D-VLA framework uses 'Plane Decoupling' and a four-thread asynchronous pipeline to enhance VLA model sampling efficiency and throughput.

Yucheng Guo, Yongjian Guo, Zhong Guan et al.

Automated red-teaming system BenchJack detects 8 classes of benchmark flaws, improving robustness.

Hao Wang, Hanchen Li, Qiuyang Mang et al.

ToolCUA optimizes GUI-Tool path selection via staged training, achieving 46.85% accuracy.

Xuhao Hu, Xi Zhang, Haiyang Xu et al.

The study proposes a framework to diagnose reward hacking in rubric-based RL, finding that even strong verification does not eliminate reward hacking.

Anas Mahmoud, MohammadHossein Rezaei, Zihao Wang et al.

DR-Gym environment optimizes electric utility demand response using reinforcement learning, enhancing grid flexibility and energy affordability.

Jose E. Aguilar Escamilla, Lingdong Zhou, Xiangqi Zhu et al.

Proposes Executable Agentic Memory (EAM) using knowledge graphs to enhance long-horizon GUI planning, achieving 19.6% success improvement and 6× cost reduction.

Zerui Qin, Sheng Yue, Xingyuan Hua et al.

BadSKP is a multi-stage optimization backdoor attack targeting graph-to-prompt interfaces in KG-enhanced LLMs, achieving over 90% success rate.

Xiaoting Lyu, Yufei Han, Hangwei Qian et al.

AutoLLMResearch employs multi-fidelity environments and long-horizon MDPs to automate high-cost LLM experiment configuration, guided by low-cost trials.

Taicheng Guo, Nitesh V. Chawla, Olaf Wiest et al.

QUIVER framework quantifies perturbation propagation and bifurcation in heterogeneous LLM pipelines using sensitivity matrices and trajectory divergence metrics.

Prashanti Nilayam, Sankalp Nayak

PathISE leverages transformer-based MIL to estimate path informativeness, boosting KGQA accuracy and efficiency.

Shengxiang Gao, Chao Lei, Jey Han Lau et al.

RADAR uses conditional graph diffusion to generate low-redundancy communication topologies, improving accuracy and efficiency.

Zhen Zhang, Wanjing Zhou, Juncheng Li et al.

EpiGraph constructs a large-scale epilepsy knowledge graph, boosting LLM clinical reasoning by 30-41% across five tasks.

Yuyang Dai, Zheng Chen, Jathurshan Pradeepkumar et al.

Introduces Posterior Distillation Index (PDI) via online trajectory verification within SPARK, significantly improving transferable skills grounded in environment interaction.

Yang Zhou, Zihan Dong, Zhenting Wang et al.

Proposes an LLM-based agent framework for automatic SCIP plugin generation, improving MIP solving by identifying global constraints and propagators.

Liding Xu, Yugeng Zhou, Sebastian Pokutta

FORTIS benchmark quantifies over-privilege in large models' skill selection and execution, with failure rates exceeding 62.5%, revealing systemic permission control issues.

Shawn Li, Chenxiao Yu, Han Wang et al.

Transforming Alpamayo 1 into a single-reasoning architecture reduces inference latency by 69.23%, maintaining trajectory diversity.

Yunseong Jeon, Namcheol Lee, Yoonsu Lee et al.

EvoMAS framework enhances complex task success by constructing execution-time multi-agent workflows.

Chengdong Xu, Kaiqiang Ke, Ziheng Liu et al.

Proposes WLDS system combining factual and logical calibration for multi-domain emergency scenario deduction with 8.5% accuracy boost.

Zhengqing Hu, Dong Chen, Junkun Yuan et al.

Proposes 'Binding Constraint Thesis', showing scheduler configuration impacts long-horizon LLM performance more than model upgrades, advocating for disclosure.

Yunbei Zhang, Janet Wang, Yingqiang Ge et al.

Introduces bridge interface theory, separating prediction, compression, and empowerment; proves perfect prediction requires identifying latent quotients or control capacity.

Richard Csaky