中 EN
登录 注册账户

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。

登录 注册账户
01.
medRxiv (Medicine) 2026-06-10

Development of a Novel Blood-Based Assay for Brain-Derived Tau and Its Validation in Traumatic Brain Injury

作者:
Balogun↗W. G↗Zeng↗Nafash↗M. N↗Sehrawat↗Shi↗Svirsky↗S. E↗Okonkwo↗D. O↗Puccio↗…

Brain-derived tau (BD-tau) is an emerging blood-based biomarker for neurodegeneration, yet there are currently limited well validated BD-tau assays available for research and clinical use. To enhance access to this vital biomarker for neurological disorders including traumatic brain injury (TBI), we developed a novel blood-based immunoassay for BD-tau on the ultra-sensitive Quanterix HD-X platform using Single Molecule Array technology. Analytical validation assessed dilution linearity, specificity, precision, detection limits, and spike recovery, each recording robust metrics in agreement with international expert recommendations. The assay demonstrated robust validation metrics, achieving between-run stability of 95% when analyzing aliquots from six independent plasma and serum samples across five analytical runs. It also showed strong dilution linearity when diluted four-fold and achieved over 90% recovery when spiked with cerebrospinal fluid. Next, we evaluated the clinical utility of the assay in cohorts of individuals with traumatic brain injury (TBI), where strong performances were recorded whether using the 2-step or 3-step assay formats ({rho}= 0.94; p < 0.0001). Furthermore, plasma BD-tau distinguished samples from TBI patients based on time from injury and severity (AUC=0.93). Plasma BD-tau differentiated between favorable and unfavorable functional outcomes in the acute-severe group. Our findings underscore the significant potential of the BD-tau assay as a biomarker for TBI in the severe phase.

阅读与讨论 → 访问原文 →
02.
arXiv (CS.CL) 2026-06-11

Pass@K Policy Optimization: Solving Harder Reinforcement Learning Problems

作者:
Christian Walder↗Deep Karkhanis↗

Reinforcement Learning (RL) algorithms sample multiple n>1 solution attempts for each problem and reward them independently. This optimizes for pass@1 performance and prioritizes the strength of isolated samples at the expense of the diversity and collective utility of sets of samples. This under-utilizes the sampling capacity, limiting exploration and eventual improvement on harder examples. As a fix, we propose Pass-at-k Policy Optimization (PKPO), a transformation on the final rewards which leads to direct optimization of pass@k performance, thus optimizing for sets of samples that maximize reward when considered jointly. Our contribution is to derive novel low variance unbiased estimators for pass@k and its gradient, in both the binary and continuous reward settings. We show optimization with our estimators reduces to standard RL with rewards that have been jointly transformed by a stable and efficient transformation function. While previous efforts are restricted to k=n, ours is the first to enable robust optimization of pass@k for any arbitrary k

阅读与讨论 → 访问原文 →
03.
arXiv (CS.CL) 2026-06-12

When Iterative RAG Beats Ideal Evidence: A Diagnostic Study in Scientific Multi-hop Question Answering

作者:
Mahdi Astaraki↗Mohammad Arshi Saloot↗Ali Shiraee Kasmaee↗Hamidreza Mahyar↗Soheila Samiee↗

Retrieval-Augmented Generation (RAG) extends large language models (LLMs) beyond parametric knowledge, yet it is unclear when iterative retrieval-reasoning loops meaningfully outperform static RAG, particularly in scientific domains with multi-hop reasoning, sparse domain knowledge, and heterogeneous evidence. We provide the first controlled, mechanism-level diagnostic study of whether synchronized iterative retrieval and reasoning can surpass an idealized static upper bound (Gold Context) RAG. We benchmark eleven state-of-the-art LLMs under three regimes: (i) No Context, measuring reliance on parametric memory; (ii) Gold Context, where all oracle evidence is supplied at once; and (iii) Iterative RAG, a training-free controller that alternates retrieval, hypothesis refinement, and evidence-aware stopping. Using the chemistry-focused ChemKGMultiHopQA dataset, we isolate questions requiring genuine retrieval and analyze behavior with diagnostics spanning retrieval coverage gaps, anchor-carry drop, query quality, composition fidelity, and control calibration. Across models, Iterative RAG consistently outperforms Gold Context, with gains up to 25.6 percentage points, especially for non-reasoning fine-tuned models. Staged retrieval reduces late-hop failures, mitigates context overload, and enables dynamic correction of early hypothesis drift, but remaining failure modes include incomplete hop coverage, distractor latch trajectories, early stopping miscalibration, and high composition failure rates even with perfect retrieval. Overall, staged retrieval is often more influential than the mere presence of ideal evidence; we provide practical guidance for deploying and diagnosing RAG systems in specialized scientific settings and a foundation for more reliable, controllable iterative retrieval-reasoning frameworks.

