❌

Normal view

Received — 4 April 2026 ⏭

When Should a Robot Think? Resource-Aware Reasoning via Reinforcement Learning for Embodied Robotic Decision-Making

✇cs.AI, q-bio.NC updates on arXiv.org
By: Jun Liu · Pu Zhao · Zhenglun Kong · Xuan Shen · Peiyan Dong · Fan Yang · Lin Cui · Hao Tang · Geng Yuan · Wei Niu · Wenbin Zhang · Xue Lin · Gaowen Liu · Yanzhi Wang · Dong Huang
3 April 2026 at 12:00
arXiv:2603.16673v3 Announce Type: replace-cross Abstract: Embodied robotic systems increasingly rely on large language model (LLM)-based agents to support high-level reasoning, planning, and decision-making during interactions with the environment. However, invoking LLM reasoning introduces substantial computational latency and resource overhead, which can interrupt action execution and reduce system reliability. Excessive reasoning may delay actions, while insufficient reasoning often leads to incorrect decisions and task failures. This raises a fundamental question for embodied agents: when should the agent reason, and when should it act? In this work, we propose RARRL (Resource-Aware Reasoning via Reinforcement Learning), a hierarchical framework for resource-aware orchestration of embodied agents. Rather than learning low-level control policies, RARRL learns a high-level orchestration policy that operates at the agent's decision-making layer. This policy enables the agent to adaptively determine whether to invoke reasoning, which reasoning role to employ, and how much computational budget to allocate based on current observations, execution history, and remaining resources. Extensive experiments, including evaluations with empirical latency profiles derived from the ALFRED benchmark, show that RARRL consistently improves task success rates while reducing execution latency and enhancing robustness compared with fixed or heuristic reasoning strategies. These results demonstrate that adaptive reasoning control is essential for building reliable and efficient embodied robotic agents.
Received — 2 April 2026 ⏭

Perspectives from machine learning and multi-omics to decoding the effects of VDAC2 malignant subsets on tumor evolution

✇Omics in Gastric
By: Jianing Yan · Jingzhi Wang · Haotian Dong · Guoliang Ye · Yongfu Shao
31 March 2026 at 18:00

NPJ Precis Oncol. 2026 Mar 31. doi: 10.1038/s41698-026-01394-1. Online ahead of print.

ABSTRACT

VDAC2's known role in cancer and immune regulation via enhancing the CD8+ T cell-mediated killing, and it is worth systematically digging out the role of VDAC2 in pan-cancer based on this research. Bulk RNA sequencing, single-cell RNA sequencing, and spatial transcriptomic analyses were utilized to explore the role of VDAC2 from multiple perspectives in pan-cancers. RT-PCR, cell co-culture, CCK-8 assay, Transwell invasion assays, and ELISA were performed to validate the expression level and biological function. VDAC2 was upregulated in the majority of pan-cancers, and functional enrichment analyses displayed that VDAC2 may take part in the biological progress of energy metabolism, mitochondrial damage and cell proliferation. The landscape of VDAC2 expression and immune infiltration was constructed, and the VDAC2-BAK1-IFNγ pathway was identified in digestive cancer. VDAC2 had the potential to serve as a novel prognostic, screening cancer indicator and immune therapeutic target sensitive to various drugs. Overexpression of VDAC2 significantly promoted gastric cancer cell proliferation, invasion and immune invasion, as validated in vitro experiments. In short, our pan-cancer analysis constructed a comprehensive landscape of VDAC2's oncogenic role, establishing VDAC2 + -BAK1-IFNγ as an important pathway in tumor progression and immune evasion. VDAC2 emerges not only as a valuable prognostic biomarker but also as a promising novel therapeutic target.

PMID:41917254 | DOI:10.1038/s41698-026-01394-1

Perspectives from machine learning and multi-omics to decoding the effects of VDAC2 malignant subsets on tumor evolution

✇(Multiomics OR Omics) AND (Lung OR gastric OR Hepatocellular)
By: Jianing Yan · Jingzhi Wang · Haotian Dong · Guoliang Ye · Yongfu Shao
31 March 2026 at 18:00

NPJ Precis Oncol. 2026 Mar 31. doi: 10.1038/s41698-026-01394-1. Online ahead of print.

