-enriched metagenomics and high-dimensional proteomics, we characterized the intra-amniotic viral landscape and immune networks in 114 healthy pregnancies including both normal and anomalous fetuses. We identify a sparse yet heterogeneous human viral signature in 26% of samples, predominantly composed of Herpesviridae, Polyomaviridae, and Picornaviridae. Although viral reads abundance was associated with fetal abnormalities, viral detection generally did not induce overt inflammatory activation, supporting a state of immune homeostasis within the amniotic cavity. Instead, viral presence was associated with subtle and selective immune modulation, including altered inducible antimicrobial peptide expression (HBD-2 and HBD-3), coupled with an attenuation of regulatory cytokines. Our results further reveal that the amniotic immune environment is primarily governed by gestational age, transitioning from a Th1-predominant "alert" phase to innate-readiness preceding parturition. These findings suggest that fragments of viral genetic material within the amniotic cavity may contribute to fetal immune instruction without triggering overt inflammation, providing a foundational framework for understanding how "silent" viral-exposure during gestation influences the developmental origins of neonatal immunity.

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

Remember, Don't Re-read: Stateful ReAct Agents for Token-Efficient Autonomous Experimentation

arXiv:2606.14945v1 Announce Type: new Abstract: The autoresearch pattern enables autonomous experimentation by having a large language model (LLM) iteratively modify code to optimize a target metric. Its stateless design, however, reconstructs experimental context from scratch at every iteration, incurring $O(n)$ token cost per iteration and $O(n^{2})$ total. This work reformulates the pattern as a stateful ReAct agent using LangGraph, where typed persistent state carries experimental history across iterations via a tool-calling interface. Two benchmarks are evaluated: hyperparameter tuning (15 iterations, small per-iteration observations) and code performance optimization (40 iterations, large per-iteration observations containing full source code and benchmark results). On hyperparameter tuning, the stateful agent consumes 90\% fewer tokens (2{,}492 vs.\ 24{,}465). On code optimization, the stateful agent consumes 52\% fewer tokens (627K vs.\ 1{,}275K) while achieving comparable optimization quality on both tasks. The token reduction is structural: the stateless agent re-reads the full history at $O(n)$ cost per iteration, while the stateful agent operates within a fixed-size conversation window at $O(1)$ cost. This paper describes the architecture in sufficient detail for practitioners to implement a stateful autoresearch agent for their own workflows.

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

TwinBI: An Agentic Digital Twin for Efficient Augmented Interactions with Business Intelligence Dashboards

arXiv:2606.13731v1 Announce Type: new Abstract: Business intelligence (BI) increasingly combines dashboard interaction with LLM-based assistance, but these two modes often fall out of sync during multi-step analysis. As users switch between direct dashboard manipulation and natural-language queries, it becomes difficult to preserve a consistent analytical state across filters, hierarchies, metrics, and chart context. We present TwinBI, an agentic digital-twin framework that couples an LLM-based agent system with an executable BI dashboard state. TwinBI unifies conversational interaction, dashboard manipulation, semantic grounding, and provenance tracking through a shared analytical state reconstructed from a unified interaction log. It also exposes artifacts such as schema views, SQL, logs, and an /insights command for state-grounded analytical summaries. We evaluate TwinBI in two complementary ways. In a controlled A/B benchmark with the same backbone agent, TwinBI improves exact-match accuracy from 43.3% to 63.3%, partial-credit accuracy from 48.3% to 70.8%, and substantially reduces timeout rate from 40.0% to 10.0% relative to Dashboard alone. In a usability study, participants benefited from the integrated dashboard-and-chat workflow, with high task accuracy, moderate workload, and favorable ratings for state-aware interaction mechanisms. These results suggest that TwinBI improves both agent-level analytical reliability and user-facing analytical support by turning visible dashboard state into richer actionable context. Our dataset and source code are available at: https://github.com/simonjisu/TwinBI

