探索全球前沿学术脉络

01.

PLOS Medicine 2026-06-01 DOI: HASH:3b2eb52d77b40730e67bd0f8b71096e9

The NIH 2025 Public Access Policy: Immediate access, unequal costs

作者:

Caitlin R. Ryus↗

by Caitlin R. Ryus, Caroline Raymond King, Edward R. Melnick The NIH 2025 Public Access Policy eliminates embargo periods for federally funded research, expanding who can read science. Yet without addressing article processing charges and market concentration, the policy risks creating new barriers to who can afford to perform and publish their science. In this Perspective, Caitlin Ryus and colleagues discuss the NIH 2025 Public Access Policy, highlighting that while expanding who can read science, the policy risks creating new barriers to who can afford to perform and publish their science.

阅读与讨论 → 访问原文 →

02.

arXiv (CS.AI) 2026-06-11 DOI: arXiv:2606.12086

IntElicit: Eliciting and Assessing Contextualized Creativity via Dialogue Policy Optimization

作者:

Mingjia Li↗Jin Wu↗Hong Qian↗Wenhao Huang↗Yiyang Huang↗Yiwen Zhang↗Chanjin Zheng↗Xiangfeng Wang↗Aimin Zhou↗Jiajun Guo↗

arXiv:2606.12086v1 Announce Type: new Abstract: Contextualized assessment offers high ecological validity for evaluating creativity but introduces a critical challenge: observed performance may be confounded with cognitive proficiency (domain knowledge) and agency (willingness to engage). Meanwhile, in the age of generative AI, creative problem solving increasingly occurs in tool-mediated and human–AI interactive environments, making fully static assessment less aligned with contemporary creative practice. To address these issues, this paper proposes IntElicit, a framework for eliciting and assessing contextualized creativity via dialogue policy optimization. IntElicit functions as a constrained adaptive AI Interviewer: it provides non-directive knowledge and agency scaffolds in multi-turn interaction to reduce non-creative confounders, while preserving participants' responsibility for generating the creative content being evaluated. Specifically, to tackle sparse rewards and potential reward hacking (e.g., answer dictation) in open-ended educational dialogue, IntElicit introduces a decomposed process reward mechanism. This mechanism aligns the policy with pedagogical elicitation, rewarding prompts that draw out participant reasoning rather than producing optimal answers on their behalf. Extensive experiments, including participant simulation and a human subject study (N=64), show that IntElicit improves elicited creative outcomes over expert-designed baselines. Together, the results suggest that interactive elicitation can reveal creative potential that static FPSP-style assessment may miss, providing a formative and diagnostic lens for contextualized creativity assessment in AI-mediated learning contexts.

阅读与讨论 → 访问原文 →

03.

arXiv (CS.AI) 2026-06-12 DOI: arXiv:2606.12437

Algorithmic Constitutionalism

作者:

Oren Perez↗Nurit Wimer↗

arXiv:2606.12437v1 Announce Type: cross Abstract: The increasing encroachment of artificial intelligence (AI) on social life raises significant risks for society, particularly within the infospheres created and controlled by companies such as Google, Facebook, Apple, and Amazon. This article examines these risks through an in-depth analysis of Facebook's content moderation regime, which is already partially governed by algorithms. We argue that the idea of ethical engineering, often proposed in the literature as a solution to the governance challenges posed by AI, is inadequate for several reasons. In response, we develop an alternative framework, which we term "algorithmic constitutionalism." Our approach rests on three pillars: (a) a layered architecture consisting of two levels of code: (i) an operative or object level and (ii) a meta level designed to protect the system's core principles from algorithmically initiated change; (b) algorithmic meta-reasoning, which enables the system to operate simultaneously at both levels so that it can monitor, verify, and potentially correct in real time operations at the object level that depart from principles protected at the meta-code level; and (c) correction through deliberation. The article elaborates the concept of algorithmic constitutionalism and demonstrates how it may be applied to Facebook's content moderation regime. As part of this analysis, we examine the tension between societal constitutionalism and algorithmic constitutionalism. Paradoxically, attempts to subject AI systems to external deliberative control may also enable AI agents to intervene in that process, potentially undermining its purpose. The article concludes by considering the implications of this argument for the European Digital Services Act, which entered into force in October 2022.