ABSTRACT

VDAC2's known role in cancer and immune regulation via enhancing the CD8+ T cell-mediated killing, and it is worth systematically digging out the role of VDAC2 in pan-cancer based on this research. Bulk RNA sequencing, single-cell RNA sequencing, and spatial transcriptomic analyses were utilized to explore the role of VDAC2 from multiple perspectives in pan-cancers. RT-PCR, cell co-culture, CCK-8 assay, Transwell invasion assays, and ELISA were performed to validate the expression level and biological function. VDAC2 was upregulated in the majority of pan-cancers, and functional enrichment analyses displayed that VDAC2 may take part in the biological progress of energy metabolism, mitochondrial damage and cell proliferation. The landscape of VDAC2 expression and immune infiltration was constructed, and the VDAC2-BAK1-IFNγ pathway was identified in digestive cancer. VDAC2 had the potential to serve as a novel prognostic, screening cancer indicator and immune therapeutic target sensitive to various drugs. Overexpression of VDAC2 significantly promoted gastric cancer cell proliferation, invasion and immune invasion, as validated in vitro experiments. In short, our pan-cancer analysis constructed a comprehensive landscape of VDAC2's oncogenic role, establishing VDAC2 + -BAK1-IFNγ as an important pathway in tumor progression and immune evasion. VDAC2 emerges not only as a valuable prognostic biomarker but also as a promising novel therapeutic target.

PMID:41917254 | DOI:10.1038/s41698-026-01394-1

Received — 26 March 2026 ⏭

CaP-X: A Framework for Benchmarking and Improving Coding Agents for Robot Manipulation

✇cs.AI, q-bio.NC updates on arXiv.org
By: Max Fu, Justin Yu, Karim El-Refai, Ethan Kou, Haoru Xue, Huang Huang, Wenli Xiao, Guanzhi Wang, Fei-Fei Li, Guanya Shi, Jiajun Wu, Shankar Sastry, Yuke Zhu, Ken Goldberg, Linxi "Jim" Fan
25 March 2026 at 12:00
arXiv:2603.22435v1 Announce Type: cross Abstract: "Code-as-Policy" considers how executable code can complement data-intensive Vision-Language-Action (VLA) methods, yet their effectiveness as autonomous controllers for embodied manipulation remains underexplored. We present CaP-X, an open-access framework for systematically studying Code-as-Policy agents in robot manipulation. At its core is CaP-Gym, an interactive environment in which agents control robots by synthesizing and executing programs that compose perception and control primitives. Building on this foundation, CaP-Bench evaluates frontier language and vision-language models across varying levels of abstraction, interaction, and perceptual grounding. Across 12 models, CaP-Bench reveals a consistent trend: performance improves with human-crafted abstractions but degrades as these priors are removed, exposing a dependence on designer scaffolding. At the same time, we observe that this gap can be mitigated through scaling agentic test-time computation--through multi-turn interaction, structured execution feedback, visual differencing, automatic skill synthesis, and ensembled reasoning--substantially improves robustness even when agents operate over low-level primitives. These findings allow us to derive CaP-Agent0, a training-free framework that recovers human-level reliability on several manipulation tasks in simulation and on real embodiments. We further introduce CaP-RL, showing reinforcement learning with verifiable rewards improves success rates and transfers from sim2real with minimal gap. Together, CaP-X provides a principled, open-access platform for advancing embodied coding agents.

From Conflict to Consensus: Boosting Medical Reasoning via Multi-Round Agentic RAG

✇cs.AI, q-bio.NC updates on arXiv.org
By: Wenhao Wu · Zhentao Tang · Yafu Li · Shixiong Kai · Mingxuan Yuan · Chunlin Chen · Zhi Wang
25 March 2026 at 12:00
arXiv:2603.03292v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) exhibit high reasoning capacity in medical question-answering, but their tendency to produce hallucinations and outdated knowledge poses critical risks in healthcare fields. While Retrieval-Augmented Generation (RAG) mitigates these issues, existing methods rely on noisy token-level signals and lack the multi-round refinement required for complex reasoning. In the paper, we propose MA-RAG (Multi-Round Agentic RAG), a framework that facilitates test-time scaling for complex medical reasoning by iteratively evolving both external evidence and internal reasoning history within an agentic refinement loop. At each round, the agent transforms semantic conflict among candidate responses into actionable queries to retrieve external evidence, while optimizing history reasoning traces to mitigate long-context degradation. MA-RAG extends the self-consistency principle by leveraging the lack of consistency as a proactive signal for multi-round agentic reasoning and retrieval, and mirrors a boosting mechanism that iteratively minimizes the residual error toward a stable, high-fidelity medical consensus. Extensive evaluations across 7 medical Q&A benchmarks show that MA-RAG consistently surpasses competitive inference-time scaling and RAG baselines, delivering substantial +6.8 points on average accuracy over the backbone model. Our code is available at https://github.com/NJU-RL/MA-RAG.
Received — 5 March 2026 ⏭

