The paper introduces K-BrowseComp, a new web-browsing agent benchmark of 400 problems grounded in Korean contexts, demonstrating that current frontier LLMs struggle significantly with complex, context…

This paper analyzes tool-calling in LLM agents, demonstrating that evaluation results are highly sensitive to implementation details and proposing new techniques to significantly improve the efficienc…

The paper introduces BenchTrace, a novel benchmark designed to rigorously evaluate the self-evolution and reflection capabilities of LLM agents, revealing that current models struggle with accurate fa…

The paper introduces BenchJack, an automated red-teaming system that systematically audits popular AI agent benchmarks, revealing numerous reward-hacking exploits and demonstrating a method to signifi…

The paper introduces AsyncTool, a new benchmark designed to evaluate LLM agents' ability to handle multiple, concurrent tasks with delayed tool feedback, demonstrating that asynchronous coordination i…

The paper introduces EgoBench, the first interactive multimodal benchmark designed to jointly evaluate advanced AI agents' capabilities in visual perception, multi-hop reasoning, and dynamic tool usag…

The paper introduces CRAB-Bench and RUSE, a rigorous evaluation framework that tests LLM agents on complex, interdependent tasks with realistic human user interactions, revealing significant performan…

The paper introduces BlueFin, a challenging benchmark for evaluating LLM agents on complex financial spreadsheet tasks, finding that even frontier models perform poorly, scoring less than 50% on avera…

SCOPE introduces a data-free self-play framework that co-evolves a task-generating Challenger and a document-answering Solver, significantly improving open-ended performance on language models without…

The paper argues that observed gains in multimodal agents using tools may be due to learning tool-calling patterns rather than genuine capability expansion, finding that tool access provides little co…

BenchEvolver introduces a solution-centric evolutionary framework to automatically transform saturated coding benchmarks into significantly harder, high-quality, and diverse evaluation suites.

The paper introduces SkillBrew, a multi-objective framework that treats skill bank curation as a constrained optimization problem to build efficient and well-curated skill repositories for LLM agents.

The paper proposes Skill-RM, a unified framework that treats reward modeling as an agentic task to consistently integrate diverse evaluation criteria, achieving superior performance over traditional m…

The paper presents a large-scale study demonstrating that tool cloning is a pervasive and severe source of hidden duplication in agent-tool ecosystems, necessitating changes in how tool diversity is m…

SelSkill introduces a dual-granularity preference learning framework that treats skill use as a 'skill-or-skip' decision, significantly improving agent performance and execution precision in complex a…

The paper introduces RoboWits, a new bi-manual robotic benchmark designed to test a robot's cognitive reasoning and adaptability to unexpected challenges, revealing that current Vision-Language-Action…

The paper introduces Grounded Agentic Interaction Synthesis (GAIS), a framework that generates high-quality, diverse, and complex agentic training data by anchoring tasks to real-world protocols, sign…

The paper introduces Unified Context Evolution (UCE), a gradient-free framework that externalizes and manages agent experience into a typed, evolving library, significantly improving performance on mu…

The paper introduces GTA, a scalable framework for generating realistic, multi-hop web-agent tasks with dense, executable trajectories, addressing the current lack of process-level supervision in web…

ExpGraph is a model-agnostic framework that uses a self-evolving experience graph to enable LLM agents to reuse past successful strategies and failure lessons, significantly improving performance acro…