阅读与讨论 → 访问原文 →
04.
arXiv (CS.CV) 2026-06-12

TimeLens: On-Device Artifact Recognition with Retrieval-Augmented Question Answering for the Grand Egyptian Museum

作者:
Rawan Hesham↗Ali Ashraf↗Amr Ahmed↗Malak Alaa↗Omar Ahmed↗Omar Wagih↗

TimeLens is an AI-powered bilingual mobile guide for the Grand Egyptian Museum (GEM). Pointing a phone at an exhibit, a visitor sees the artifact recognized in real time and can ask follow-up questions answered in English or Arabic. The work addresses three problems specific to in-gallery deployment: fine-grained visual similarity among 51 catalogued artifacts (many near-identical Ramesside statues), the gap between curated training data and handheld camera conditions, and the risk of an AI guide stating unsupported historical facts. Two engineering contributions are reported. First, an on-device artifact detector was developed through a data-quality-driven iteration study – from foundation-model auto-annotation (YOLO-World), through spatial label-cleaning rules, to a fully hand-annotated dataset – isolating label quality as the decisive factor: the final YOLOv8n model resolves every previously failing class while remaining a 5.97 MB TensorFlow Lite asset that runs in real time on a mid-range phone (mAP@0.5 = 0.995, mAP@0.5:0.95 = 0.924). Second, a bilingual Retrieval-Augmented Generation (RAG) guide, grounded in a 108-record ChromaDB knowledge base, was benchmarked across seven candidate language models, with Gemma 4 E2B (Q4 K M) selected; ten targeted optimizations reduce end-to-end latency from over 30 s to approximately 10 s. Both subsystems are integrated in a production Flutter application with bilingual interface, museum location gating, and text-to-speech support.

阅读与讨论 → 访问原文 →
05.
arXiv (CS.AI) 2026-06-16

Adaptive and Explicit safe: Triggering Latent Safety Awareness in Large Reasoning Models

作者:
Ke Miao↗Jiaxin Li↗Hongliang Chen↗Yuke Hu↗Zhan Qin↗

arXiv:2606.16808v1 Announce Type: new Abstract: While Large Reasoning Models (LRMs) excel at complex tasks, they remain highly vulnerable to sophisticated jailbreaks and direct harmful queries. To address this vulnerability, prior works depend heavily on external manual data annotation for safety alignment. However, we observe that LRMs can inherently identify safety risks when being re-presented with original queries alongside their own reasoning trajectories – a capability we term Latent Safety Awareness. To leverage this safety awareness, we first employ Supervised Fine-Tuning (SFT) to explicitly induce safe tags to trigger safety analysis and guidance following the initial reasoning content for unsafe queries, while preserving standard responses for general queries to ensure adaptive triggering. Subsequently, we apply Direct Preference Optimization (DPO) to further enhance the correctness and stability of the safety analysis and guidance. Notably, responses required for both training stages are entirely generated by models being optimized. With (Safe Trigger) SFT and DPO, experimental results demonstrate significant safety enhancement. For example, the Attack Success Rate (ASR) of DeepSeek-R1-Distill-Llama-8B, on average, drops 24.65% and 36.72% on harmful and jailbreak benchmarks, respectively. Finally, our Safe Trigger method exerts almost no negative impact on general performance or user experience.

阅读与讨论 → 访问原文 →
06.
arXiv (CS.CL) 2026-06-19

MENTOR: Reinforcement Learning via Flexible Teacher-Optimized Rewards for Tool-Use Distillation

作者:
ChangSu Choi↗Hoyun Song↗Dongyeon Kim↗WooHyeon Jung↗Minkyung Cho↗Sunjin Park↗NohHyeob Bae↗Seona Yu↗KyungTae Lim↗