From Conflict to Consensus: Boosting Medical Reasoning via Multi-Round Agentic RAG

✇cs.AI, q-bio.NC updates on arXiv.org
By: Wenhao Wu · Zhentao Tang · Yafu Li · Shixiong Kai · Mingxuan Yuan · Zhenhong Sun · Chunlin Chen · Zhi Wang
5 March 2026 at 13:00
arXiv:2603.03292v1 Announce Type: cross Abstract: Large Language Models (LLMs) exhibit high reasoning capacity in medical question-answering, but their tendency to produce hallucinations and outdated knowledge poses critical risks in healthcare fields. While Retrieval-Augmented Generation (RAG) mitigates these issues, existing methods rely on noisy token-level signals and lack the multi-round refinement required for complex reasoning. In the paper, we propose **MA-RAG** (**M**ulti-Round **A**gentic RAG), a framework that facilitates test-time scaling for complex medical reasoning by iteratively evolving both external evidence and internal reasoning history within an agentic refinement loop. At each round, the agent transforms semantic **conflict** among candidate responses into actionable queries to retrieve external evidence, while optimizing history reasoning traces to mitigate long-context degradation. MA-RAG extends the *self-consistency* principle by leveraging the lack of consistency as a proactive signal for multi-round agentic reasoning and retrieval, and mirrors a *boosting* mechanism that iteratively minimizes the residual error toward a stable, high-fidelity medical **consensus**. Extensive evaluations across 7 medical Q&A benchmarks show that MA-RAG consistently surpasses competitive inference-time scaling and RAG baselines, delivering **substantial +6.8 points** on average accuracy over the backbone model. Our code is available at [this url](https://github.com/NJU-RL/MA-RAG).

CubeComposer: Spatio-Temporal Autoregressive 4K 360{\deg} Video Generation from Perspective Video

✇cs.AI, q-bio.NC updates on arXiv.org
By: Lingen Li · Guangzhi Wang · Xiaoyu Li · Zhaoyang Zhang · Qi Dou · Jinwei Gu · Tianfan Xue · Ying Shan
5 March 2026 at 13:00
arXiv:2603.04291v1 Announce Type: cross Abstract: Generating high-quality 360{\deg} panoramic videos from perspective input is one of the crucial applications for virtual reality (VR), whereby high-resolution videos are especially important for immersive experience. Existing methods are constrained by computational limitations of vanilla diffusion models, only supporting $\leq$ 1K resolution native generation and relying on suboptimal post super-resolution to increase resolution. We introduce CubeComposer, a novel spatio-temporal autoregressive diffusion model that natively generates 4K-resolution 360{\deg} videos. By decomposing videos into cubemap representations with six faces, CubeComposer autoregressively synthesizes content in a well-planned spatio-temporal order, reducing memory demands while enabling high-resolution output. Specifically, to address challenges in multi-dimensional autoregression, we propose: (1) a spatio-temporal autoregressive strategy that orchestrates 360{\deg} video generation across cube faces and time windows for coherent synthesis; (2) a cube face context management mechanism, equipped with a sparse context attention design to improve efficiency; and (3) continuity-aware techniques, including cube-aware positional encoding, padding, and blending to eliminate boundary seams. Extensive experiments on benchmark datasets demonstrate that CubeComposer outperforms state-of-the-art methods in native resolution and visual quality, supporting practical VR application scenarios. Project page: https://lg-li.github.io/project/cubecomposer

GLEAN: Grounded Lightweight Evaluation Anchors for Contamination-Aware Tabular Reasoning

✇cs.AI, q-bio.NC updates on arXiv.org
By: Qizhi Wang
4 March 2026 at 13:00
arXiv:2603.02212v1 Announce Type: cross Abstract: Tabular reasoning benchmarks mix semantic inference, numerical computation, and brittle table formatting, yet evaluations for small models remain vulnerable to contamination, dataset artifacts, and retrieval failures. We propose GLEAN, a lightweight evaluation protocol that integrates contamination-aware probes, weak-supervision governance, retrieval-reasoning diagnostics, and structured error attribution under tight hardware constraints. We evaluate across TabFact, WTQ via Squall, TableBench, RobuT, and SciTab under a 16GB GPU budget. Using Squall gold SQL as an executable anchor (95.2% execution), GLEAN assigns a deterministic error taxonomy (L0-L4 plus L0.5 context miss) and reveals a stable error-mode separation: TAPEX errors skew toward grounding (L3) while TAPAS errors skew toward hallucination/abstention (L2/L0). We validate evidence-row heuristics against SQL-derived rows on simple queries (0.62 precision / 0.71 recall; hybrid recall 0.81) and show that retrieval Recall@K can saturate even when end-to-end EM/F1 remains limited, motivating attribution beyond raw recall. We release a modular framework with audits and sensitivity checks to make small-model tabular evaluation more contamination-aware and diagnostic.

