❌

Normal view

Received — 27 May 2026 ⏭

Test-Time Deep Thinking to Explore Implicit Rules

✇cs.AI, q-bio.NC updates on arXiv.org
By: Wentong Chen · Xin Cong · Zhong Zhang · Yaxi Lu · Siyuan Zhao · Yesai Wu · Qinyu Luo · Haotian Chen · Yankai Lin · Zhiyuan Liu · Maosong Sun
26 May 2026 at 12:00
arXiv:2605.24828v1 Announce Type: new Abstract: With the continuous advancement of Large Language Models (LLMs), intelligent agents are becoming increasingly vital. However, these agents often fail in environments governed by implicit rules--hidden constraints that cannot be observed directly and must be inferred through interaction. This causes agents to fall into repetitive trial-and-error loops, ultimately leading to task failure. To address this challenge, we propose Test-Time Exploration (TTExplore), a framework where a thinker component analyzes interaction history to infer these implicit rules and guide an actor. Effective exploration in this setting critically depends on the reasoning ability of the thinker. However, evaluating deep reasoning trajectories is inherently unstable and difficult, which poses a major obstacle to effective training. To overcome this issue, we introduce a novel and stable reinforcement learning pipeline. The core idea is to use accurate task-level scores as indirect rewards to bypass the difficulty of evaluating intermediate reasoning, and to retain only a single thinking node per trajectory to alleviate reward sparsity. Using this pipeline, we train a specialized 7B model, Exp-Thinker. Experiments on five text-based embodied tasks show that TTExplore equipped with Exp-Thinker improves baseline agent performance by an average of $14$-$19$ points, demonstrating the effectiveness of explicitly reasoning about implicit rules.

CITYREP: A Unified Benchmark for Urban Representations Across Cities, Tasks, and Modalities

✇cs.AI, q-bio.NC updates on arXiv.org
By: Junyuan Liu · Xinglei Wang · Zichao Zeng · Jiazhuang Feng · Quan Qin · Ilya Ilyankou · Guangsheng Dong · Tao Cheng
26 May 2026 at 12:00
arXiv:2605.26036v1 Announce Type: new Abstract: Urban representation learning encodes complex urban environments into general-purpose embeddings for diverse downstream tasks and emerging urban foundation models. However, current evaluations are limited, typically focusing on one or two cities and tasks and relying on random splits that introduce spatial leakage, leading to inflated performance and weak support for cross-location generalization and fair comparison. To address this, we propose CityRep, a unified benchmark that evaluates urban representations across data modalities, cities, and tasks using spatially structured splits. CityRep consists of three key components: (1) a spatial unit-agnostic evaluation framework that supports heterogeneous urban representations through a standardized alignment module; (2) a unified evaluation protocol using block-based spatial splits to mitigate spatial leakage and enable rigorous model comparison; and (3) an extensible multi-city, multi-task benchmark suite spanning 8 cities and 8 tasks across regression, classification, and distribution prediction. We evaluate 11 representative urban representation models. Results show that performance is highly sensitive to the split protocol, with random splits inflating scores and altering model rankings. We also observe substantial variability across cities and tasks, underscoring the need for generalization-aware evaluation. CityRep is released as a reproducible benchmark with datasets, evaluation pipelines, and diagnostic tools to facilitate fair comparison and support future research in urban representation learning towards urban foundation models.

Claw-Anything: Benchmarking Always-On Personal Assistants with Broader Access to User's Digital World

