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…

The paper introduces WebSP-Eval, a new framework to evaluate web agents on complex website security and privacy tasks, finding that current state-of-the-art models struggle significantly with stateful…

LongTraceRL addresses long-context reasoning challenges by generating highly challenging training data and introducing a fine-grained rubric reward, significantly improving evidence-grounded reasoning…

This paper empirically demonstrates that the choice of plan representation (e.g., checklist vs. narrative) significantly impacts the robustness and success rate of LLM-based web agents.

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 OpenWebRL, an open framework that enables training visual web agents using online multi-turn Reinforcement Learning directly on live websites, achieving state-of-the-art performan…

The paper proposes SCALE, a self-improving web agent framework that uses adversarial roles and graph exploration to autonomously discover agent limitations and enhance adaptability in complex web envi…

The paper argues that web agents should abandon the reactive ReAct paradigm in favor of a plan-then-execute approach, which requires developing typed, task-level APIs to properly structure web interac…

The paper introduces a data-centric optimization pipeline to improve coding agents' ability to interact with a branching lakehouse, showing significant accuracy gains by treating agent evaluation as a…

The paper introduces TASTE, an automatic task synthesis method that generates challenging agent benchmarks by evolving tool sequences, demonstrating that existing benchmarks are saturated and that TAS…

The paper introduces VibeSearchBench, a new benchmark designed to evaluate long-horizon, proactive search capabilities, demonstrating that current state-of-the-art LLM agents are still significantly i…

GrepSeek introduces a novel direct corpus interaction (DCI) search agent that trains an LLM to find and compose evidence from large text corpora by issuing executable shell commands, achieving state-o…

The paper proposes Multi-Agent Computer Use (MACU) systems, which significantly improve performance on complex, long-horizon tasks by enabling parallel execution and dynamic task decomposition compare…

This paper proposes the first web-focused threat model for agentic browsers, demonstrating that traditional web social engineering attacks can be amplified into dangerous, reproducible threats when ex…

The paper introduces Andes, a framework that treats data generation as a plug-and-play agent skill, enabling autonomous alignment of LLMs by providing an intelligent, closed-loop data synthesis interf…

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…

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…

ExpWeaver introduces a novel framework for LLM agents to learn from past experiences using latent retrieval-augmented generation, achieving state-of-the-art performance while significantly improving t…

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…

The paper introduces LearnWeak, an annotation-free framework that automatically specializes small computer-use agents by identifying and targeting their specific weaknesses using a stronger reference…