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

FinP: Fairness-in-Privacy in Federated Learning by Addressing Disparities in Privacy Risk

arXiv:2502.17748v4 Announce Type: replace Abstract: Federated Learning (FL) inherently mitigates mass data centralization risks; however, its privacy protections are not equally distributed - leaving vulnerable individuals disproportionately exposed to sophisticated privacy attacks. Crucially, statistical heterogeneity in human-centric FL environments often results in an inequitable distribution of privacy risks, particularly affecting those whose sensitive attributes or behaviors make them outliers. To address this critical gap, we introduce FinP, a novel framework designed to formalize and enforce fairness-in-privacy by mitigating disproportionate client vulnerability to Source Inference Attacks (SIA). FinP operationalizes a two-pronged defense strategy that tackles both the symptoms and root causes of privacy disparity, ensuring that no group of clients bears an excessive privacy burden. It combines a server-side adaptive aggregation mechanism, which dynamically weights client contributions based on their estimated privacy risk, with a client-side regularization technique to curb localized overfitting that drives unique data memorization. Extensive empirical evaluations on FEMNIST, Human Activity Recognition (HAR), and CIFAR-10 datasets demonstrate that FinP effectively aligns privacy fairness with primary task utility. Notably, FinP successfully mitigates SIA risks and reduces disparities in privacy exposure, establishing that strong fairness-in-privacy guarantees need not compromise model utility. Ultimately, FinP establishes equitable privacy protections by reducing vulnerability disparities by up to 57.14%, while preserving global model utility within a marginal +/- 1.75% of standard federated baselines.

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

ExpRL: Exploratory RL for LLM Mid-Training

arXiv:2606.17024v1 Announce Type: new Abstract: Sparse reward reinforcement learning (RL) has become a standard tool for improving LLM reasoning, but its success depends critically on the coverage present in the base model. In practice, models are often primed for RL through mid-training on curated reasoning traces that teach useful primitive skills such as decomposition, verification, or self-correction. Although effective, this strategy requires manually specifying what the model should learn, and it remains unclear whether such primitive coverage is enough for much harder problems, which require combining these skills into broader solution strategies. We study a more automated approach: RL-based mid-training using large corpora of human-written question-answer data. Rather than treating reference solutions as targets to imitate, our method, ExpRL, uses them as reward scaffolds: references are hidden from the policy and used only to construct problem-specific grading rubrics for judging on-policy reasoning traces. The policy samples from the original problem prompt, while an LLM judge compares the sampled reasoning trace against the reference solution and assigns outcome-level or process-level dense rewards. This lets ExpRL reinforce partial progress, useful intermediate reductions, and productive reasoning behaviors that sparse final-answer rewards often fail to upweight. On challenging math reasoning tasks, ExpRL yields stronger RL priming than SFT, sparse-reward GRPO, and self-distillation, and provides a better initialization for subsequent sparse-reward RL. Additional mixed-domain experiments further suggest that ExpRL can extend beyond the original math-only setting.

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

MetaResearcher: Scaling Deep Research via Self-Reflective Reinforcement Learning in Adversarial Virtual Environments

arXiv:2606.19893v1 Announce Type: new Abstract: Deep research agents have demonstrated remarkable capabilities in autonomous information gathering and synthesis, yet their training remains constrained by the static nature of simulated environments, the limits of fact-retrieval-only task designs, and the inefficiency of outcome-based reinforcement learning. In this work, we propose MetaResearcher, a novel framework that scales deep research agent training across four synergistic dimensions. First, we introduce an Evolving Virtual World that injects temporal dynamics and adversarial misinformation into the training environment, forcing agents to develop source credibility assessment and temporal conflict resolution skills. Second, we design Discovery-Oriented Tasks – including hypothesis generation and contradiction resolution – that transcend simple fact retrieval and push agents toward genuine research behaviors. Third, we propose a Self-Reflective Meta-Reward mechanism within the GRPO framework that jointly optimizes for answer correctness, search path efficiency, reflection depth, and tool call diversity, directly addressing the repetitive action loop problem observed in prior work. Fourth, we introduce a Heterogeneous Multi-Agent Swarm architecture comprising specialized Scout, Filter, and Synthesizer models that learn collaborative research strategies through coordinated reinforcement learning. Built upon the LiteResearcher infrastructure, MetaResearcher requires zero marginal API cost for training while targeting substantial improvements in both benchmark performance (GAIA, Xbench-DS) and epistemic robustness under adversarial conditions. We present the complete framework design, training methodology, and planned experimental validation.

