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.
arXiv (CS.AI) 2026-06-11

Search Discipline for Long-Horizon Research Agents

作者:
Adithya Srinivasan↗Devesh Paragiri↗

arXiv:2606.11522v1 Announce Type: new Abstract: Autoresearch agents now propose, evaluate, and select scientific candidates against a metric, and that metric is usually an aggregate reduced over a heterogeneous space of regions, slices, or cohorts. We show that when scientific validity lives in that disaggregated structure, the aggregate can rank the wrong candidate first. The headline number improves while the structure underneath inverts, so a decision made on the number accepts a candidate that quietly breaks the model. The failure is not domain-specific. It appears wherever a candidate's validity is multi-dimensional but its verifier is a single reduction. We demonstrate the inversion on a fire-model task in the Ecosystem Demography model. The highest-scoring candidate and a slightly lower one are within noise of each other on global score, yet the top-scoring one collapses the protected boreal regions while the other preserves them. What separates them is the per-region behavior, not the headline number. This decision should not be left to the agent that produced the candidates. The agent optimizing the score is the last party likely to catch the score being wrong, and a prompt has no remaining turn once the agent has stopped. We move the decision to an external control loop that audits each candidate on its disaggregated behavior and acts after the agent has decided. It can demote a candidate the agent would have accepted, and it can reopen a run the agent had declared finished. Our contribution is the inversion finding itself, and a search-discipline protocol that decides on reviewable candidate-effect evidence instead of the score.

阅读与讨论 → 访问原文 →
02.
arXiv (CS.AI) 2026-06-17

ParkingTransformer: LLM-Enhanced End-to-End Trajectory Planning for Autonomous Parking

作者:
Hauteng Wu↗Xu Li↗Dong Kong↗Zihang Wang↗Xieyuanli Chen↗Benwu Wang↗Wenkai Zhu↗

arXiv:2606.17082v1 Announce Type: cross Abstract: End-to-end autonomous parking has emerged as a critical task within the realm of autonomous driving. However, existing methods suffer from black-box characteristics, lacking high-level semantic understanding and interpretability, which impedes the realization of seamless long-distance autonomous parking from the road to the target spot. To address these limitations, we propose ParkingTransformer, a novel framework that leverages multi-view perception and the scene understanding capability of Large Language Models (LLMs). By combining trajectory queries with LLMs implicit state features, our method interacts directly with historical information and raw sensor data to output planning trajectories, eliminating the need for dense Bird's-View (BEV) representations. To compensate for the inadequate spatial reasoning ability of LLMs, we introduce 3D positional encoding to explicitly inject spatial geometric awareness. Furthermore, a fixed-window streaming mechanism is designed for historical information processing, significantly improving long-term temporal processing efficiency and inference speed. Additionally, a coarse-to-fine decoding strategy is employed to progressively enhance trajectory precision. Extensive closed-loop experiments are conducted on the CARLA simulator and real-world vehicle platforms. The results demonstrate that our method achieves a driving score of 61.32 in CARLA simulator and an average success rate of 88.70% in real-world experiments, validating the feasibility and effectiveness of the proposed algorithms.

阅读与讨论 → 访问原文 →
03.
arXiv (CS.AI) 2026-06-15

Selective Agentic Recovery for UAV Autonomy with a Persistent Mission Runtime

作者:
Taewoo Park↗Kyeonghyun Yoo↗Seunghyun Yoo↗Hwangnam Kim↗

arXiv:2606.14219v1 Announce Type: cross Abstract: Agentic AI can support unmanned aerial vehicle (UAV) autonomy by providing high-level recovery reasoning when local waypoint- or setpoint-based execution encounters blocked passages, repeated no-progress behavior, or mission-level ambiguity. On physical UAVs, however, remote reasoning is most useful when it is invoked selectively, since each call introduces latency, resource cost, backend uncertainty, and a need to validate the returned decision. This paper presents Persistent Mission Runtime (PMR), a UAV recovery framework that keeps the mission loop and safety-critical execution local while using an external agentic reasoner only as an on-demand recovery module. The reasoner selects from predefined recovery skills, and each returned decision is parsed, verified, safety-filtered, and mapped to local executor actions before it can affect flight. PMR introduces learned Cognitive Value of Invocation (learned-CVI), a compact admission gate that estimates when remote agentic reasoning is likely to improve near-term mission progress enough to justify its operational cost. Across a fixed 400-run Gazebo/PX4 benchmark with eight scenarios, learned-CVI raises hard/ambiguous-regime success from 5.0% under local-only autonomy to 95.0%, outperforms one-shot and periodic reasoning baselines by 20.0 and 32.5 percentage points, and reduces remote-agent calls by 16.7% and logged tokens by 29.2% relative to a manually tuned rule-based invocation baseline.