阅读与讨论 → 访问原文 →

04.

arXiv (CS.AI) 2026-06-17 DOI: arXiv:2602.06014

Optimism Stabilizes Thompson Sampling for Adaptive Inference

作者:

Shunxing Yan↗Han Zhong↗

arXiv:2602.06014v2 Announce Type: replace-cross Abstract: Thompson sampling (TS) is widely used for stochastic multi-armed bandits, yet its inferential properties under adaptive data collection are subtle. Classical asymptotic theory for sample means can fail because arm-specific sample sizes are random and coupled with the rewards through the action-selection rule. We study adaptive inference for Thompson sampling with Gaussian randomized indices in $K$-armed stochastic bandits with independent sub-Gaussian reward noises, and identify optimism as a key mechanism for restoring stability, meaning that each arm's pull count concentrates around a deterministic scale. This stability yields asymptotically valid Wald inference despite adaptive sampling. First, we prove that variance-inflated TS is stable for any $K \ge 2$, including the challenging regime where multiple arms are optimal, with asymptotically uniform allocation over optimal arms and sharp logarithmic pull-count asymptotics for suboptimal arms. This resolves the $K$-armed extension question raised by \citet{halder2025stable}, using new winner-map and Lyapunov-drift techniques to control allocation among multiple optimal arms. Second, we analyze an alternative optimistic modification that keeps the Gaussian index variance unchanged but adds an explicit mean bonus to the index center, and establish a similar stability conclusion. In summary, suitably implemented optimism stabilizes Thompson sampling and enables asymptotically valid Wald inference in multi-armed bandits, while incurring only a mild additional regret cost.

阅读与讨论 → 访问原文 →

05.

arXiv (CS.LG) 2026-06-12 DOI: arXiv:2606.13076

$\alpha$-fair heterogeneous agent reinforcement learning

作者:

Yao-hua Franck Xu↗Tayeb Lemlouma↗Jean-Marie Bonnin↗Arnaud Braud↗

arXiv:2606.13076v1 Announce Type: cross Abstract: Cooperation in multi-agent systems is typically optimized through utilitarian objectives that maximize overall efficiency but fail to account for reward distribution, often resulting in inequitable "leader-follower" dynamics. While fairness-based approaches encourage pro-social behaviors where every agent benefits from cooperation, many current algorithms - including those utilizing reward shaping - break the stationarity of Markov Games or lack rigorous theoretical guarantees. This creates a critical gap between fair objective methods and theoretically safe learning frameworks. We propose a novel framework that bridges $\alpha$-fairness with Heterogeneous-Agent Trust Region Learning (HATRL), ensuring monotonic improvement and convergence toward Nash Equilibria. Our approach leverages a fair advantage function that dynamically weights agent utilities based on their expected returns, allowing the global objective to transition from purely utilitarian efficiency to $\alpha$-fairness welfare based on the parameter $\alpha$. We introduce two practical algorithms, $\alpha$-fair HATRPO and $\alpha$-fair HAPPO, and demonstrate through experiments in sequential social dilemmas like CleanUp and CommonHarvest that they perform better than HATRL's algorithms from a utilitarian point of view while achieving socially higher outcomes.

阅读与讨论 → 访问原文 →

06.

arXiv (CS.CV) 2026-06-16 DOI: arXiv:2606.15019

Towards Global AI-Driven Cervical Cancer Screening

作者:

Thuy Nuong Tran↗\"Omer S\"umer↗Evangelia Christodoulou↗Lennart Nausch\"utte↗Simon Kalteis↗Martin Paulikat↗Esmira Pashayeva↗Klara Steinheuer↗Isabella Borges↗Piotr Kalinowski↗Hermann Bussmann↗Sieng Sokmney↗…

The global elimination of cervical cancer is a key public health goal set by the World Health Organization (WHO), with screening programs reducing mortality by up to 80%. However, access to experts and biopsy services is limited in low- to middle-income countries (LMICs). Deep learning (DL)-based algorithms offer promising support for screening, but most existing approaches have been developed and validated on private datasets from single countries. We present the first DL-based approach to cervical cancer screening validated on data from multiple countries. Technically, we phrase the problem of detecting and classifying lesions in colposcopy images as a multi-task learning problem, in which we simultaneously perform image-level classification and lesion segmentation. Our model was trained on a private data set of acid stain colposcopy images with manually generated lesion segmentation masks and corresponding histopathological results, employing extensive data augmentation to address image variability. In an in-distribution validation with pathology results serving as ground truth, our algorithm outperformed medical experts (Balanced Accuracy: 0.68 vs 0.64) in CIN1- (Cervical intraepithelial neoplasia grade 1 or lower) versus CIN2+ (grade 2 or higher) classification. External validation on four colposcopy data sets from four countries featuring radical differences in prevalence and patient characteristics yielded superior performance of our method compared to baseline methods. Performance variability across countries was high with AUC values ranging from 0.54 - 0.80. Overall, algorithm performance varied with age, transformation zone (cervical area most prone to lesion development), presence of comorbidities and pathognomonic signs, with comorbidities having by far the largest negative effect. Future work should focus on improving model robustness and generalizability.