Distilling the tool-use capabilities of large language models (LLMs) into small language models (SLMs) is essential for their practical application. The predominant approach, supervised fine-tuning (SFT), suffers from poor out-of-domain (OOD) generalization due to its rigid alignment with static teacher trajectories. While reinforcement learning (RL) offers an alternative, the capacity limitations of SLMs pose a severe dilemma: sparse outcome rewards provide insufficient guidance, whereas strict trajectory matching imposes overly restrictive constraints. To bridge this capacity-driven gap, we propose MENTOR, which introduces a flexible yet process-aware reward structure. Instead of enforcing rigid replication, MENTOR uses the teacher's reference to guide tool-use behavior, balancing behavioral alignment with downstream performance. Extensive experiments on controlled executable-tool benchmarks demonstrate that MENTOR improves OOD tool-use performance compared to SFT and strict RL baselines. Our findings suggest that within verifiable tool-use environments, flexible tool-use alignment offers a more effective approach than strict trajectory replication for developing adaptable small models.

阅读与讨论 → 访问原文 →
07.
medRxiv (Medicine) 2026-06-23

Default Handling of the Non-Assessable Verbal Glasgow Coma Scale Misclassifies Illness Severity in Mechanically Ventilated Patients: A Retrospective Analysis

作者:
Gorenshtein↗Adiniaev↗Omar↗Barash↗Klang↗Daniel↗

Background: The Glasgow Coma Scale (GCS) is a universal neurologic severity score in the intensive care unit and is incorporated into APACHE, SOFA, mortality prediction models, ICU benchmarking, and quality metrics. In mechanically ventilated patients, however, the verbal component cannot be assessed. Common conventions, including assigning a normal total GCS of 15 or excluding patients with missing verbal scores, may misclassify the sickest patients as neurologically normal or remove them from analysis. Objective: To quantify non-assessable verbal GCS examinations after acute brain injury and determine how different handling conventions affect severity scoring and mortality-model performance across two independent critical care databases. Materials and Methods: We conducted a retrospective cohort study of adults with acute brain injury during their first ICU stay in MIMIC-IV, with replication in eICU-CRD. A verbal examination was considered non-assessable when documented as No Response-ETT. We measured the burden and determinants of non-assessability, compared the MIMIC-IV derived GCS convention with a component-aware GCS, and evaluated mortality-model handling strategies. Results: Among 14,230 patients, 45.2% had a non-assessable verbal examination, and 47.5% of ventilated patients had no assessable verbal score in the first 24 hours. Non-assessability was strongly associated with mechanical ventilation and mortality. The MIMIC-IV derived GCS assigned a score of 15 to 42.9% of patients and placed 11.6% in the lowest severity category despite eye and motor findings consistent with GCS [&le;]9. Complete-case handling excluded 28.5% of patients, who accounted for 50.2% of deaths. Similar distortions were observed in eICU-CRD/APACHE across 171 hospitals. Discussion: Default-to-normal scoring can make severely ill intubated patients appear neurologically normal, while complete-case analysis removes the highest-risk patients. Conclusion: Non-assessable verbal GCS in mechanically ventilated patients should be explicitly flagged and reported in ICU severity scores, risk-adjusted mortality models, and benchmarking systems.

阅读与讨论 → 访问原文 →
08.
arXiv (CS.AI) 2026-06-11

Embodied-BenchClaw: An Autonomous Multi-Agent System for Embodied Spatial Intelligence Benchmark Construction

作者:
Baoyang Jiang↗Fengchun Zhang↗Leyuan Wang↗Haotian Li↗Yida Wang↗Zhe Ji↗Jinshan Lai↗Xi Ren↗Jianwei Hu↗Qiang Ma↗

arXiv:2606.11909v1 Announce Type: new Abstract: Benchmarks are essential for evaluating embodied spatial intelligence, yet their construction is labor-intensive, hard to reuse, and difficult to maintain. Existing embodied benchmarks are often static and may quickly become saturated as models improve, limiting their ability to distinguish new capabilities. We propose Embodied-BenchClaw, an autonomous agentic system for constructing embodied spatial intelligence benchmarks. Given a user-specified evaluation intent, Embodied-BenchClaw automatically produces a complete and continually updatable benchmark package through a five-stage pipeline: intent blueprinting, data collection, structuring and cleaning, benchmark synthesis, and evaluation reporting. The pipeline is coordinated by three agents for planning, construction, and evaluation. To improve reusability and reliability, Embodied-BenchClaw introduces an extensible Skill Library and process quality control, enabling benchmark construction to be composable, verifiable, and repairable. We instantiate multiple benchmarks covering indoor spatial reasoning, outdoor spatial reasoning, robotic manipulation, quadruped robot navigation, UAV/aerial-view understanding, and static benchmark enhancement. These benchmarks span diverse embodied carriers, data sources, and spatial capabilities. Experiments with human evaluation, judge-based assessment, consistency checks, cost analysis, and ablations show that Embodied-BenchClaw can construct verifiable, executable, maintainable, and diagnostically useful embodied spatial benchmarks with reduced manual effort.

