Key papers

• ModernBERT or DeBERTaV3? Examining Architecture and Data Influence on Transformer Encoder Models Performance (2025)
  Wissam Antoun et al.
  3.81
• Multimodal Continuous Reasoning via Asymmetric Mutual Variational Learning (2026)
  Shijie Li et al.
  2.00
• AgenticDataBench: A Comprehensive Benchmark for Data Agents (2026)
  Zhaoyan Sun et al.
  2.00
• VIBE: Visual Instruction Based Editor (2026)
  Grigorii Alekseenko et al.
  1.94
• Your Group-Relative Advantage Is Biased (2026)
  Fengkai Yang et al.
  1.94
• EvoFSM: Controllable Self-Evolution for Deep Research with Finite State Machines (2026)
  Shuo Zhang et al.
  1.94
• The Side Effects of Being Smart: Safety Risks in MLLMs' Multi-Image Reasoning (2026)
  Renmiao Chen et al.
  1.94
• Wiki Live Challenge: Challenging Deep Research Agents with Expert-Level Wikipedia Articles (2026)
  Shaohan Wang et al.
  1.94
• FullStack-Agent: Enhancing Agentic Full-Stack Web Coding via Development-Oriented Testing and Repository Back-Translation (2026)
  Zimu Lu et al.
  1.94
• P1-VL: Bridging Visual Perception and Scientific Reasoning in Physics Olympiads (2026)
  Yun Luo et al.
  1.94
• SenTSR-Bench: Thinking with Injected Knowledge for Time-Series Reasoning (2026)
  Zelin He et al.
  1.94
• ISO-Bench: Can Coding Agents Optimize Real-World Inference Workloads? (2026)
  Ayush Nangia et al.
  1.94
• CMI-RewardBench: Evaluating Music Reward Models with Compositional Multimodal Instruction (2026)
  Yinghao Ma et al.
  1.94
• The PokeAgent Challenge: Competitive and Long-Context Learning at Scale (2026)
  Seth Karten et al.
  1.94
• CREval: An Automated Interpretable Evaluation for Creative Image Manipulation under Complex Instructions (2026)
  Chonghuinan Wang et al.
  1.94
• PRBench: End-to-end Paper Reproduction in Physics Research (2026)
  Shi Qiu et al.
  1.94
• VideoZeroBench: Probing the Limits of Video MLLMs with Spatio-Temporal Evidence Verification (2026)
  Jiahao Meng et al.
  1.94
• HiL-Bench (Human-in-Loop Benchmark): Do Agents Know When to Ask for Help? (2026)
  Mohamed Elfeki et al.
  1.94
• MERRIN: A Benchmark for Multimodal Evidence Retrieval and Reasoning in Noisy Web Environments (2026)
  Han Wang et al.
  1.94
• VEFX-Bench: A Holistic Benchmark for Generic Video Editing and Visual Effects (2026)
  Xiangbo Gao et al.
  1.94
• Latent Preference Modeling for Cross-Session Personalized Tool Calling (2026)
  Yejin Yoon et al.
  1.94
• Dual-View Training for Instruction-Following Information Retrieval (2026)
  Qingcheng Zeng et al.
  1.94
• PatRe: A Full-Stage Office Action and Rebuttal Generation Benchmark for Patent Examination (2026)
  Qiyao Wang et al.
  1.94
• Uncovering Entity Identity Confusion in Multimodal Knowledge Editing (2026)
  Shu Wu et al.
  1.94
• Editor's Choice: Evaluating Abstract Intent in Image Editing through Atomic Entity Analysis (2026)
  Mor Ventura et al.
  1.94
• AgentKernelArena: Generalization-Aware Benchmarking of GPU Kernel Optimization Agents (2026)
  Sharareh Younesian et al.
  1.94
• SimuWoB: Simulating Real-World Mobile Apps for Fast and Faithful GUI Agent Benchmarking (2026)
  Guohong Liu et al.
  1.94
• LLaVA-OneVision-2: Towards Next-Generation Perceptual Intelligence (2026)
  Xiang An et al.
  1.94
• OmniInteract: Benchmarking Real-World Streaming Interaction for Real-Time Omnimodal Assistants (2026)
  Xudong Lu et al.
  1.94
• LiveBrowseComp: Are Search Agents Searching, or Just Verifying What They Already Know? (2026)
  HuiMing Fan et al.