Proactive Guiding Strategy for Item-side Fairness in Interactive Recommendation

✇cs.AI, q-bio.NC updates on arXiv.org
By: Chongjun Xia · Xiaoyu Shi · Hong Xie · Xianzhi Wang · yun lu · Mingsheng Shang
4 March 2026 at 13:00
arXiv:2603.03094v1 Announce Type: cross Abstract: Item-side fairness is crucial for ensuring the fair exposure of long-tail items in interactive recommender systems. Existing approaches promote the exposure of long-tail items by directly incorporating them into recommended results. This causes misalignment between user preferences and the recommended long-tail items, which hinders long-term user engagement and reduces the effectiveness of recommendations. We aim for a proactive fairness-guiding strategy, which actively guides user preferences toward long-tail items while preserving user satisfaction during the interactive recommendation process. To this end, we propose HRL4PFG, an interactive recommendation framework that leverages hierarchical reinforcement learning to guide user preferences toward long-tail items progressively. HRL4PFG operates through a macro-level process that generates fairness-guided targets based on multi-step feedback, and a micro-level process that fine-tunes recommendations in real time according to both these targets and evolving user preferences. Extensive experiments show that HRL4PFG improves cumulative interaction rewards and maximum user interaction length by a larger margin when compared with state-of-the-art methods in interactive recommendation environments.
Received — 25 February 2026 ⏭

A Very Big Video Reasoning Suite

✇cs.AI, q-bio.NC updates on arXiv.org
By: Maijunxian Wang, Ruisi Wang, Juyi Lin, Ran Ji, Thadd\"aus Wiedemer, Qingying Gao, Dezhi Luo, Yaoyao Qian, Lianyu Huang, Zelong Hong, Jiahui Ge, Qianli Ma, Hang He, Yifan Zhou, Lingzi Guo, Lantao Mei, Jiachen Li, Hanwen Xing, Tianqi Zhao, Fengyuan Yu, Weihang Xiao, Yizheng Jiao, Jianheng Hou, Danyang Zhang, Pengcheng Xu, Boyang Zhong, Zehong Zhao, Gaoyun Fang, John Kitaoka, Yile Xu, Hua Xu, Kenton Blacutt, Tin Nguyen, Siyuan Song, Haoran Sun, Shaoyue Wen, Linyang He, Runming Wang, Yanzhi Wang, Mengyue Yang, Ziqiao Ma, Rapha\"el Milli\`ere, Freda Shi, Nuno Vasconcelos, Daniel Khashabi, Alan Yuille, Yilun Du, Ziming Liu, Bo Li, Dahua Lin, Ziwei Liu, Vikash Kumar, Yijiang Li, Lei Yang, Zhongang Cai, Hokin Deng
24 February 2026 at 13:00
arXiv:2602.20159v1 Announce Type: cross Abstract: Rapid progress in video models has largely focused on visual quality, leaving their reasoning capabilities underexplored. Video reasoning grounds intelligence in spatiotemporally consistent visual environments that go beyond what text can naturally capture, enabling intuitive reasoning over spatiotemporal structure such as continuity, interaction, and causality. However, systematically studying video reasoning and its scaling behavior is hindered by the lack of large-scale training data. To address this gap, we introduce the Very Big Video Reasoning (VBVR) Dataset, an unprecedentedly large-scale resource spanning 200 curated reasoning tasks following a principled taxonomy and over one million video clips, approximately three orders of magnitude larger than existing datasets. We further present VBVR-Bench, a verifiable evaluation framework that moves beyond model-based judging by incorporating rule-based, human-aligned scorers, enabling reproducible and interpretable diagnosis of video reasoning capabilities. Leveraging the VBVR suite, we conduct one of the first large-scale scaling studies of video reasoning and observe early signs of emergent generalization to unseen reasoning tasks. Together, VBVR lays a foundation for the next stage of research in generalizable video reasoning. The data, benchmark toolkit, and models are publicly available at https://video-reason.com/ .