阅读与讨论 → 访问原文 →
10.
arXiv (CS.AI) 2026-06-19

Latent Gaussian Splatting for 4D Panoptic Occupancy Tracking

作者:
Maximilian Luz↗Rohit Mohan↗Thomas N\"urnberg↗Yakov Miron↗Daniele Cattaneo↗Abhinav Valada↗

arXiv:2602.23172v2 Announce Type: replace-cross Abstract: Capturing 4D spatiotemporal scene structure is crucial for the safe and reliable operation of robots in dynamic environments. However, existing approaches typically address only part of the problem: they either provide coarse geometric tracking via bounding boxes or detailed 3D occupancy estimates that lack explicit temporal association and instance-level reasoning. In this work, we present Latent Gaussian Splatting (LaGS) for 4D Panoptic Occupancy Tracking (4D-POT). We revisit the underlying representation and model 3D features as a sparse set of feature-bearing Gaussians. These act as dynamic, volume-oriented keypoints that enable spatially continuous, distance-weighted aggregation of multi-view features before being splatted into a voxel grid for decoding. This point-centric formulation enables flexible, data-dependent receptive fields and long-range spatial interactions that are difficult to capture with local and dense voxel-based operators. A hierarchical Gaussian representation further enables multi-scale reasoning by combining global context from coarse super-points with fine-grained detail from higher-resolution streams. Extensive experiments on Occ3D nuScenes and Waymo demonstrate state-of-the-art performance for 4D-POT. We provide code and models at https://lags.cs.uni-freiburg.de/.

阅读与讨论 → 访问原文 →
11.
arXiv (CS.AI) 2026-06-12

HD-Prot: A Protein Language Model for Joint Sequence-Structure Modeling with Continuous Structure Tokens

作者:
Yi Zhou↗Haohao Qu↗Yunqing Liu↗Shanru Lin↗Le Song↗Wenqi Fan↗

arXiv:2512.15133v3 Announce Type: replace-cross Abstract: Proteins inherently possess a consistent sequence-structure duality. The abundance of protein sequence data, which can be readily represented as discrete tokens, has driven fruitful developments in protein language models (pLMs). A key remaining challenge, however, is how to effectively integrate continuous structural knowledge into pLMs. Current methods often discretize protein structures to accommodate the language modeling framework, which inevitably results in the loss of fine-grained information and limits the performance potential of multimodal pLMs. In this paper, we argue that such concerns can be circumvented: a sequence-based pLM can be extended to incorporate the structure modality through continuous tokens, i.e., high-fidelity protein structure latents that avoid vector quantization. Specifically, we propose a hybrid diffusion protein language model, HD-Prot, which embeds a continuous-valued diffusion head atop a discrete pLM, enabling seamless operation with both discrete and continuous tokens for joint sequence-structure modeling. It captures inter-token dependencies across modalities through a unified absorbing diffusion process, and estimates per-token distributions via categorical prediction for sequences and continuous diffusion for structures. Extensive results demonstrate that HD-Prot achieves competitive performance in unconditional sequence-structure co-generation, motif-scaffolding, protein structure prediction, and inverse folding tasks. Furthermore, our method can perform on par with state-of-the-art multimodal pLMs, despite being developed under limited computational resources (i.e., less than one-tenth the budget for modality extension fine-tuning). It highlights the viability of simultaneously estimating categorical and continuous distributions within a unified language model architecture, offering a promising alternative direction for multimodal pLMs.