✇cs.AI, q-bio.NC updates on arXiv.org
By: Yusong Lin · Xinyuan Liang · Haiyang Wang · Qipeng Gu · Siqi Cheng · Jiangui Chen · Shuzhe Wu · Feiyang Pan · Lue Fan · Sanyuan Zhao · Dandan Tu
26 May 2026 at 12:00
arXiv:2605.26086v1 Announce Type: new Abstract: Large language model agents are increasingly envisioned as always-on personal assistants with access to anything relevant in the user's digital world. Yet current systems operate over only narrow slices of that world, limiting context-sensitive reasoning and effective assistance. Existing benchmarks similarly provide only partial user state and therefore fail to capture performance in such a broad, always-on setting. To address this gap, we introduce Claw-Anything, a benchmark that expands agent context along three dimensions: long-horizon activity histories, interdependent backend services, and integrated GUI and CLI interaction across multiple devices. To instantiate this setting, we simulate months of user activity through multi-round event injection, producing complex world states and realistic noise, including irrelevant events and conflicting signals. Agents must reason over rich contextual environments while remaining robust to such noise. This expanded scope also enables the evaluation of proactive assistance, requiring agents to anticipate user needs and deliver timely recommendations. Experiments show that GPT-5.5 achieves only 34.5% pass@1, substantially below prior benchmarks, underscoring a gap between current agent capabilities and the demands of always-on personal assistance. Alongside the benchmark, we release an automated data-generation pipeline that yields 2,000 training environments and improves the base model by 23.7%, demonstrating its utility of scalable data infrastructure.

MuNet: A Mutualistic Network for Joint 3D Human Mesh Recovery and 3D Clothed Human Reconstruction from Single Images

✇cs.AI, q-bio.NC updates on arXiv.org
By: Yunqi Gao · Leyuan Liu · Yuhan Li · Changxin Gao · Jingying Chen
26 May 2026 at 12:00
arXiv:2605.25861v2 Announce Type: cross Abstract: 3D human mesh recovery and 3D clothed human reconstruction are inherently related, yet they have long been studied in isolation, thereby overlooking the potential gains of joint optimization. To overcome this limitation, we propose to address these two tasks within a unified framework, which allows their mutual dependencies to be effectively exploited. Building on this idea, we propose MuNet, a mutualistic network for joint 3D human mesh recovery and 3D clothed human reconstruction from single images. First, we adopt 2-manifold graphs as a unified representation for all 3D models, enabling consistent modeling across 3D human mesh recovery and clothed human reconstruction. Second, we design an end-to-end graph convolutional network that progressively deforms an initial graph into a 3D human mesh and refines it into a detailed 3D clothed human model. Third, we introduce a mutualistic mechanism that allows reciprocal interaction between the two tasks {during training}, where 3D human mesh recovery provides guidance for 3D clothed human reconstruction, and reconstruction feedback refines the 3D human mesh recovery. We extensively evaluate MuNet on six benchmark datasets for 3D human mesh recovery and 3D clothed human reconstruction, including Human3.6M, 3DPW, MPI-INF-3DHP, THuman2.0, CAPE, and RenderPeople. Experimental results demonstrate that MuNet achieves state-of-the-art performance on both tasks across all datasets. The code of MuNet is released for research purposes at https://github.com/starVisionTeam/MuNet.

Data Difficulty and the Generalization--Extrapolation Tradeoff in LLM Fine-Tuning

✇cs.AI, q-bio.NC updates on arXiv.org
By: Siyuan Liu · Tinghong Chen · Xinghan Li · Yifei Wang · Jingzhao Zhang
26 May 2026 at 12:00
arXiv:2605.12906v2 Announce Type: replace-cross Abstract: Data selection during supervised fine-tuning (SFT) can critically change the behavior of large language models (LLMs). Although existing work has studied the effect of selecting data based on heuristics such as perplexity, difficulty, or length, the reported findings are often inconsistent or context-dependent. In this work, we systematically study the role of data difficulty in fine-tuning from both empirical and theoretical perspectives, and find that there is no universally optimal difficulty level; rather, its effectiveness depends on the dataset size. We show that for a fixed data budget, there exists an optimal data difficulty for SFT, and that this optimal difficulty shifts toward harder data as the data budget increases. To explain this phenomenon, we conduct controlled synthetic experiments that reveal a simple underlying mechanism: the interplay between the (in-distribution) generalization gap and the extrapolation gap. We further support this mechanism through a theoretical analysis using PAC-Bayesian generalization bounds. Overall, our results clarify how data size and difficulty jointly affect the trade-off between generalization and extrapolation in SFT, providing guidance for difficulty-based data selection under certain model and data conditions.

