Proposes SD-GPS framework using QwenVL3-2B for autoformalization and lemma proposing, achieving 86.4% accuracy on Geometry3K.

Can Li, Ting Zhang, Junbo Zhao et al.

ATOD combines annealed schedule and turn-level uncertainty weighting to boost multi-turn agent performance.

Qitai Tan, Zefang Zong, Mo Li et al.

BINEVAL decomposes evaluation into binary questions, enabling interpretable, multi-dimensional assessment with superior correlation to human judgments.

Sangwoo Cho, Kushal Chawla, Pengshan Cai et al.

JERP jointly updates experiential rule pool and policy, boosting decision accuracy in multi-step tasks.

Shicheng Ye, Chao Yu

AgentX employs a multi-agent system for autonomous self-iteration in industrial recommender systems, significantly boosting efficiency and business value.

Changxin Lao, Fei Pan, Guozhuang Ma et al.

Proposes AHOIS, a multi-agent system using Socratic questioning for autonomous discovery in high-dimensional physical systems, validated on multimode fiber platform.

Xianrui Zeng, Pengfei Liu, Yirui Zang et al.

Autodata uses meta-optimized agentic data scientists to generate high-quality synthetic data, significantly improving model performance.

Ilia Kulikov, Chenxi Whitehouse, Tianhao Wu et al.

MM-R2 framework improves accuracy in multimodal RAG by reasoning before retrieval.

Tianyu Yang, Shir Simon, Zhenzhen Li et al.

Using reasoning tokens as a proxy for reaction time, the study analyzes vision-language models' search behaviors across classic paradigms, revealing partial human-like signatures.

Farahnaz Wick

Introduces a structural certification framework using deep goal composition to filter specific transitions, with an error bound of O(1/n)+δ, enabling local validation of internal world models.

Yikai Lu, Yifei Wu, Xinyu Lu et al.

This paper critically analyzes Andreas & Günther's seven definitions of actual causation, revealing their logical equivalence and exposing flaws in their categorical distinctions.

Sander Beckers

FlowR2A learns reward-conditioned action distributions via flow matching, unifying dense reward supervision with proposal generation, achieving state-of-the-art in multimodal driving planning.

Xirui Li, Zhe Liu, Xiaoqing Ye et al.

RIFT-Bench provides a dynamic red-teaming method for unified evaluation of diverse agentic AI systems.

Yarin Yerushalmi Levi, Roy Betser, Amit Giloni et al.

VeriEvol employs iterative prompt evolution and offline answer verification to scale visual math reasoning data from 10K to 250K, boosting accuracy by 19.31%.

Haoling Li, Kai Zheng, Jie Wu et al.

EHR-Complex is a large-scale interactive clinical reasoning benchmark based on MIMIC-IV, with an average SQL complexity of 31.93 components and top model accuracy of 62.3%.

Yitong Qiao, Lei Liu, Yue Shen et al.

Proposes a formula-driven taxonomy for on-policy distillation, analyzing stability and performance with emphasis on temporal credit and vocabulary routing.

Bowen Zhang

PAPERCLAW employs a multi-agent system with a stoppable hypothesis map to automate research from literature curation to paper writing, integrating human-in-the-loop.

Weiwei Ye, Hangchen Liu, Dongyuan Li et al.

Proposes GRPO with JS divergence to balance performance and diversity in LlamaGen and Janus-7B.

Yuanhao Chiang, Hongbo Duan, Chunru Yang et al.

Answer Engineering uses local trajectory editing to improve protocol compliance in LLMs, boosting SSNHL compliance from 25.1% to 83.5%.

Victor Lavrenko, Anastasiia Molodnitskaia

FaraGen1.5 enables scalable data generation for computer use agents using modular components, achieving 72.3% on Online-Mind2Web with Fara1.5-27B.

Ahmed Awadallah, Sahil Gupta, Yash Lara et al.