…Training Search Agents for Direct Corpus Interaction (2026) Superintelligent Retrieval Agent: The Next Frontier of Agentic Retrieval (2026) Retrieval as Reasoning: Self-Evolving Agent-Native Retrieval via LLM-Wiki (2026) Rethinking Agentic…
…We further characterize common failure modes across agents and identify opportunities for improving their reliability, autonomy, and scientific reasoning . Together, SciAgentArena provides a practical framework for measuring progress in AI agents for…
…Yigeng Jiang , , , , , , , , , , , , , , , , , , , , , Abstract PhySciBench benchmark reveals limited performance of current LLM agents in physical science research, leading to development of DelveAgent framework that improves accuracy through modular design and physics-grounded mechanisms…
…Yuwen Du , , , , , , , , , , Abstract PaSaMaster is a self-evolving agentic literature retrieval system that improves academic search accuracy and cost efficiency through iterative intent analysis and evidence-based ranking. AI-generated summary As…
…Amazon Authors: , , , , , , , , , , , , , , , , Abstract Automated agent evaluation using AI assistants requires specialized domain knowledge and procedural skills to achieve reliable results, as demonstrated by the EvalAgent system that improves evaluation accuracy through structured…
…Experiments on AgentDojo, AgentHarm, and ATBench show that FATE improves safety across different models and scales while preserving useful behavior. Compared with strong baselines, FATE reduces attack success rate by 33.5…
…AI-generated summary LLM-based evolution has emerged as a promising way to improve agents by refining non-parametric artifacts, but its wall-clock cost remains a major bottleneck. We identify that…
…Fine-tuning UI-TARS 7B on ProCUA-SFT for one epoch yields 45.0% on OSWorld -- an 18.7 percentage-point improvement over the base model and over 35% above AgentNet-trained…
…Tianpeng Bu , Xin Liu , , Hao Jiang , , , , , , Abstract GUI agents lack robust error recovery capabilities, which this work addresses through GUI-RobustEval and Robustness-driven Trajectory Synthesis, demonstrating improved performance on real-world…
…Across four customer-service domains and a mixed panel of open- and closed-weight models, Ledger Agent improves average passk over a standard prompt-based tool-calling approach, with the largest gains…