阅读与讨论 → 访问原文 →

07.

arXiv (CS.AI) 2026-06-19 DOI: arXiv:2606.19658

Denoising Implicit Feedback for Cold-start Recommendation

作者:

Gaode Chen↗Shicheng Wang↗Shikun Li↗Rui Huang↗Xinghua Zhang↗Yunze Luo↗Shipeng Li↗Shiming Ge↗Ruina Sun↗Yinjie Jiang↗Jun Zhang↗

arXiv:2606.19658v1 Announce Type: new Abstract: Implicit feedback is widely used in recommender systems due to its accessibility and generality, yet it usually presents noisy samples (e.g., clickbait, position bias). Meanwhile, recommenders inevitably face the item cold-start problem due to the continuous influx of new items. We identify that cold items are more prone to noisy samples due to the aforementioned factors, and researchers often overlook the significance of denoising implicit feedback for cold items. Previous denoising studies usually identify noisy samples based on heuristic patterns, such as higher loss values, and mitigate noise through sample selection or re-weighting. However, these methods have limited adaptability and are ineffective in cold-start scenarios. To achieve denoising implicit feedback for cold-start recommendation, we propose a model-agnostic denoising method called DIF. First, user preferences for content remain stable, which allows us to infer pseudo-labels indicating whether a user is interested in a cold item through content-similar warm items. Furthermore, to improve pseudo-label accuracy, we model the confidence of pseudo-labels based on the content similarity between the cold item and warm items, and then aggregate multiple pseudo-labels for each sample. Finally, we explicitly estimate the uncertainty of the noisy sample label by considering its relative entropy and the cold-start status of the item, which adaptively guides the role of pseudo-labels to correct the noisy labels at the sample level. DIF's superiority is supported by both theoretical justification and extensive experiments on real-world datasets. The method has been deployed on a billion-user scale short video application Kuaishou and has significantly improved various commercial metrics within cold-start scenarios.

阅读与讨论 → 访问原文 →

08.

arXiv (CS.AI) 2026-06-16 DOI: arXiv:2604.13301

Honeypot Protocol

作者:

Najmul Hasan↗

arXiv:2604.13301v1 Announce Type: cross Abstract: Trusted monitoring, the standard defense in AI control, is vulnerable to adaptive attacks, collusion, and strategic attack selection. All of these exploit the fact that monitoring is passive: it observes model behavior but never probes whether the model would behave differently under different perceived conditions. We introduce the honeypot protocol, which tests for context-dependent behavior by varying only the system prompt across three conditions (evaluation, synthetic deployment, explicit no-monitoring) while holding the task, environment, and scoring identical. We evaluate Claude Opus 4.6 in BashArena across all three conditions in both honest and attack modes. The model achieved 100% main task success and triggered zero side tasks uniformly across conditions, providing a baseline for future comparisons with stronger attack policies and additional models.

阅读与讨论 → 访问原文 →

09.

arXiv (CS.AI) 2026-06-15 DOI: arXiv:2606.13884

Capability Minimization as a Safety Primitive: Risk-Aware Causal Gating for Least-Privilege LLM Agents

作者:

Laxmipriya Ganesh Iyer↗Rahul Suresh Babu↗

arXiv:2606.13884v1 Announce Type: new Abstract: Modern decision systems increasingly rely on learned components whose outputs may be confident yet wrong, exposing downstream actions to costly errors. We introduce Risk-Aware Causal Gating (RACG), a framework that decides whether to act on, defer, or abstain from a model's prediction by combining causal effect estimation with calibrated risk control. RACG models the causal pathway from candidate actions to outcomes and gates each decision according to an estimated counterfactual risk rather than raw predictive confidence. To make gating reliable, we derive distribution-free bounds on the probability of acting under high-risk conditions and show how these bounds translate into operating thresholds that satisfy user-specified safety constraints. We further propose an adaptive gating policy that adjusts to distribution shift by monitoring discrepancies between predicted and realized outcomes, tightening the gate when causal assumptions appear violated. Across simulated interventions and real-world decision benchmarks, RACG reduces high-cost errors substantially while preserving most of the utility of an ungated policy, and it outperforms confidence-based and selective-prediction baselines at matched abstention rates. Our results indicate that explicitly separating causal risk from predictive uncertainty yields decision systems that are both safer and more transparent, offering a principled mechanism for trustworthy automation in high-stakes settings.