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

MemToolAgent: Leveraging Memory for Tool Using Agents Based on Environment and User Feedback

Modern large language model (LLM) agents can use external tools to help users solve complex tasks. However, for problems that require learning from long-term historical events or from previous agent-environment interactions, LLM agents are required to use memory mechanisms to store and retrieve experiences. While sophisticated memory systems exist for dialogue agents, few studies have empirically examined how to improve agents' tool-using capabilities through past user-agent conversations. We propose MemToolAgent, a framework that improves tool use through memory management. Our approach contains a memory extraction module that processes past experiences into structured memory entries, and a retrieval module that dynamically selects a subset of the stored memory entries. This enables more personalized and accurate responses aligned with user preferences and feedback without requiring LLM fine-tuning. In summary, this work has three main contributions: (1) a unified memory entry format that improves both general-purpose and personalized tool use without LLM fine-tuning, (2) a reflection-based memory extraction that uses environment and user feedback to distill wrong executions into critiques to store, and (3) a retrieval module that chooses how many past experiences to use based on the memory similarity distribution. MemToolAgent achieves 29%, 80%, and 17% relative improvements compared to strong baselines on the WorkBench, NESTFUL, and PEToolBench benchmarks, respectively.

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

Hard or Just Unreached? Diagnosing the Sampling Blind Spot in Math-Reasoning Difficulty Estimation

arXiv:2606.19636v1 Announce Type: cross Abstract: Math and science reasoning benchmarks rely on pass@k, the fraction of sampled chains that reach gold, as the canonical per-example difficulty signal. The same signal drives RL with verifiable rewards, math data curation, synthetic curricula, and verifier training. We show this proxy has a persistent blind spot on its hardest stratum: on the eight free-form math cells we test (GSM8K and MATH across four open-weight models), 10.3-22.9% of the examples that no sampling seed solves in six tries are instead solved at matched compute by a six-chain deterministic regime. These are greedy decoding plus five cheap residual-stream perturbations applied via activation grafting, while greedy alone solves at most 6% on these math cells. Recovery scales with the additional budget, across perturbations whose mechanistic distinctness we verify across all twelve cells (cross-kind fix-set Jaccard

22.
arXiv (CS.CL) 2026-06-17

MemSlides: A Hierarchical Memory Driven Agent Framework for Personalized Slide Generation with Multi-turn Local Revision

Personalized presentation generation requires more than conditioning on a current prompt or template: agents must preserve stable user preferences across tasks, retain newly introduced preferences and constraints during multi-turn revision, and carry out local edits reliably. We propose MemSlides, a hierarchical memory framework for personalized presentation agents that separates long-term memory from working memory and further divides long-term memory into user profile memory and tool memory. User profile memory stores intent-conditioned profiles for round-0 personalization, working memory carries active preferences and session constraints across revision rounds, and tool memory stores reusable execution experience for reliable localized editing. MemSlides pairs this memory design with scoped slide-local revision, so targeted updates act on the smallest affected region instead of repeatedly regenerating the full deck. In controlled experiments, user profile memory improves persona-alignment judgments on a multi-persona, multi-intent profile bank, tool-memory injection improves closed-loop modify behavior in diagnostic matched-pair settings, and qualitative cases illustrate working memory's ability to carryover preferences. Taken together, these results suggest that effective personalization in presentation authoring depends on separating persistent user profiles, session-level working memory, and reusable execution experience across generation and localized revision.