阅读与讨论 → 访问原文 →
04.
arXiv (CS.CL) 2026-06-17

Compositional Skill Routing for LLM Agents: Decompose, Retrieve, and Compose

作者:
Xueping Gao↗

LLM agents increasingly rely on external skills – reusable tool specifications – but real-world tasks often require composing multiple skills, not just selecting one. We formalize this as the Compositional Skill Routing problem: given a complex user query and a large skill library, decompose the query into atomic sub-tasks, retrieve the appropriate skill for each sub-task, and compose an executable plan. We present SkillWeaver, a decompose-retrieve-compose framework combining an LLM task decomposer, a bi-encoder skill retriever with FAISS indexing, and a dependency-aware DAG planner. To support evaluation, we introduce CompSkillBench, a benchmark of 300 compositional queries over 2,209 real MCP server skills spanning 24 functional categories, sourced from the public MCP ecosystem. Our experiments reveal that task decomposition quality is the primary bottleneck: standard LLM decomposition reaches only 34.2% category recall at the step level. To address this, we propose Iterative Skill-Aware Decomposition (SAD), a retrieval-augmented feedback loop that iteratively aligns decomposition with available skills. SAD improves decomposition accuracy from 51.0% to 67.7% (+32.7%, Wilcoxon p < 10^-6) in a single iteration; DA-conditioned analysis confirms that correct granularity is the prerequisite for effective retrieval (CatR@1 rises from 34% to 41% when DA=1). SkillWeaver reduces context window consumption by over 99%, and transfer experiments confirm generalization (+35.6% relative DA gain even when target categories are absent from the retrieval pool).

阅读与讨论 → 访问原文 →
05.
arXiv (CS.CL) 2026-06-12

Getting Better at Working With You: Compiling User Corrections into Runtime Enforcement for Coding Agents

作者:
Yujun Zhou↗Kehan Guo↗Haomin Zhuang↗Xiangqi Wang↗Yue Huang↗Zhenwen Liang↗Pin-Yu Chen↗Tian Gao↗Nuno Moniz↗Nitesh V. Chawla↗Xiangliang Zhang↗

Interactive LLM agents are becoming part of daily work, but they do not reliably become easier to work with over time: a correction remembered in one session may still be violated in the next. We study this gap between preference access and preference compliance. In tasks derived from anonymized real-user friction cases, Mem0 memory still leaves 57.5% of applicable preference checks violated. We introduce Test-time Rule Acquisition and Compiled Enforcement (TRACE), a drop-in skill-layer pipeline for coding-agent runtimes that mines user corrections, rewrites them as atomic rules, and compiles them into runtime checks that must pass before an agent completes future tasks. Unlike runtime checks written ahead of time by developers, TRACE skills come from the user's own chat corrections. We evaluate TRACE with simulated user-in-the-loop experiments on ClawArena coding-agent tasks and MemoryArena-derived memory-intensive tasks. On ClawArena, TRACE reduces held-out preference violation from 100.0% to 37.6% on in-distribution tasks and from 100.0% to 2.0% on out-of-distribution tasks. On MemoryArena-derived tasks, TRACE reduces in-distribution violation from 100.0% to 60.5% while matching or exceeding the strongest memory baseline on task pass. These results suggest that compiling corrections into runtime enforcement can address a repeated-friction failure mode that memory alone does not reliably solve, reducing the need for users to restate the same correction across future sessions. Experiment code is available at https://github.com/YujunZhou/TRACE_exp, and the deployable skill is available at https://github.com/YujunZhou/tellonce.

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

Too long; didn't solve

作者:
Luc\'ia M. Cabrera↗Isaac Saxton-Knight↗Jocelyn D'Arcy↗

arXiv:2604.07593v2 Announce Type: replace Abstract: Mathematical benchmarks consisting of a range of mathematics problems are widely used to evaluate the reasoning abilities of large language models, yet little is known about how their structural properties influence model behaviour. In this work, we investigate two structural length variables, prompt length and solution length, and analyse how they relate to model performance on a newly constructed adversarial dataset of expert-authored mathematics problems. We find that both prompt and solution lengths correlate positively with increased model failure across models. We also include a secondary, exploratory analysis of cross-model disagreement. Under a difficulty-adjusted normalised analysis, both variables retain weak negative associations with realised model separation, slightly stronger for prompt length. Overall, our main robust finding is that structural length is linked to empirical difficulty in this dataset.