阅读与讨论 → 访问原文 →

10.

arXiv (CS.AI) 2026-06-11 DOI: arXiv:2605.19031

KAN-MLP-Mixer: A comprehensive investigation of the usage of Kolmogorov-Arnold Networks (KANs) for improving IMU-based Human Activity Recognition

作者:

Mengxi Liu↗Sizhen Bian↗Vitor Fortes↗Francisco Calatrava Nicolas↗Daniel Gei{\ss}ler↗Maximilian Kiefer-Emmanouilidis↗Bo Zhou↗Paul Lukowicz↗

arXiv:2605.19031v2 Announce Type: replace Abstract: Kolmogorov-Arnold Networks (KANs) have demonstrated an exceptional ability to learn complex functions on clean, low-dimensional data but struggle to maintain performance on noisy and imperfect real-world datasets. In contrast, conventional multi-layer perceptrons (MLPs) are far more tolerant to noise and computationally efficient. Replacing all MLP components with KANs in HAR models often degrades accuracy and computation efficiency, highlighting an open challenge: how to combine KANs' precision with MLPs' noise robustness and efficiency. To address this, we systematically explore various placements of KAN modules within deep HAR networks and propose a hybrid architecture that strategically synergizes the strengths of both paradigms, which uses a KAN-based input embedding layer, retains MLP layers for intermediate feature mixing, and introduces a specialized LarctanKAN module for final activity classification. Across eight public HAR datasets, the hybrid KAN-MLP model achieves an average macro F1 score relative improvement of 5.33\% compared pure-MLP model, significantly outperforming standalone KAN and MLP baselines. Furthermore, integrating this hybrid strategy into other state-of-the-art HAR architectures consistently boosts their performance. Our findings demonstrate that a carefully orchestrated combination of KAN, MLP, or other conventional neural components yields more robust and accurate HAR models for real-world wearable sensing environments.

阅读与讨论 → 访问原文 →

11.

arXiv (CS.AI) 2026-06-16 DOI: arXiv:2605.26595

Cordyceps: Covert Control Attacks on LLMs via Data Poisoning

作者:

Zedian Shao↗Charles Fleming↗Teodora Baluta↗

arXiv:2605.26595v2 Announce Type: replace-cross Abstract: Large language models (LLMs) are often fine-tuned on uncurated text datasets that adversaries can poison. Existing poisoning attacks primarily rely on fixed trigger phrases that defenses such as outlier detection, clean-data regularization, or online monitoring can neutralize. In this paper, we propose a data poisoning method that teaches an LLM an information hiding scheme reliably and stealthily through semantic associations between shared knowledge such as facts or concepts and attacker-chosen phrases. The induced hiding scheme can encode and decode arbitrary malicious instructions, thus revealing a new and subtle poisoning-induced vulnerability: covert control attacks. We precisely characterize covert control attacks and evaluate them across $5$ LLMs, $3$ backdoor defenses, and $4$ prompt injection defenses. With a small poisoned fraction, covert control attacks outperform heuristic-based prompt injection attacks in average attack success rate by about $40\%$ relative to clean fine-tuned models. They also circumvent defenses based on detection and fine-tuning, maintaining up to $93\%$ attack success rate after backdoor defenses and up to $98\%$ after prompt injection defenses.

阅读与讨论 → 访问原文 →

12.

arXiv (CS.AI) 2026-06-11 DOI: arXiv:2605.26418

When Does Deep RL Beat Calibrated Baselines? A Benchmark Study on Adaptive Resource Control

作者:

Guilin Zhang↗Chuanyi Sun↗Kai Zhao↗Shahryar Sarkani↗John Fossaceca↗

arXiv:2605.26418v2 Announce Type: replace-cross Abstract: A properly calibrated rule-based autoscaler can beat every one of six mainstream deep reinforcement learning (DRL) algorithms on cost across every workload we test - so when, if ever, does DRL actually help? We study this in RLScale-Bench, a reproducible benchmark and evaluation protocol for DRL on adaptive resource control, where an agent allocates compute to a dynamic workload under cost and service-level constraints. We evaluate PPO, DQN, A2C, SAC, TD3, and DDPG under matched architectures, training budgets, and reward functions against a calibrated rule-based baseline across six workload patterns and five seeds (240 runs), instantiate the benchmark on Kubernetes Horizontal Pod Autoscaling, and probe distribution-shift generalization. Three findings challenge common assumptions: (i) the calibrated controller achieves the lowest cost on all six workloads, though it trails the best RL agents on bursty and flash traffic; (ii) discrete-action algorithms outperform continuous-action ones by one to two orders of magnitude in constraint violations due to action-space mismatch; and (iii) no single algorithm dominates across workloads, with rankings shifting by up to four positions. The bottleneck in RL-based resource control is not algorithm selection but baseline calibration, reward engineering, and realistic evaluation protocols.