阅读与讨论 → 访问原文 →
12.
arXiv (CS.CL) 2026-06-18

CoreMem: Riemannian Retrieval and Fisher-Guided Distillation for Long-Term Memory in Dialogue Agents

作者:
Jiaqi Chen↗Yongqin Zeng↗Shaoshen Chen↗Yijian Zhang↗Hai-Tao Zheng↗Chunxia Ma↗XiuTeng Zhou↗

Personalized dialogue agents require continuous long-term memory to maintain coherent interactions across multiple sessions. However, deploying these capabilities on consumer-grade hardware (e.g., 8 GB VRAM edge devices) introduces severe memory and compute bottlenecks. Existing systems typically rely on isotropic cosine similarity for retrieval and heuristic rules for context compression. These approaches lack a unified theoretical foundation, frequently suffering from the hubness problem in high-dimensional retrieval and syntactic fragmentation during compression. To overcome these limitations, we propose CoreMem, a resource-efficient edge-cloud memory architecture fundamentally unified by information geometry. First, Riemannian retrieval replaces cosine matching with a locally adaptive Fisher-Rao metric, effectively penalizing hub memories via Mahalanobis distance with O(Ndr) Woodbury acceleration for real-time search. Second, Fisher-guided discrete token distillation (FDTD) introduces a hierarchical sentence-to-token compression mechanism. It derives sensitivity scores from Fisher information traces, providing a principled compression-KL tradeoff augmented with explicit structural syntax protection. Evaluated on the LOCOMO and LongMemEval-S benchmarks, CoreMem achieves strong accuracy improvements, yielding substantial gains in Open-domain (+4.51 pp) and Temporal (+4.17 pp) reasoning. Extensive profiling confirms that CoreMem operates seamlessly within a strict 8 GB VRAM budget, successfully bridging the gap between resource-constrained edge devices and the demand for theoretically grounded, lifelong memory agents.

阅读与讨论 → 访问原文 →
13.
arXiv (CS.LG) 2026-06-12

Crossing the Validation Crisis: Cross-Validation Reduces Benchmarking Variance Surprisingly Well

作者:
C\'elestin Eve↗Ga\"el Varoquaux↗Thomas Moreau↗

arXiv:2606.12552v1 Announce Type: new Abstract: Modern machine learning progresses through empirical work, benchmarking new methods to evaluate relative performance. However, the statistical variability inherent to evaluation - exacerbated by the stochastic nature of many algorithms - often makes performance estimation unreliable due to the limited test samples available, leading to a validation crisis in which genuine advances are difficult to discern. In this work, we show that cross-validation improves markedly confidence when evaluating and comparing learning algorithm performances. We introduce the concept of sample gain, which quantifies the virtual data augmentation achieved by using multiple cross-validation splits to reduce benchmarking variance. Experiments on both synthetic and real-world datasets (histopathologic scans and NLP fine-tuning) demonstrate that multiple splits can substantially improve the reliability and stability of performance estimates, with diminishing returns often setting in later than expected. We also introduce a procedure to dynamically early-stop cross-validation by estimating from the first few folds if subsequent folds will bring large sample gains. Our findings highlight the value of pushing cross-validation on available samples to achieve robust and reliable benchmarking.

阅读与讨论 → 访问原文 →
14.
arXiv (CS.LG) 2026-06-18

The Chandra-Gaia Catalog of Counterparts: Resolving ambiguous Gaia matches to X-ray sources in the Chandra Source Catalog using Machine Learning

作者:
V. Samuel P\'erez-D\'iaz↗Vinay L. Kashyap↗Joshua D. Ingram↗David Fouhey↗Juan Rafael Mart\'inez-Galarza↗Pavlos Protopapas↗Jeremy J. Drake↗Dong-Woo Kim↗Cecilia Garraffo↗

arXiv:2606.19329v1 Announce Type: cross Abstract: We present a framework to cross-match sources from the Chandra Source Catalog (CSC v2.1) with optical sources from Gaia Data Release 3. Unlike purely spatial approaches, we use source properties such as magnitudes, colors, and distances to identify true counterparts, detect chance coincidences, and resolve ambiguities when multiple plausible candidates exist. We define a training set of high-confidence matches using NWAY, a Bayesian cross-matching framework that accounts for positional errors and source densities. We train a gradient-boosted classifier (LightGBM) on a variety of features from both catalogs. Of the ~$254$k unique X-ray sources, we find counterparts for ~$113$k sources, of which plausible multiple counterparts are found for ~$7$k. We find no counterparts for ~$20$k sources for which separation-based cross-matching does find a match, and attribute half of these to chance coincidences. We validate the pipeline on the Chandra Orion Ultradeep Project (COUP), where the machine-learning matches reproduce 95% of NWAY cross-matches without using any positional information. We release a catalog of the ~$113$k Chandra-Gaia counterparts, together with ~$7$k alternative matches and ~$20$k ambiguous NWAY associations, supporting future population studies of sources detectable by both Chandra and Gaia. We discuss limitations and provide a generalization of the framework that is applicable in other cross-matching scenarios.