阅读与讨论 → 访问原文 →
07.
arXiv (quant-ph) 2026-06-19

Thermodynamic Value of XOR-Game-Induced Side Information in a Szilard Engine

作者:
Piotr \'Cwikli\'nski↗

arXiv:2605.12044v3 Announce Type: replace Abstract: We introduce a Szilard-type thermodynamic valuation of side-information channels induced by Bell-type correlations. In each round, a two-level working system is thermalized with a degenerate Hamiltonian, so that its physical microstate is a uniform classical bit. A trusted referee embeds this bit into a finite two-player XOR game, and a correlation resource produces a compressed controller bit. The controller uses only this compressed bit as side information for feedback. The construction is formulated first for arbitrary finite XOR games. The referee encoding makes the game-winning event equivalent to correct prediction of the physical microstate. Consequently, the induced side-information channel is binary symmetric, with success probability equal to the XOR-game winning probability of the supplied behaviour. The reversible Szilard feedback value is therefore fixed by the mutual information between the microstate and the controller record. Optimizing over local, quantum, and nonsignalling behaviour sets turns the corresponding game values into local, quantum, and nonsignalling thermodynamic ceilings. The construction is an effective-channel valuation, not a claim that Bell nonlocality is thermodynamic fuel. The controller receives only the compressed prediction bit, not the auxiliary variables that define the game. The thermodynamic costs of the referee, the correlation resource, and the preprocessing are not included. When controller-memory reset is included in a full cycle, the net work is non-positive, consistently with the second law.

阅读与讨论 → 访问原文 →
08.
arXiv (CS.LG) 2026-06-12

Smarter Saboteurs, Better Fixers: Scaling & Security in Linear Multi-Agent Workflows

作者:
Timothy McAllister↗Sina Abdidizaji↗Ivan Garibay↗Ozlem Ozmen Garibay↗

arXiv:2606.12709v1 Announce Type: cross Abstract: As LLM-based multi-agent systems (MAS) are deployed in the wild, the resilience of their collaboration structures against adversarial compromise becomes a critical safety concern. Attackers may leverage prompt-injection or jailbreaking to sabotage individual agents within MAS workflows, but the interaction between model scaling and system-level resilience remains poorly understood. This paper investigates how model scale affects the security of linear multi-agent workflows. Our experiments across scales of two open-weight model families on the HumanEval benchmark reveal a compliance-correction symmetry: larger models are far more likely to faithfully execute malicious instructions, with the control-to-malicious performance drop reaching 53.7pp at 27B in uncorrected pipelines. However, appending a lightweight terminal Fixer stage collapses this to 0.6pp and restores statistical parity with control-level performance, demonstrating that strictly linear collaboration structures can be viable and resilient to adversaries at this scale, and suggesting that the brittleness previously attributed to linear topology may stem from a lack of correction.

阅读与讨论 → 访问原文 →
09.
arXiv (CS.CV) 2026-06-15

A Multi-Domain Feature Fusion Framework for Generalizable Deepfake Detection Across Different Generators

作者:
Amna Amjid↗Sana Qadir↗Mehwish Fatima↗Raja Khurram Shahzad↗

Deepfakes are artificially generated images, audio, or videos that threaten privacy, security, and information integrity. Detecting such content is crucial for countering disinformation, as the latest models generate highly realistic content. While spatial- or frequency-based approaches achieve good detection rates on Generative Adversarial Networks (GANs)-based generated deepfakes, they often struggle with recent diffusion model-generated images. In particular, existing approaches rarely exploit complementary multi-domain representations or systematically evaluate cross-generator robustness. To address these challenges, we propose a multi-domain deepfake detection framework called SGFF-Net (Spatial-Gradient-Frequency Fusion Network) that integrates spatial, gradient, and DWT (Discrete Wavelet Transform)-based frequency representations within a dual residual learning architecture. Experimental results show that the SGFF-Net achieves 98.95\% accuracy in intra-dataset evaluation and improves performance in both cross-model (70.46\%) and cross-paradigm (69.94\%) settings. Incorporating multi-source training and data augmentation further enhances robustness, increasing accuracy from 70.46\% to 79.80\% in cross-model evaluation, from 69\% to 78\% in cross-paradigm evaluation, and from 61.50\% to 75.80\% on real-world data. Unlike single-domain detectors, the SGFF-Net learns complementary forensic cues across spatial, gradient, and wavelet-frequency domains, resulting in greater robustness under cross-generator and cross-paradigm evaluation. The results further show that combining multi-domain representations with data diversity and augmentation substantially improves generalization, providing practical insights for developing more reliable deepfake detection systems.