阅读与讨论 → 访问原文 →

13.

arXiv (quant-ph) 2026-06-12 DOI: arXiv:2409.04091

Squeezing Enhancement in Lossy Multi-Path Atom Interferometers

作者:

Julian G\"unther↗Jan-Niclas Kirsten-Siem{\ss}↗Naceur Gaaloul↗Klemens Hammerer↗

arXiv:2409.04091v3 Announce Type: replace Abstract: This paper explores the sensitivity gains afforded by spin-squeezed states in atom interferometry, in particular using Bragg diffraction. We introduce a generalised input-output formalism that accurately describes realistic, non-unitary interferometers, including losses due to velocity selectivity and scattering into undesired momentum states. This formalism is applied to evaluate the performance of one-axis twisted spin-squeezed states in improving phase sensitivity. Our results show that by carefully optimising the parameters of the Bragg beam splitters and controlling the degree of squeezing, it is possible to improve the sensitivity of the interferometer by several dB with respect to the standard quantum limit despite realistic levels of losses in light pulse operations. However, the analysis also highlights the challenges associated with achieving these improvements in practice, most notably the impact of finite temperature on the benefits of entanglement. The results suggest ways of optimising interferometric setups to exploit quantum entanglement under realistic conditions, thereby contributing to advances in precision metrology with atom interferometers.

阅读与讨论 → 访问原文 →

14.

arXiv (CS.AI) 2026-06-17 DOI: arXiv:2606.18096

S4oP: Operator-level Pruning of Structured State Space Models for Resource-Constrained Devices

作者:

Marco Deano↗Filippo Ziche↗Nicola Bombieri↗

arXiv:2606.18096v1 Announce Type: cross Abstract: Structured State Space Models (SSMs), including the S4 and S4D architectures, have recently emerged as powerful alternatives to attention-based models for capturing long-range dependencies in sequential data. Despite their strong empirical performance, deploying these models in time- and resource-constrained settings remains challenging due to their computational and memory demands. In this paper, we propose a novel incremental, operator-level pruning approach for S4- and S4D-based models that significantly reduces inference cost while preserving predictive performance. To the best of our knowledge, this is the first work to systematically investigate structured operator pruning for SSMs. Our method progressively prunes model operators by interleaving structured masking with fine-tuning, while jointly monitoring accuracy and inference latency. We implement this approach within a unified training and evaluation framework that enables systematic exploration of efficiency-accuracy trade-offs. Experiments across multiple benchmark datasets show that pruning up to 70% of the model operators preserves the performance of the original models in most cases, while substantially reducing inference latency. These results demonstrate that structured operator pruning is an effective and previously unexplored strategy for improving the efficiency of SSMs and facilitate their deployment in practical, resource-constrained scenarios.

阅读与讨论 → 访问原文 →

15.

arXiv (quant-ph) 2026-06-19 DOI: arXiv:2606.19310

Exclusion Statistics as a Thermodynamic Resource in Quantum Heat Engines

作者:

Sampurna Karmakar↗Aziz Hasan↗Sourin Das↗

arXiv:2606.19310v1 Announce Type: cross Abstract: The maximum power extractable from a quantum thermoelectric heat engine operating with free fermion carriers is bounded by the universal Whitney limit, $P_{fermion}^{\max} \simeq 0.0321\pi^2 k_B^2(T_L-T_R)^2/h$. We demonstrate that this bound is not fundamental to quantum heat engines but is instead an artifact of fermionic statistics. Within the nonlinear Landauer-B\"{u}ttiker framework, a bosonic working medium yields a strictly enhanced universal maximum power, $P_{boson}^{\max} = (\ln 2)^2\, k_B^2(T_L-T_R)^2/h$, exceeding the fermionic limit by a factor of $(\ln 2)^2/(0.0321\pi^2) \approx 1.52$. We propose magnon transport through a ferromagnetic spin chain as an experimentally viable bosonic realization. Incorporating Haldane fractional exclusion statistics with parameter $g$ provides a continuous interpolation between the bosonic ($g = 0$) and fermionic ($g = 1$) limits, revealing a monotonic enhancement of maximum power for $g < 1$ at reduced bias cost. These results establish quantum statistical exclusion as a previously unrecognized and independently tunable thermodynamic resource, opening performance regimes inaccessible to conventional carrier-engineering approaches.

阅读与讨论 → 访问原文 →

16.

arXiv (CS.CL) 2026-06-12 DOI: arXiv:2602.13379

Unsafer in Many Turns: Benchmarking and Defending Multi-Turn Safety Risks in Tool-Using Agents

作者:

Xu Li↗Simon Yu↗Minzhou Pan↗Yiyou Sun↗Bo Li↗Dawn Song↗Xue Lin↗Weiyan Shi↗

LLM-based agents are becoming increasingly capable, yet their safety lags behind. This creates a gap between what agents can do and should do. This gap widens as agents engage in multi-turn interactions and employ diverse tools, introducing new risks overlooked by existing benchmarks. To systematically scale safety testing into multi-turn, tool-realistic settings, we propose a principled taxonomy that transforms single-turn harmful tasks into multi-turn attack sequences. Using this taxonomy, we construct MT-AgentRisk (Multi-Turn Agent Risk Benchmark), the first benchmark to evaluate multi-turn tool-using agent safety. Our experiments reveal substantial safety degradation: the Attack Success Rate (ASR) increases by 16% on average across open and closed models in multi-turn settings. To close this gap, we propose ToolShield, a training-free, tool-agnostic, self-exploration defense: when encountering a new tool, the agent autonomously generates test cases, executes them to observe downstream effects, and distills safety experiences for deployment. Experiments show that ToolShield effectively reduces ASR by 30% on average in multi-turn interactions. Our code is available at https://github.com/CHATS-lab/ToolShield.