阅读与讨论 → 访问原文 →
15.
arXiv (quant-ph) 2026-06-11

Residual-Squeezing Mechanism of Mismatch in Inverse-Squeezing Kennedy Receivers

作者:
Enhao Bai↗Fengkai Sun↗Tianyi Wu↗Yang Ran↗Zichao Zhou↗Huankai Zhang↗Jian Peng↗Chen Dong↗Laiyuan Tong↗Zhenrong Zhang↗Yaping Li↗

arXiv:2601.19093v4 Announce Type: replace Abstract: The discrimination of quantum states is fundamental to quantum information processing. Inverse-squeezing Kennedy (IS-Kennedy) receivers can outperform the coherent-state BPSK Helstrom benchmark at the same energy by converting transmitter-side squeezing into an effective coherent-state separation gain, without violating the Helstrom bound for the squeezed-state alphabet. This work investigates how squeezing mismatch degrades this mechanism. We show that imperfect inverse squeezing transforms the ideally nulled output into a residually squeezed state, thereby altering the photon-number statistics before detection. This residual-squeezing picture reveals a strong physical asymmetry between squeezing-magnitude and squeezing-phase mismatches. Magnitude mismatch produces an energy-independent error floor in the high-signal-energy regime, whereas phase mismatch generates a residual squeezing term that grows with signal energy. In the small-residual-squeezing regime, this leads to a polynomial growth of the leading error contribution and a rapid collapse of the SQL advantage. We also identify a parity-step effect in photon-number-resolving detection: because the nulled residual squeezed vacuum contains only even photon numbers, increasing detector resolution improves the high-energy robustness only when the effective saturation threshold crosses the next even photon number. These results identify phase locking as the dominant bottleneck for IS-Kennedy-type non-Gaussian receivers under unitary squeezing mismatch and provide design guidelines for robust squeezed-state quantum receivers.

阅读与讨论 → 访问原文 →
16.
arXiv (CS.CV) 2026-06-15

ForceForget: Reinforcement Concept Removal for Enhancing Safety in Text-to-Image Models

作者:
Dong Han↗Yong Li↗

With the advance of generative AI, the text-to-image (T2I) model has the ability to generate various contents. However, T2I models still can generate unsafe contents. To alleviate this issue, various concept erasing methods are proposed. However, existing methods tend to excessively erase unsafe concepts and suppress benign concepts contained in harmful prompts, which can negatively affect model utility. In this paper, we focus on eliminating unsafe content while maintaining model capability in safe semantic meaning interpretation by optimizing the concept erasing reward (CER) with reinforcement learning. To avoid overly content erasure, we introduce the Safe Adapter to project partial text embedding for efficient concept regulation in cross-attention layers. Extensive experiments conducted on different datasets demonstrate the effectiveness of the proposed method in alleviating unsafe content generation while preserving the high fidelity of benign images compared with existing state-of-the-art (SOTA) concept erasing methods. In terms of robustness, our method outperforms counterparts against red-teaming tools. Moreover, we showcase the proposed approach is more effective in emerging image-to-image (I2I) scenarios compared with others. Lastly, we extend our method to erase general concepts, such as artistic styles and objects. Disclaimer: This paper includes discussions of sexually explicit content that may be offensive to certain readers. All images used in this work are synthesized or from public datasets.

阅读与讨论 → 访问原文 →
17.
arXiv (CS.AI) 2026-06-18

RODS: Reward-Driven Online Data Synthesis for Multi-Turn Tool-Use Agents

作者:
Ruishan Fang↗Siyuan Lu↗Chenyi Zhuang↗Tao Lin↗

arXiv:2606.19047v1 Announce Type: new Abstract: Multi-turn tool-use RL is bottlenecked by the rapid depletion of informative samples in static datasets. We observe that the gradient signal in GRPO concentrates on tasks with the highest rollout reward variance, a consequence of the Popoviciu upper bound. Consequently, samples near the agent's capability boundary – where successes and failures are roughly balanced – contribute disproportionately large policy gradients. As training progresses, this boundary continuously shifts, which gradually depletes the pool of informative samples in a static dataset. We propose RODS (Reward-driven Online Data Synthesis) to resolve this depletion. RODS closes the loop between RL training and data generation by repurposing the progress reward variance as a practical, zero-cost boundary detector that requires no extra inference beyond the rollouts already computed for training. It continuously identifies such boundary samples, synthesizes new multi-turn variants matching their structural complexity (e.g., API topology and dependency depth) via a skill-aligned resampling pipeline, and manages a dynamic replay buffer that co-evolves with the policy. Starting from 400 human seeds and maintaining an active training pool of ~800 samples, RODS achieves comparable performance to a 17K-sample offline pipeline while requiring roughly 20x fewer trajectories, and improves over fixed-data RL and environment augmentation in our controlled setting.