阅读与讨论 → 访问原文 →
10.
arXiv (CS.AI) 2026-06-16

Why Low-Precision Transformer Training Fails: An Analysis on Flash Attention

作者:
Haiquan Qiu↗Quanming Yao↗

arXiv:2510.04212v4 Announce Type: replace-cross Abstract: The pursuit of computational efficiency has driven the adoption of low-precision formats for training transformer models. However, this progress is often hindered by notorious training instabilities. This paper provides the first mechanistic explanation for a long-standing and unresolved failure case where training with flash attention in low-precision settings leads to catastrophic loss explosion. Our in-depth analysis reveals that the failure is not a random artifact but caused by two intertwined phenomena: the emergence of similar low-rank representations within the attention mechanism and the compounding effect of biased rounding errors inherent in low-precision arithmetic. We demonstrate how these factors create a vicious cycle of error accumulation that corrupts weight updates, ultimately derailing the training dynamics. To validate our findings, we introduce a minimal modification to the flash attention that mitigates the bias in rounding errors. This simple change stabilizes the training process, confirming our analysis and offering a practical solution to this persistent problem. Code is available at https://github.com/ucker/why-low-precision-training-fails.

阅读与讨论 → 访问原文 →
11.
arXiv (CS.CV) 2026-06-18

DreamReg: Belief-Driven World Model for 2D-3D Ultrasound Registration

作者:
Luoyao Kang↗Yuelin Zhang↗Jiwei Shan↗Haifan Gong↗Qingpeng Ding↗Shing Shin Cheng↗

Ultrasound (US) is widely used for surgical navigation, yet real-time registration between intraoperative 2D slices and preoperative 3D volumes remains challenging due to partial observability, speckle noise, and the action-dependent US acquisition. Existing methods are one-shot or short-horizon, making it hard for them to gather evidence over time or capture how surgeons adjust probe motion based on on-screen feedback. We propose DreamReg, a belief-driven world-model framework that formulates 2D-3D registration as belief updating over rigid transformations. DreamReg maintains a latent belief state that summarizes past observations and poses information, and continuously refines the transformation through learned dynamics as new slices arrive. During training, DreamReg is exposed to probe-motion trajectories that mimic clinical scanning behavior and learns to update its belief by conditioning pose refinement on the current US observation. During inference, DreamReg refines registration via internal imagination: it rolls out the learned world model to simulate candidate probe motions and their predicted observations, and integrates these imagined outcomes to converge to an accurate rigid transformation. Experiments on CAMUS and u-RegPro datasets demonstrate improved robustness and competitive registration accuracy for real-time guidance compared with state-of-the-art methods.

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

Improve Large Language Model Systems with User Logs

作者:
Changyue Wang↗Weihang Su↗Qingyao Ai↗Xingzhao Yue↗Rui Zhang↗Xiaojia Chang↗Yiqun Liu↗

Scaling training data and model parameters has long driven progress in large language models (LLMs), but this paradigm is increasingly constrained by the scarcity of high-quality data and diminishing returns from rising computational costs. As a result, recent work is increasing the focus on continual learning from real-world deployment, where user interaction logs provide a rich source of authentic human feedback and procedural knowledge. However, learning from user logs is challenging due to their unstructured and noisy nature. Vanilla LLM systems often struggle to distinguish useful feedback signals from noisy user behavior, and the disparity between user log collection and model optimization (e.g., the off-policy optimization problem) further strengthens the problem. To this end, we propose UNO (User log-driveN Optimization), a unified framework for improving LLM systems (LLMsys) with user logs. UNO first distills logs into semi-structured rules and preference pairs, then employs query-and-feedback-driven clustering to manage data heterogeneity, and finally quantifies the cognitive gap between the model's prior knowledge and the log data. This assessment guides the LLMsys to adaptively filter out noisy feedback and construct different modules for primary and reflective experiences extracted from user logs, thereby improving future responses. Extensive experiments show that UNO achieves state-of-the-art effectiveness and efficiency, significantly outperforming Retrieval Augmented Generation (RAG) and memory-based baselines. We have open-sourced our code at https://github.com/bebr2/UNO .

阅读与讨论 → 访问原文 →
13.
arXiv (CS.CL) 2026-06-11

On the Optimal Reasoning Length for RL-Trained Language Models

作者:
Daisuke Nohara↗Taishi Nakamura↗Rio Yokota↗

Reinforcement learning substantially improves reasoning in large language models, but it also tends to lengthen chain-of-thought outputs and increase computational cost. Although length-control methods have been proposed, the length-accuracy relationship they induce remains unclear. We train policies with several length-control methods on multiple base models in a controlled setup and find that, across both mathematical reasoning and code generation, accuracy is non-monotonic in output length, peaking at an intermediate value. Mode accuracy, however, continues to improve with length even in settings where sample accuracy plateaus or declines, indicating that the non-monotonic length-accuracy relationship is driven by dispersion around an increasingly correct center.