阅读与讨论 → 访问原文 →

17.

arXiv (CS.AI) 2026-06-16 DOI: arXiv:2512.11682

MedAI: Evaluating TxAgent's Therapeutic Agentic Reasoning in the NeurIPS CURE-Bench Competition

作者:

Tim Cofala↗Christian Kalfar↗Jingge Xiao↗Johanna Schrader↗Michelle Tang↗Wolfgang Nejdl↗

arXiv:2512.11682v2 Announce Type: replace Abstract: Therapeutic decision-making in clinical medicine constitutes a high-stakes domain in which AI guidance interacts with complex interactions among patient characteristics, disease processes, and pharmacological agents. Tasks such as drug recommendation, treatment planning, and adverse-effect prediction demand robust, multi-step reasoning grounded in reliable biomedical knowledge. Agentic AI methods, exemplified by TxAgent, address these challenges through iterative retrieval-augmented generation (RAG). TxAgent employs a fine-tuned Llama-3.1-8B model that dynamically generates and executes function calls to a unified biomedical tool suite (ToolUniverse), integrating FDA Drug API, OpenTargets, and Monarch resources to ensure access to current therapeutic information. In contrast to general-purpose RAG systems, medical applications impose stringent safety constraints, rendering the accuracy of both the reasoning trace and the sequence of tool invocations critical. These considerations motivate evaluation protocols treating token-level reasoning and tool-usage behaviors as explicit supervision signals. This work presents insights derived from our participation in the CURE-Bench NeurIPS 2025 Challenge, which benchmarks therapeutic-reasoning systems using metrics that assess correctness, tool utilization, and reasoning quality. We analyze how retrieval quality for function (tool) calls influences overall model performance and demonstrate performance gains achieved through improved tool-retrieval strategies. Our work was awarded the Excellence Award in Open Science. Complete information can be found at https://curebench.ai/.

阅读与讨论 → 访问原文 →

18.

arXiv (CS.LG) 2026-06-17 DOI: arXiv:2606.17524

Learning to Refine Hidden States for Reliable LLM Reasoning

作者:

Chia-Hsuan Hsu↗Jui-Ming Yao↗

arXiv:2606.17524v1 Announce Type: new Abstract: Large language models show strong reasoning ability, but their internal reasoning process can remain unstable in complex multi-step settings, where early hidden-state errors may propagate to incorrect predictions. We propose ReLAR, a reinforcement-guided latent refinement framework that iteratively updates hidden representations before decoding. ReLAR maintains a compact latent reasoning state and uses learned depth and action controllers to adaptively determine both the number and direction of refinement steps. The controllers are trained with a policy gradient objective based on step-wise likelihood improvement, enabling efficient input-dependent reasoning without explicit chain-of-thought generation. Experiments on medical, mathematical, multi-hop reasoning, and open-ended generation benchmarks show that ReLAR improves accuracy, generation quality, and reasoning stability with substantially lower inference overhead than explicit reasoning baselines.

阅读与讨论 → 访问原文 →

19.

arXiv (CS.LG) 2026-06-18 DOI: arXiv:2606.18338

ThousandWorlds: A benchmark for climate emulation of potentially habitable exoplanets

作者:

Edward T. Stevenson↗Mei Ting Mak↗Eric Wolf↗Denis E. Sergeev↗Tobi Hammond↗N. J. Mayne↗Miles Cranmer↗

arXiv:2606.18338v1 Announce Type: new Abstract: The search for life beyond Earth will depend on detecting faint signatures in the atmospheres of potentially habitable exoplanets. Interpreting those signatures requires understanding the host planet's climate: the same molecule may signal life on one planet and abiotic chemistry on another. Global climate models (GCMs) provide this understanding, but individual runs can require up to millions of core-hours and substantial domain expert time. Machine-learning emulators could remove this bottleneck, but progress has been limited by the absence of a curated, multi-model exoclimate dataset. We introduce ThousandWorlds, an ML-ready benchmark for exoclimate emulation and for the broader regime of low-data, multi-simulator, parameter-to-field regression. The dataset contains approximately 1800 simulations from five GCMs, mapping eight planet parameters to 3D atmospheric fields including temperature, humidity, winds, clouds, and radiation. Three nested subsets define progressively harder challenges: single-simulator regression, multi-simulator regression with complete observations, and multi-simulator regression with structured missingness. We propose two evaluation protocols: one for ranking methods, and one that measures performance relative to the disagreement between GCMs themselves. We evaluate seven baselines spanning simple methods, deep learning, and Gaussian processes. GP-based methods perform best, suggesting that ThousandWorlds exposes a regime where off-the-shelf deep learning does not yet succeed. Data: https://doi.org/10.57967/hf/8695. Code: https://github.com/edstevenson/ThousandWorlds.