  1.94
• ForeSci: Evaluating LLM Agents for Forward-Looking AI Research Judgment (2026)
  Qiuyu Tian et al.
  1.94
• K-BrowseComp: A Web Browsing Agent Benchmark Grounded in Korean Contexts (2026)
  Nahyun Lee et al.
  1.94
• Memory is Reconstructed, Not Retrieved: Graph Memory for LLM Agents (2026)
  Shuo Ji et al.
  1.94
• Benchmark Everything Everywhere All at Once (2026)
  Shiyun Xiong et al.
  1.94
• Precision Is Not Faithfulness: Coverage-Aware Evaluation of Grounded Generation with a Complete Oracle (2026)
  Juan S. Santillana
  1.94
• DeNovoSWE: Scaling Long-Horizon Environments for Generating Entire Repositories from Scratch (2026)
  Jiale Zhao et al.
  1.94
• Deep Research in Physical Sciences: A Multi-Agent Framework and Comprehensive Benchmark (2026)
  Yigeng Jiang et al.
  1.94
• Are Text-to-Image Models Inductivist Turkeys? A Counterfactual Benchmark for Causal Reasoning (2026)
  Jiayi Lei et al.
  1.94
• Formalizing Latent Thoughts: Four Axioms of Thought Representation in LLMs (2026)
  Fahd Seddik et al.
  1.94
• TUA-Bench: A Benchmark for General-Purpose Terminal-Use Agents (2026)
  Shoufa Chen et al.
  1.94
• AtomiMed: Hierarchical Atomic Fact-Checking for Universal Clinical-Aware Medical Report Evaluation (2026)
  Yuan Wang et al.
  1.94
• UniClawBench: A Universal Benchmark for Proactive Agents on Real-World Tasks (2026)
  Zhekai Chen et al.
  1.94
• Diversed Model Discovery via Structured Table Discovery (2026)
  Zhengyuan Dong et al.
  1.89
• Omni-SimpleMem: Autoresearch-Guided Discovery of Lifelong Multimodal Agent Memory (2026)
  Jiaqi Liu et al.
  1.83
• Claw-Eval-Live: A Live Agent Benchmark for Evolving Real-World Workflows (2026)
  Chenxin Li et al.
  1.83
• TRIP-Bench: A Benchmark for Long-Horizon Interactive Agents in Real-World Scenarios (2026)
  Yuanzhe Shen et al.
  1.72
• Centurio: On Drivers of Multilingual Ability of Large Vision-Language Model (2025)
  Gregor Geigle et al.
  1.28
• WebWalker: Benchmarking LLMs in Web Traversal (2025)
  Jialong Wu et al.
  1.28
• Can We Generate Images with CoT? Let's Verify and Reinforce Image Generation Step by Step (2025)
  Ziyu Guo et al.
  1.28
• Chain-of-Retrieval Augmented Generation (2025)
  Liang Wang et al.
  1.28
• MetaChain: A Fully-Automated and Zero-Code Framework for LLM Agents (2025)
  Jiabin Tang et al.
  1.28
• mmE5: Improving Multimodal Multilingual Embeddings via High-quality Synthetic Data (2025)
  Haonan Chen et al.
  1.28
• GIMMICK -- Globally Inclusive Multimodal Multitask Cultural Knowledge Benchmarking (2025)
  Florian Schneider et al.
  1.28
• LettuceDetect: A Hallucination Detection Framework for RAG Applications (2025)
  Ádám Kovács et al.
  1.28
• Multimodal Representation Alignment for Image Generation: Text-Image Interleaved Control Is Easier Than You Think (2025)
  Liang Chen et al.
  1.28
• SwiLTra-Bench: The Swiss Legal Translation Benchmark (2025)
  Joel Niklaus et al.
  1.28
• IFIR: A Comprehensive Benchmark for Evaluating Instruction-Following in Expert-Domain Information Retrieval (2025)
  Tingyu Song et al.
  1.28
• CoSTAast: Cost-Sensitive Toolpath Agent for Multi-turn Image Editing (2025)
  Advait Gupta et al.
  1.28
• VERIFY: A Benchmark of Visual Explanation and Reasoning for Investigating Multimodal Reasoning Fidelity (2025)
  Jing Bi et al.
  1.28
• ETVA: Evaluation of Text-to-Video Alignment via Fine-grained Question Generation and Answering (2025)
  Kaisi Guan et al.
  1.28