23.
arXiv (CS.AI) 2026-06-12

FinSTaR: Towards Financial Reasoning with Time Series Reasoning Models

arXiv:2605.03460v3 Announce Type: replace Abstract: Time series (TS) reasoning models (TSRMs) have shown promising capabilities in general domains, yet they consistently fail in the financial domain, which exhibits unique characteristics. We propose a general 2 x 2 capability taxonomy for TSRMs by crossing 1) single-entity vs. multi-entity analysis with 2) assessment of the current state vs. prediction of future behavior. We instantiate this taxonomy in the financial domain-where the distinction between deterministic assessment and stochastic prediction is particularly critical-as ten financial reasoning tasks, forming the FinTSR-Bench benchmark based on S&P stocks. To this end, we propose FinSTaR (Financial Time Series Thinking and Reasoning), trained on FinTSR-Bench with distinct chain-of-thought (CoT) strategies tailored to each category. For assessment, which is deterministic (i.e., computable from observable data), we employ Compute-in-CoT, a programmatic CoT that enables models to derive answers directly from raw prices. For prediction, which is inherently stochastic (i.e., subject to unobservable factors), we adopt Scenario-Aware CoT, which generates diverse scenarios before making a judgment, mirroring how financial analysts reason under uncertainty. The proposed method achieves 78.9% average accuracy on FinTSR-Bench, substantially outperforming LLM and TSRM baselines. Furthermore, we show that the four capability categories are complementary and mutually reinforcing through joint training, and that Scenario-Aware CoT consistently improves prediction accuracy over standard CoT. Code is available at https://github.com/seunghan96/FinSTaR.

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

Phi-Actor-Critic: Steering General-Sum Games to Pareto-Efficient Correlated Equilibria

arXiv:2606.11284v1 Announce Type: cross Abstract: Real-world multi-agent systems, from traffic coordination to resource allocation, are often modeled as general-sum games where individual incentives conflict with collective welfare. In these settings, the central challenge is not merely finding an equilibrium, but selecting socially desirable outcomes among many suboptimal Nash equilibria. Standard deep multi-agent reinforcement learning (MARL) methods struggle with this problem, as value-decomposition approaches are constrained by monotonicity assumptions and policy-gradient methods often converge to stable but socially inefficient equilibria. To address this limitation, we propose $\Phi$-Actor-Critic ($\Phi$-AC), a framework that leverages swap regret minimization to steer learning toward high-welfare correlated equilibria (CE). To make counterfactual regret estimation tractable in deep MARL, $\Phi$-AC employs a centralized attention critic that predicts vector-valued regrets in a single forward pass, avoiding computationally expensive counterfactual simulations. We further introduce a Lagrangian-based equilibrium selection mechanism that optimizes social welfare while enforcing stability through regret constraints. Experiments on matrix games, Multi-Agent Particle Environments (MPE), and the Melting Pot Harvest scenario demonstrate that $\Phi$-AC learns efficient and stable coordination strategies across diverse mixed-motive settings while maintaining high collective return and competitive fairness.

25.
arXiv (CS.LG) 2026-06-16

Machine learning enables roughness-driven inverse design of milling processes

arXiv:2606.16032v1 Announce Type: cross Abstract: Interest in applying data-driven approaches in manufacturing has grown significantly, particularly for mapping complex, high-dimensional relationships. The milling process is one area where predictive models can link influential parameters to surface roughness metrics prior to in situ operations. While this approach offers clear advantages, it faces challenges due to limited datasets and robustness issues in inverse design paradigms. To address these challenges, this paper proposes a machine learning (ML)-based framework for the inverse design of the surface milling process, with a focus on surface roughness as the design objective. The framework employs forward training of two ML models, a deep neural network (DNN) and a random forest (RF) ensemble, both developed using a high-fidelity synthetic dataset generated from a computational simulation framework. These trained models are integrated into a Bayesian optimization (BO) procedure to overcome the multiplicity problem arising from the many-to-one mapping inherent in the dataset. The approach identifies top-performing milling process configurations, considering both process and tool parameters, and presents them from the full solution space. The models achieve average relative errors below 5% when compared to reference results, thereby demonstrating the robustness and reliability of the proposed methodology.