阅读与讨论 → 访问原文 →

20.

arXiv (CS.LG) 2026-06-15 DOI: arXiv:2606.14335

Recovery thresholds for hidden weighted sparse graphs

作者:

Zhe Hou↗Jingcheng Liu↗

arXiv:2606.14335v1 Announce Type: cross Abstract: Recovering structural information from noisy high-dimensional data is a fundamental task in statistical inference. We investigate the recovery thresholds for a graph hidden in a randomly weighted complete graph. Specifically, an unknown graph $H^* \in H_n$ is chosen uniformly at random, and hidden in a complete graph of $n$ vertices as follows: the weight of an edge $e \in H$ is distributed independently according to $P_n$; otherwise the weight is distributed independently according to $Q_n$. The goal is to recover almost all of $H$ from these edge weights. Assuming a local Lipschitzness of the Rényi divergence between distributions $P_n$ and $Q_n$, and a mild density condition for the graphs $H_n$, we give a unified characterization of the information-theoretic limit for recovering almost all of $H$ (also known as almost exact recovery). Our characterization connects the KL divergence between $P_n$ and $Q_n$ to the logarithm of the first moment threshold of $H$ in the Erdős-Rényi random graph model $G(n,p)$. Our lower bound also extends to the task of partial recovery, in which only a constant $\lambda$-fraction of $H$ needs to be recovered. Last but not least, for certain Bernoulli and Exponential regimes, and for Gaussian distributions, we are able to show an All-or-Nothing (AoN) threshold phenomenon at the exponential scale.

阅读与讨论 → 访问原文 →

21.

arXiv (CS.AI) 2026-06-12 DOI: arXiv:2507.05019

Meta-Learning Transformers to Improve In-Context Generalization

作者:

Lorenzo Braccaioli↗Anna Vettoruzzo↗Prabhant Singh↗Joaquin Vanschoren↗Mohamed-Rafik Bouguelia↗Nicola Conci↗

arXiv:2507.05019v2 Announce Type: replace-cross Abstract: In-context learning enables transformer models to generalize to new tasks based solely on input prompts, without any need for weight updates. However, existing training paradigms typically rely on large, unstructured datasets that are costly to store, difficult to evaluate for quality and balance, and pose privacy and ethical concerns due to the inclusion of sensitive information. Motivated by these limitations and risks, we propose an alternative training strategy where we leverage a collection of multiple, small-scale, and domain-specific datasets. We empirically demonstrate that the increased quality and diversity of such data improve the generalization abilities of in-context learners beyond their training domain, while achieving comparable performance with models trained on a single large-scale dataset. We investigate this paradigm by leveraging meta-learning to train an in-context learner on the Meta-Album collection under several settings. Firstly, we show the performance in a controlled environment, where the test domain is completely excluded from the training knowledge. Secondly, we explore the robustness of these models to forgetting in a continual scenario where the information is accessible for a limited time. Finally, we explore the more challenging unsupervised scenario. Our findings demonstrate that transformers still generalize for in-context prediction when trained on a curated dataset collection while offering advantages in modularity and replaceability.

阅读与讨论 → 访问原文 →

22.

arXiv (CS.AI) 2026-06-12 DOI: arXiv:2606.12821

GeoNatureAgent Benchmark: Benchmarking LLM Agents for Environmental Geospatial Analysis Across Frontier and Open-Weight Foundation Models

作者:

Gabriel Diaz-Ireland↗Diego Prieto-Herr\'aez↗Mario Garc\'ia Peces↗Javier Vel\'azquez↗Devika Jain↗