阅读与讨论 → 访问原文 →
14.
medRxiv (Medicine) 2026-06-22

Demographic Calibration Gaps in Breast Cancer Risk Prediction: Introducing the Demographic Calibration Gap Score

作者:
Eniolade↗

ABSTRACT: Most breast cancer prediction studies skip calibration reporting entirely. Fewer still examine calibration by demographic subgroup. Predicted probabilities that are systematically off for specific racial or gender groups produce biased clinical decisions, and aggregate statistics will not catch that. Objective: To introduce the Demographic Calibration Gap Score (DCGS), a metric that measures how much calibration error varies across demographic subgroups, and to show how it performs across five classifiers, four calibration conditions, and two datasets. Methods: Five classifiers were trained on the Wisconsin Diagnostic Breast Cancer dataset (n=569) and evaluated on a breast cancer cohort from MIMIC-IV (n=1,316). Three global calibration methods were applied: no calibration, Platt scaling, and isotonic regression. A fourth condition, subgroup-targeted Platt scaling, was applied to the MIMIC cohort. DCGS was computed as across racial and gender subgroups, with 95% bootstrap confidence intervals. Conformal prediction coverage and Demographic Coverage Gap (DCG) were reported. Results: On Wisconsin, all five models achieved AUROC above 0.98 and ECE below 0.12. Performance fell sharply on the MIMIC external cohort: AUROC dropped to 0.45-0.57 for base and globally calibrated variants, confirming distributional shift. DCGS exceeded the 0.05 clinical significance threshold in 28 of 40 model-calibration combinations on the race axis. Neither global Platt nor isotonic calibration reliably reduced DCGS below that threshold. Conformal coverage collapsed to roughly 25% on MIMIC, and racial DCG exceeded 0.15 for all 20 model-variant combinations. Conclusions: Reducing population-level ECE through global recalibration does not reliably close demographic calibration gaps. DCGS gives researchers a direct, standardized way to detect and report those disparities. Code and the DCGS computation library are released as open-source Python under the MIT License.

阅读与讨论 → 访问原文 →
15.
arXiv (quant-ph) 2026-06-19

Sparse positive maps on qutrits with exact nondecomposability thresholds and PPT-entanglement transitions

作者:
Davide Poderini↗Angela Rosy Morgillo↗Fabio Benatti↗Fabio Anselmi↗Chiara Macchiavello↗Massimiliano F. Sacchi↗

arXiv:2606.19765v1 Announce Type: new Abstract: We study a family of sparse positive maps on qutrits for which positivity, decomposability, and PPT entanglement can all be analysed explicitly. The block structure of the associated Choi matrices reduces positivity to a Hermitian biquadratic form and leads to exact positivity boundaries for three representative parametric families. For the same families we determine the exact transition between decomposable and non-decomposable maps and construct associated PPT states of two classes. The first consists of witness-adapted deformations naturally tied to the non-decomposability analysis. The second consists of analytically tractable families whose full PPT-entangled branch is detected by fixed positive maps, yielding exact thresholds between separability and bound entanglement. For the trace-preserving subclass, we further compare positivity with a recent eigenvalue bound for 2-positive maps, thereby making the gap between positivity and higher-order positivity fully explicit within this family.

阅读与讨论 → 访问原文 →
16.
medRxiv (Medicine) 2026-06-12

Association of circulating endothelial progenitor cell count and functional outcome in patients with acute ischemic stroke due to intracranial large vessel occlusion

作者:
Aguilera-Simon↗Camps-Renom↗Guasch-Jimenez↗Puig↗Jimenez-Xarrie↗Marin↗Soler↗Gallego-Fabrega↗Ezcurra-Diaz↗Lambea-Gil↗Martinez Domeno↗Prats-Sanchez↗…

Background: Circulating endothelial progenitor cells (cEPCs) contribute to vascular repair following an ischemic stroke. The aim of the study was to evaluate the association between cEPCs and functional outcomes in patients with acute ischemic stroke (AIS) due to large vessel occlusion (LVO) who received endovascular therapy (EVT). Methods: Prospective study of patients with LVO-AIS who received EVT. Blood samples were obtained within 24 +- 12 hours and on day 7+-1 from stroke onset. cEPCs were detected using flow cytometry (CD34+/VEGFR2+/CD133+). The primary endpoint was a favourable functional outcome (modified Rankin Scale 0-2) at three months of follow-up. Secondary endpoints include baseline to 24 hours/day 7 changes in the National Institutes of Health Stroke Scale (NIHSS) score and collateral circulation (CC) status. Bivariate and multivariable logistic regression analyses were performed. Results: Included were 90 patients (73.2+-12.7 years, 41.1% women) in 42 of whom (46.7%) cEPCs were detected at 24 hours. On day 7, cEPCs were detected in 27 (43.6%) of 62 patients for which this information was available. Atrial fibrillation, prior anticoagulant treatment and stroke onset-to-door time