Diversity-Incentivized Exploration for Versatile Reasoning

✇cs.AI, q-bio.NC updates on arXiv.org
By: Zican Hu · Shilin Zhang · Yafu Li · Jianhao Yan · Xuyang Hu · Leyang Cui · Xiaoye Qu · Chunlin Chen · Yu Cheng · Zhi Wang
24 February 2026 at 13:00
arXiv:2509.26209v2 Announce Type: replace Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as a crucial paradigm for incentivizing reasoning capabilities in Large Language Models (LLMs). Due to vast state-action spaces and reward sparsity in reasoning tasks, existing methods often struggle with deficient exploration and poor sample efficiency. In the paper, we propose \textbf{DIVER} (\textbf{D}iversity-\textbf{I}ncentivized Exploration for \textbf{V}ersatil\textbf{E} \textbf{R}easoning), an innovative framework that highlights the pivotal role of global sequence-level diversity to incentivize deep exploration for versatile reasoning. We first conduct a primary empirical study to reveal a strong positive correlation between global diversity and reasoning capacity. Building on this insight, we introduce global diversity incentives as an intrinsic reward to promote deep exploration in a semantically structured space. Incorporating the intrinsic reward, we develop a potential-based reward shaping mechanism to preserve optimal policy invariance and design simple heuristics to mitigate possible reward hacking. Experimental results show that DIVER outperforms competitive RLVR baselines with various exploration strategies on both in-domain and out-of-domain tasks, excelling in both Pass@1 and Pass@k evaluations. Our code is available at https://github.com/NJU-RL/DIVER.
Received — 17 February 2026 ⏭

WiSparse: Boosting LLM Inference Efficiency with Weight-Aware Mixed Activation Sparsity

✇cs.AI, q-bio.NC updates on arXiv.org
By: Lei Chen · Yuan Meng · Xiaoyu Zhan · Zhi Wang · Wenwu Zhu
17 February 2026 at 13:00
arXiv:2602.14452v1 Announce Type: cross Abstract: Large Language Models (LLMs) offer strong capabilities but incur high inference costs due to dense computation and memory access. Training-free activation sparsity is a promising approach for efficient LLM inference, yet existing methods often rely solely on activation information and uniform sparsity ratios. This overlooks the critical interplay with weights and inter-block sensitivity variation, leading to suboptimal performance. We identify two key phenomena in modern LLMs: 1) less significant activations may align with highly important weights, and 2) sparsity sensitivity varies non-monotonically across model blocks. We propose Weight-aware Mixed-Granularity Training-free Activation Sparsity (WiSparse), which leverages both activation and weight information for adaptive sparsity allocation. Specifically, we introduce a weight-aware mechanism integrating activation magnitudes with precomputed weight norms to accurately identify salient channels. This is combined with a mixed-granularity allocation scheme: a global budget is distributed across blocks via evolutionary search to protect sensitive regions, then refined within blocks to minimize reconstruction error. We improve sparse kernels and demonstrate effectiveness on three representative models. Notably, at 50% sparsity, WiSparse preserves 97% of Llama3.1's dense performance, surpassing the strongest baseline by 2.23 percentage points while achieving a 21.4% acceleration in end-to-end inference speed. Our research advances the limits of training-free approaches for efficient LLM inference, pushing the boundaries of achievable speedup without training.

Training Multimodal Large Reasoning Models Needs Better Thoughts: A Three-Stage Framework for Long Chain-of-Thought Synthesis and Selection

✇cs.AI, q-bio.NC updates on arXiv.org
By: Yizhi Wang · Linan Yue · Min-Ling Zhang
17 February 2026 at 13:00
arXiv:2512.18956v2 Announce Type: replace Abstract: Large Reasoning Models (LRMs) have demonstrated remarkable performance on complex reasoning tasks through long Chain-of-Thought (CoT) reasoning. Extending these successes to multimodal reasoning remains challenging due to the increased complexity of integrating diverse input modalities and the scarcity of high-quality long CoT training data. Existing multimodal datasets and CoT synthesis methods still suffer from limited reasoning depth, modality conversion errors, and rigid generation pipelines, hindering model performance and stability. To this end, in this paper, we propose SynSelect, a novel three-stage Synthesis-Selection framework for generating high-quality long CoT data tailored to multimodal reasoning tasks. Specifically, SynSelect first leverages multiple heterogeneous multimodal LRMs to produce diverse candidate CoTs, and then applies both instance and batch level selection to filter high-quality CoTs that can effectively enhance the model's reasoning capabilities. Extensive experiments on multiple multimodal benchmarks demonstrate that models supervised fine-tuned on SynSelect-generated data significantly outperform baselines and achieve further improvements after reinforcement learning post-training. Our results validate SynSelect as an effective approach for advancing multimodal LRMs reasoning capabilities.
There are no more articles
❌