arXiv:2606.12821v1 Announce Type: new Abstract: Environmental scientists spend disproportionate effort on data wrangling rather than analysis, and AI agents that automate geospatial workflows remain unvalidated: no benchmark evaluates agents operating through structured tool calling against real APIs. We introduce the GeoNatureAgent Benchmark, the first benchmark for environmental analysis agents that operate via structured tool calls to a production-style geospatial API. It comprises 93 tasks across 18 categories, covering municipality analysis, multi-turn conversation, spatial reasoning, cross-indicator synthesis, error handling and recovery, ranking, comparison, multilingual understanding, habitat analysis, and task rejection. Tasks are evaluated against an open, self-hostable API serving three environmental indicators across Spain and Portugal via sixteen tools. We evaluate seven LLMs (Claude Sonnet 4, DeepSeek V3.2, GLM-5, Gemini 2.5 Pro, Qwen3-235B, GPT-OSS-120B, Llama 4 Scout) under three temperature-1.0 seeds, reporting capability and per-case cost as orthogonal axes. We find: (1) Claude Sonnet 4 leads at 60.8% +/- 0.8%, followed by DeepSeek V3.2 at 56.3% +/- 3.1%, with no other model above 51%; (2) the cost-accuracy Pareto frontier is occupied mostly by open-weight models, with DeepSeek V3.2 offering 93% of Claude's capability at 11x lower cost ($0.011/case); (3) comparison tasks remain universally unsolved (0% on close-value comparisons), exposing systematic reasoning limits; and (4) structured tool calling against a real API is more discriminative than general-purpose GIS benchmarks, with accuracies 25-35 points lower. We further show extensibility by integrating BigEarthNet V2 land cover for Portugal alongside Spanish CO2 and erosion indicators. The benchmark, harness, and self-hostable API are publicly available.

阅读与讨论 → 访问原文 →

23.

arXiv (CS.CL) 2026-06-19 DOI: arXiv:2606.20075

What Makes Effective Supervision in Latent Chain-of-Thought: An Information-Theoretic Analysis

作者:

Xinghao Chen↗Chak Tou Leong↗Wenjin Guo↗Jian Wang↗Wenjie Li↗Xiaoyu Shen↗

Latent Chain-of-Thought (CoT) internalizes reasoning within continuous hidden states, offering a promising alternative to verbose discrete reasoning traces. However, robust latent reasoning remains difficult because outcome supervision provides weak learning signals and leaves latent trajectories prone to semantic drift. In this work, we analyze Latent CoT from an information-theoretic perspective and identify this failure as a dual collapse: gradient attenuation along the optimization path and representational drift in the latent space. We further decompose process supervision into two complementary dimensions: Trajectory Supervision, which injects dense stepwise reasoning signals, and Space Supervision, which preserves the semantic structure of the latent manifold. Our analysis shows that rigid geometric compression can collapse the reasoning space, whereas generative reconstruction provides a more flexible semantic anchor that better preserves information capacity. To measure these effects, we introduce the Unified Latent Probe (ULP), which quantifies the mutual information between latent trajectories and explicit reasoning steps. Experiments reveal a clear Information-Performance Binding: reasoning accuracy depends on the information fidelity preserved in the latent chain. These findings provide a principled framework for latent reasoning supervision and suggest shifting from geometric imitation toward mutual information maximization. Our code is available at \href{https://github.com/EIT-NLP/Supervision-in-Latent-CoT}{this repository}.

阅读与讨论 → 访问原文 →

24.

arXiv (CS.AI) 2026-06-19 DOI: arXiv:2601.21542

Bi-Anchor Interpolation Solver for Accelerating Generative Modeling

作者:

Hongxu Chen↗Hongxiang Li↗Zhen Wang↗Long Chen↗

arXiv:2601.21542v3 Announce Type: replace-cross Abstract: Flow Matching (FM) models have emerged as a leading paradigm for high-fidelity synthesis. However, their reliance on iterative Ordinary Differential Equation (ODE) solving creates a significant latency bottleneck. Existing solutions face a dichotomy: training-free solvers suffer from significant performance degradation at low Neural Function Evaluations (NFEs), while training-based one- or few-steps generation methods incur prohibitive training costs and lack plug-and-play versatility. To bridge this gap, we propose the Bi-Anchor Interpolation Solver (BA-solver). BA-solver retains the versatility of standard training-free solvers while achieving significant acceleration by introducing a lightweight SideNet (1-2% backbone size) alongside the frozen backbone. Specifically, our method is founded on two synergistic components: 1) Bidirectional Temporal Perception, where the SideNet learns to approximate both future and historical velocities without retraining the heavy backbone; and 2) Bi-Anchor Velocity Integration, which utilizes the SideNet with two anchor velocities to efficiently approximate intermediate velocities for batched high-order integration. By utilizing the backbone to establish high-precision ``anchors'' and the SideNet to densify the trajectory, BA-solver enables large interval sizes with minimized error. Empirical results on ImageNet-256^2 demonstrate that BA-solver achieves generation quality comparable to 100+ NFEs Euler solver in just 10 NFEs and maintains high fidelity in as few as 5 NFEs, incurring negligible training costs. Furthermore, BA-solver ensures seamless integration with existing generative pipelines, facilitating downstream tasks such as image editing.

阅读与讨论 → 访问原文 →

25.

arXiv (CS.LG) 2026-06-16 DOI: arXiv:2606.14945

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

作者:

Faramarz Jabbarvaziri↗

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.

阅读与讨论 → 访问原文 →