阅读与讨论 → 访问原文 →
18.
arXiv (CS.CV) 2026-06-18

Seeing Before Reasoning: Decoupling Perception and Reasoning for Shortcut-Resilient Multimodal On-Policy Self-Distillation

作者:
Sihan Wang↗Xiyao Liu↗Lianqing Liu↗Zhi Han↗

On-policy self-distillation (OPSD) trains a model on its own rollouts and uses a frozen copy to provide dense token-level targets conditioned on a reference target. This works well for LLM reasoning, but a direct extension to multimodal large language models (MLLMs) can create a shortcut: the privileged target may guide tokens mainly based on the text reference target rather than the image. We propose ViGOS, a visually grounded OPSD framework for MLLM post-training. The student first writes a visual description and then reasons toward the final answer. For valid rollouts, an image-only perception teacher supervises the description, while a privileged reasoning teacher supervises the reasoning and final answer on the same student prefix. A reference teacher is used only for invalid rollouts to recover the output format. Across general vision-language, expert reasoning, visual math, spatial grounding, and visual-language-prior benchmarks, ViGOS keeps the main benefits of OPSD and improves image-grounded behavior in shortcut-prone settings.

阅读与讨论 → 访问原文 →
19.
arXiv (CS.LG) 2026-06-16

Agent trajectories as programs: fingerprinting and programming coding-agent behavior

作者:
Hamidah Oderinwale↗

arXiv:2606.16988v1 Announce Type: cross Abstract: Benchmark scores tell you what an agent got right; they do not tell you how it got there. In this work, we introduce methods for comparing agents procedurally in different contexts, where the model, tasks, and approaches vary. We compare ten agents and find that they are identifiable by their behavioral habits, which we define as fingerprints: a probe over these procedural signatures attributes an unseen trajectory to the correct agent at 85.7% accuracy, controlling for leakage across tasks. We develop procedural representations for agent problem-solving procedures with an emergent vocabulary induction technique that is meant to be maximally compressive to avoid surface-level variation while being expressive enough to unveil the quirks of the models' patterns. We apply our framework to the software engineering evaluation dataset SWE-Bench to study the structural distinctness of agent trajectories and find that behavior is most similar between models from similar release periods and those that are distilled from one another (e.g., a distilled student model and its teacher have a Jensen-Shannon divergence of 0.25, about half the distance between other model pairs). As more models saturate evaluations, we believe that it will be important to probe model behavior along more holistic dimensions than success rates alone. We introduce ProcGrep, a library for auditing and evaluating agents for how they approach tasks at a procedural level given their traces in a top-down fashion. We believe this work has a range of applications to help developers work with and program coding agents, such as task-aware model routing, agent monitoring, and finer-grained cost analysis.

阅读与讨论 → 访问原文 →
20.
PLOS Computational Biology 2026-06-16

Evolution and the ultimatum game: An agent-based model with interbirth intervals and population structure

作者:
Jeffrey C. Schank↗

by Jeffrey C. Schank, Matt L. Miller The ultimatum game (UG) is widely used to study mutually beneficial exchanges, fairness, and prosocial behavior across different societies. However, human behavior in UG experiments does not align with the game-theoretical prediction that proposers should offer the least positive amount and responders should accept such offers. Instead, proposers make generous offers that are greater than the minimum responders are willing to accept, resulting in generous offers with wide offer-acceptance gaps. Numerous evolutionary models of the UG have been created and studied to explain human behavior, particularly generous offers made in UG experiments. These models have recently faced criticism for lacking biological realism and not adequately explaining the data. Here, we present an agent-based model inspired by our hunter-gatherer ancestors and with a biologically more realistic selection process. We assume that (1) agents exist in group-structured and group-clustered populations, where reproduction (2) depends on resource accumulation, but (3) is limited by interbirth intervals. We ran simulations to assess whether this biologically more realistic model evolves patterns of behavior consistent with patterns in the data from meta-analyses of human behavior in the UG. For the proposed model, we show that generous offers robustly evolve, as well as the difficult-to-explain offer-acceptance gaps, only in group-structured populations with interbirth intervals. We demonstrate that these results are robust and may help explain variation in data across societies. We discuss how interbirth intervals interact with group structure to modulate offer and rejection costs, favoring the evolution of generous offers, offer-acceptance gaps, and other patterns in the data on human behavior in the UG. We also discuss why weak selection and/or high mutation rate models cannot explain all the patterns in UG experimental data. We discuss biological realism and conclude that group structure and interbirth intervals may be essential for explaining prosocial behavior across societies.