TimeGuard: Channel-wise Pool Training for Backdoor Defense in Time Series Forecasting

✇cs.AI, q-bio.NC updates on arXiv.org
By: Quang Duc Nguyen · Siyuan Liang · Yiming Li · Fushuo Huo · Dacheng Tao
26 May 2026 at 12:00
arXiv:2605.22365v2 Announce Type: replace-cross Abstract: Time Series Forecasting (TSF) is highly vulnerable to backdoor attacks, yet effective defenses remain underexplored due to challenges arising from data entanglement and shifts in task formulation. To fill this gap, we conduct a systematic evaluation of thirteen representative backdoor defenses across the TSF life cycle and analyze their failure modes. Our results reveal two fundamental issues: (1) data entanglement induces channel-level signal dilution, rendering sample-filtering and trigger-synthesis defenses ineffective at localizing backdoors; and (2) task-formulation shift leads to training-loss degeneration, causing poisoned and clean windows to become indistinguishable at training stages. Based on these findings, we propose a training-time backdoor defense for TSF, termed TimeGuard. Our method adopts channel-wise pool training as the core paradigm and initializes a high-confidence pool using time-aware criteria to mitigate signal dilution. Moreover, we introduce distance-regularized loss selection to progressively expand the reliable pool during training and ease loss degeneration. Extensive experiments across multiple datasets, forecasting architectures, and TSF backdoor attacks demonstrate that TimeGuard substantially improves robustness, boosting $\mathrm{MAE}_\mathrm{P}$ by $1.96\times$ over the leading baseline, while preserving clean performance within 5% $\mathrm{MAE}_\mathrm{C}$.

FGFR1 Promotes Malignant Progression in Lung Squamous Cell Carcinoma Through Activation of Wnt/beta-Catenin Signaling

✇Omics In Lung
By: Xingyuan Li · Shuya Mu · Yinjia Sun · Yongfeng Yu
18 April 2026 at 18:00

Cancer Med. 2026 Apr;15(4):e71833. doi: 10.1002/cam4.71833.

ABSTRACT

OBJECTIVES: This study aims to elucidate the role of FGFR1 in activating the Wnt/β-catenin signaling pathway and the underlying mechanisms by which it promotes malignant progression in lung squamous cell carcinoma (LUSC). By integrating multi-omics analysis with functional experiments, the clinical heterogeneity of FGFR1 amplification, signaling crosstalk, and their regulatory networks governing tumor phenotypes were revealed.

METHODS: Using TCGA data (n = 490), we analyzed the relationship between FGFR1 copy number variation (CNV) and mRNA expression in LUSC, and validated the correlation with protein expression in a clinical cohort (n = 38). GSEA and single-gene GSEA were performed to identify signaling pathways associated with high FGFR1 expression. The interaction between FGFR1 and the Wnt/β-catenin pathway was investigated by immunohistochemistry, immunofluorescence, stable cell lines, Western blot, qPCR, and functional assays.

RESULTS: FGFR1 amplification correlated with increased mRNA and protein expression. The top 25% FGFR1 high-expression group enriched Wnt/β-catenin, PI3K-Akt, and cAMP pathways. Mechanistically, FGFR1 promoted β-catenin nuclear accumulation and enhanced β-catenin signaling through PKA-associated phosphorylation and Akt/GSK3β-related regulation of β-catenin stability, and these effects were attenuated by AKT inhibition. CTNNB1 knockdown significantly inhibited proliferation, migration, invasion, and tumor growth of LUSC cells.

CONCLUSIONS: Our findings indicate that FGFR1 activates Wnt/β-catenin signaling through coordinated regulation of β-catenin phosphorylation, stability, and subcellular localization, thereby promoting malignant progression in LUSC. These results provide a rationale for targeting the FGFR1-Wnt/β-catenin axis as a potential therapeutic strategy.

PMID:41998829 | DOI:10.1002/cam4.71833

There are no more articles
❌