阅读与讨论 → 访问原文 →
17.
arXiv (CS.CV) 2026-06-19

Reliability-Aware Prototype Calibration for Frozen Pose-Flow Video Anomaly Detection

作者:
Ning Dong↗Yingna Su↗Xin Dong↗Ziyun Jiao↗Xinnian Guo↗Zhuangzhuang Pan↗

Pose-flow video anomaly detectors are attractive for one-class surveillance because they provide likelihood-based rankings for tracked skeleton windows. However, a single likelihood score may hide multimodal normal behavior and be sensitive to pose-observation noise. We study a frozen-detector setting in which the pose-flow backbone, cached skeleton tracks, and evaluation pipeline are fixed. Reliability-Aware Prototype Calibration (RPC) is a post-hoc score calibration method for this setting. It adds a standardized nearest-prototype deviation in the frozen latent space to the standardized flow score, and uses keypoint confidence only to gate this added geometric evidence. Thus, RPC preserves the original density signal while correcting the ranking with empirical normal-mode structure under pose reliability. Across two frozen pose-flow backbones and four datasets, RPC improves frame-level AUROC in all eight backbone-dataset pairs, with gains ranging from 0.34 to 4.49 percentage points and averaging 2.03 points. Ablation and reliability analyses show that prototype deviation is the main corrective signal, while reliability gating is most useful when pose observations are less trustworthy. These results suggest that lightweight post-hoc calibration can strengthen cached pose-flow systems when retraining or reproducing the full pose pipeline is impractical.

阅读与讨论 → 访问原文 →
18.
arXiv (CS.CL) 2026-06-16

PhoneHarness: Harnessing Phone-Use Agents through Mixed GUI, CLI, and Tool Actions

作者:
Chenxin Li↗Zhengyao Fang↗Zhengyang Tang↗Pengyuan Lyu↗Xingran Zhou↗Xin Lai↗Fei Tang↗Liang Wu↗Yiduo Guo↗Weinong Wang↗Junyi Li↗Yi Zhang↗…

Phone agents are increasingly expected to complete real mobile workflows rather than merely predict the next screen action. However, much of the current mobile-agent literature still evaluates agents primarily as GUI controllers that observe a screen, emit taps and swipes, and are scored by target app state. Real phone-use tasks are broader: they require deciding when to use app GUIs, device-side commands, or structured tools, while leaving evidence that the intended side effect actually occurred. We introduce PhoneHarness, a mixed-action benchmark and execution harness for studying phone-use agents on verifiable mobile workflows. PhoneHarness runs a device-side agent loop over GUI, CLI, and host-side tool actions, combining deterministic action routing with bounded GUI delegation and auditable execution traces. Its benchmark, PhoneHarness Bench, evaluates whether agents complete tasks with observable side effects, not only whether they produce plausible final answers. On the annotated evaluation split, PhoneHarness reaches a 75.0% pass rate, outperforming the strongest non-PhoneHarness settings by 12.9 percentage points. PhoneHarness and PhoneHarness Bench therefore play distinct but mutually dependent roles: the harness makes mixed phone workflows executable, while the benchmark measures whether agents can use that harness reliably and safely. Our findings suggest that reliable phone automation depends on action-surface routing and verifiable execution, not only visual GUI control.

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

When Correct Edges Cannot Be Verified: A Provenance Gap in Incomplete KGQA and a Provenance-Favoring Completion Policy