阅读与讨论 → 访问原文 →
22.
arXiv (CS.LG) 2026-06-11

Critic Architecture Matters: Dual vs. Unified Critics for Humanoid Loco-Manipulation

作者:
Mehmet Turan Yard{\i}mc{\i}↗

arXiv:2606.11891v1 Announce Type: cross Abstract: Multi-objective reinforcement learning for humanoid robots must coordinate locomotion and manipulation within a single policy. A natural design choice is whether to use a single (unified) critic that estimates the combined value of all objectives, or separate (dual) critics with disjoint reward signals. We present a controlled comparison on the Unitree G1 humanoid (23 active DoF) in NVIDIA Isaac Lab, training loco-manipulation policies through a sequential curriculum spanning 13 levels from stationary reaching to walking with variable-orientation targets. In standardized evaluation, dual-critic policies reach targets 3.5$\times$ faster (6.5 vs. 22.6 simulation steps), achieve 2$\times$ higher throughput (14.3 vs. 7.0 validated reaches per 1,000 steps), and attain higher validated reach rates (65.2% vs. 53.8%) compared to the unified-critic policy. Notably, additional anti-gaming reward mechanisms provide no further improvement beyond the architectural change alone (60.9% vs. 65.2%). These results have direct implications for the emerging paradigm of RL fine-tuning of imitation-learned policies: when refining a pre-trained manipulation policy with RL, a unified critic risks suppressing the learned behavior through competing locomotion gradients. These findings demonstrate that critic architecture is a primary - and often overlooked - design choice in multi-objective humanoid RL, with greater impact than reward engineering on reaching efficiency.

阅读与讨论 → 访问原文 →
23.
arXiv (CS.AI) 2026-06-11

A Resilient Solution for Sewer Overflow Monitoring across Cloud and Edge

作者:
Vipin Singh↗Tianheng Ling↗Peter Ghaly↗Felix Grimmeisen↗Gregor Schiele↗Felix Biessmann↗

arXiv:2605.10592v2 Announce Type: replace Abstract: Aging combined sewer systems in many historical cities are increasingly stressed by extreme rainfall events, which can trigger combined sewer overflows (CSO) with significant environmental and public health impacts. Forecasting the filling dynamics of overflow basins is critical for anticipating capacity exceedance and enabling timely preventive actions for CSO. We present a web-based demonstrator that integrates Deep Learning forecasting methods in both cloud and edge settings into an interactive monitoring dashboard for overflow monitoring, resilient to network outages. A video showcase is available online (https://cloud.bht-berlin.de/index.php/s/b9xt4T3SdiLBiFZ).

阅读与讨论 → 访问原文 →
24.
arXiv (quant-ph) 2026-06-16

Fuzzy-processing quantum computation

作者:
Yan-Xiong Du↗

arXiv:2606.16623v1 Announce Type: new Abstract: Quantum computation has attracted numerous attentions and develops rapidly in the recent decades. To against the decoherence and the control errors upon the qubits, quantum error corrections are adopted. Such approaches require lots of redundant qubits, accurate measurement and timely feedback. Here we investigate a new framework of quantum computation that is associated with fuzzy processing. It will benefit significantly from three aspects: the fuzzy recognition of qubit states reduce the required gate fidelity; the fuzzy encoding encodes the information of the qubits into a distribution of probability, suppressing the fluctuations in the output of long quantum circuits; the fuzzy feedback offers a more efficient way to control the qubits when precision information of quantum states are absent. Furthermore, the fuzzy processing can be integrated into quantum error correction, eliminating the need for immediate correction operations. The proposed scheme will be fairly suitable for the solution of decision problems, which has significant applications in the optimization problems and control problems.

阅读与讨论 → 访问原文 →