作者:
Yongqi Kang↗Yu Fu↗Yong Zhao↗

Incomplete Knowledge Graph Question Answering (IKGQA) requires completing missing edges to continue reasoning. A growing line of work verifies completed edges against retrieved text, treating textual support as a proxy for edge quality. We ask a question that, to our knowledge, has not been systematically tested: does textual verifiability actually track correctness? Exploiting the gold deleted triples provided by the standard random-deletion protocol, we measure both. The finding is counterintuitive: among gold-correct completed edges, 76-96% have no supporting passage even under exhaustive retrieval, robustly across deletion rates (20%/40%), datasets (CWQ/WebQSP), and relation types (structural, commonsense, long-tail). Most Freebase-style facts simply do not occur as head-tail co-mentions in text. Textual faithfulness therefore measures provenance, not correctness – separated by a paradigm-level gap no in-corpus retrieval closes. This reframes edge completion. Since most completed edges – correct or not – are causally redundant for the answer (95-97% of correct answers do not depend on any unsupported edge), the central question shifts from "is the edge correct?" to "admit or abstain under provenance uncertainty?" Within this framing we present TGComplete, a provenance-favoring admission policy that retrieves evidence at a reasoning breakpoint, verifies a candidate through a lightweight loop, and abstains when support is absent. Against the generate-to-complete baseline GoG, it attains higher edge precision against gold (15-21% vs 3-14%), with no statistically detectable EM loss and 3.1-7.4 times higher strict faithfulness of admitted edges – at the cost of lower recall. We position TGComplete not as uniformly better, but as a principled point on a precision/provenance-recall trade-off, appropriate when auditability matters.

阅读与讨论 → 访问原文 →
20.
arXiv (CS.AI) 2026-06-12

Counterfactual Credit Policy Optimization for Multi-Agent Collaboration

作者:
Zhongyi Li↗Wan Tian↗Jinju Chen↗Huiming Zhang↗Yang Liu↗Yikun Ban↗Fuzhen Zhuang↗

arXiv:2603.21563v5 Announce Type: replace Abstract: Collaborative multi-agent large language models (LLMs) can solve complex reasoning tasks by decomposing roles, but reinforcement learning for such systems is limited by credit assignment: shared terminal rewards obscure individual contributions and can encourage free-riding. We introduce two optimizer-agnostic credit assignment methods for converting joint outcomes into agent-specific learning signals. Counterfactual Credit for Policy Optimization (CCPO) estimates an agent's marginal contribution by comparing the realized joint outcome with a counterfactual outcome where that agent is removed. Self-Evaluated Credit for Policy Optimization (SEPO) uses constrained self- and peer-evaluations as a verifier-anchored credit signal while keeping the external task outcome dominant. Both operate at the reward-construction layer rather than as policy optimizers, producing role-specific rewards or advantages for GRPO, GSPO, or REINFORCE++. We instantiate these credit signals in a sequential Think–Solve setting and evaluate them on mathematical reasoning benchmarks. Results show that explicit credit assignment often improves dual-agent reasoning, especially on MATH500 and several out-of-distribution settings, while gains vary across models and datasets. Our code is available at: https://github.com/bhai114/ccpo.

阅读与讨论 → 访问原文 →
21.
arXiv (CS.AI) 2026-06-11

Architecture-Aware Reinforcement Learning Makes Sliding-Window Attention Competitive in Math Reasoning

作者:
Kai Liu↗Peijie Dong↗Xinchen Xie↗Jianfei Gao↗Qipeng Guo↗Xiaowen Chu↗Shaoting Zhang↗Kai Chen↗

arXiv:2606.11634v1 Announce Type: new Abstract: The rapid progress of reasoning and agentic large language models (LLMs) has increased the demand for long-context inference, but self-attention (SA) scales quadratically with context length. To address this, we study SWARR (Sliding-Window Attention with Reinforced Adaptation for Math Reasoning), a practical recipe for adapting SWA models to mathematical reasoning. SWARR has two stages: (1) efficient conversion from a pretrained SA model to SWA with supervised fine-tuning (SFT), which avoids pretraining a new base model, and (2) policy adaptation with reinforcement learning (RL). We find that SWA still underperforms SA after SFT, and we hypothesize that this gap is caused in part by a data-architecture mismatch: most SFT data are prepared for SA models and may contain long-range dependencies that are difficult for SWA to model. Because on-policy RL optimizes self-generated trajectories under the SWA constraint, it can adapt trajectories to better match SWA. Experiments on mathematical reasoning benchmarks show that this recipe substantially narrows the gap between SWA and SA, recovering much of the accuracy lost during SWA conversion while preserving the efficiency benefits of linear-complexity attention. Our central contribution is the empirical finding that RL changes the conclusion one would draw from conversion and SFT alone about SWA's viability for math reasoning.

阅读与讨论 → 访问原文 →
23.
arXiv (CS.AI) 2026-06-17

Transformer-Based Warm-Starting for Feasible and Optimal Terminal Approach to Tumbling Objects with Space Manipulators

作者:
Yuji Takubo↗Maximilian Adang↗Mac Schwager↗Simone D'Amico↗

arXiv:2606.17317v1 Announce Type: cross Abstract: Real-time trajectory generation for on-orbit robotic servicing is challenging due to the nonlinear coupling between spacecraft bus motion, manipulator dynamics, visibility cone, and trajectory-level safety constraints. This paper studies learning-based warm-starting for sequential convex programming (SCP) in the terminal approach of a space manipulator toward a tumbling target. The proposed framework decomposes the problem into a system center-of-mass translational planning stage and a coupled attitude–manipulator torque-allocation stage, and applies a causal transformer warm-start to the latter, which constitutes the dominant computational bottleneck. Linear and flow matching action decoders are compared under different action-chunking and training dataset sizes, and the resulting warm-starts are evaluated under both cost-optimal and feasibility projection using SCP. Across 300 held-out scenarios, the learned warm-start reduces the second-stage SCP iteration count by up to 28% and the runtime by 23% while preserving the final control-cost distribution. When the learned warm-starts are used for nonconvex feasibility projection, they nearly halve the runtime relative to cost-optimal SCP, while avoiding the catastrophic high-cost tail behavior observed when initialized heuristically. These results indicate that sequence-model warm-starts can improve both the computational efficiency and trajectory robustness of optimization-based terminal guidance for space manipulation.

阅读与讨论 → 访问原文 →
24.
arXiv (CS.CV) 2026-06-18

CAMEO: A Conditional and Quality-Aware Multi-Agent Image Editing Orchestrator

作者:
Yuhan Pu↗Hao Zheng↗Ziqian Mo↗Zirui Pang↗Hill Zhang↗Tianyi Fan↗Shuhong Wu↗Jiaheng Wei↗

Conditional image editing aims to modify a source image according to textual prompts and optional reference guidance. Such editing is crucial in scenarios requiring strict structural control (i.e., anomaly insertion in driving scenes and complex human pose transformation). Despite recent advances in large-scale editing models (i.e., Seedream, Nano Banana, etc), most approaches rely on single-step generation. This paradigm often lacks explicit quality control, may introduce excessive deviation from the original image, and frequently produces structural artifacts or environment-inconsistent modifications, typically requiring manual prompt tuning to achieve acceptable results. We propose CAMEO, a structured multi-agent framework that reformulates conditional editing as a quality-aware, feedback-driven process rather than a one-shot generation task. CAMEO decomposes editing into coordinated stages of planning, structured prompting, hypothesis generation, and adaptive reference grounding, where external guidance is invoked only when task complexity requires it. To overcome the lack of intrinsic quality control in existing methods, evaluation is embedded directly within the editing loop. Intermediate results are iteratively refined through structured feedback, forming a closed-loop process that progressively corrects structural and contextual inconsistencies. We evaluate CAMEO on anomaly insertion and human pose switching tasks. Across multiple strong editing backbones and independent evaluation models, CAMEO consistently achieves 20\% more win rate on average compared to multiple state-of-the-art models, demonstrating improved robustness, controllability, and structural reliability in conditional image editing.

阅读与讨论 → 访问原文 →
25.
arXiv (CS.LG) 2026-06-16

Semantic DLM+: Improving Diffusion Language Models through Bias-variance Trade-off in Transition Kernel Design

作者:
Keyue Jiang↗Yuxiang Wang↗Yanan Zhao↗Xiang Yu↗Qifang Zhao↗Bohan Tang↗Baojian Zhou↗Yanghua Xiao↗Lin Qu↗Xiaoxiao Xu↗

arXiv:2606.15327v1 Announce Type: new Abstract: Diffusion Language Models (DLMs) have demonstrated strong scaling capacity as alternatives to autoregressive language models. However, their performance is highly sensitive to the choice of transition kernels, and poorly designed kernels can lead to issues like training instability, slow convergence, and biased sampling. In this paper, we study this sensitivity through a principled analysis of generalization error and identify three critical factors: asymptotic bias (difficulty in approximating the posterior distribution), exposure bias (error propagation during sampling), and optimization variance induced by kernel dispersion. We further compare different transition kernels: masking diffusion yields sparse and easier posterior-approximation targets, while uniform diffusion provides stronger sampling-side repair but induces harder approximation. Motivated by this trade-off, we revisit a previously overlooked variant, semantic DLM (SemDLM), where the transition kernel corrupts tokens to neighborhoods that are semantically similar. Our theory suggests that SemDLM can serve as a plausible middle ground by reducing the posterior approximation difficulty of uniform diffusion while retaining repair ability. However, we find that SemDLM suffers from a semantic basin problem, where sampling repeatedly stays within a semantic region and produces low-diversity text. To address this, we propose SemDLM+, which adds a global transition and a semantic-frequency penalty during sampling. Experiments on LM1B and OpenWebText show that SemDLM+ improves training dynamics and achieves competitive language modeling and generation quality with satisfactory diversity.

阅读与讨论 → 访问原文 →