VLA-Pro is a plug-and-play framework that enhances cross-task generalization in Vision-Language-Action models by storing and dynamically retrieving task-specific procedural memories, achieving signifi…

The paper introduces MMG2Skill, a closed-loop framework that converts noisy, human-oriented web guides into editable, executable skills, significantly improving agent performance across diverse tasks.

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 pause-and-think-T, a reasoning-centric dataset and benchmark that enables compact Vision-Language Models to perform visually grounded, context-aware action suggestion, matching la…

The paper argues that current embodied planning benchmarks prioritize superficial language prediction over true physical reasoning, introducing new benchmarks and a large-scale dataset to demonstrate…

The paper introduces a diagnostic framework to determine if World-Action Models (WAMs) provide genuinely actionable behavioral improvements beyond simply achieving task success, finding that WAMs ofte…

SkillRevise is an execution-grounded framework that iteratively refines initial, imperfect LLM agent skills by diagnosing defects from execution evidence and applying empirically validated edits, sign…

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…

GRASP introduces a gated, regression-aware framework for improving LLM agents by ensuring that every proposed skill edit improves performance on a balanced probe without degrading previously learned c…

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…

PRO-CUA introduces a process-reward optimization framework that enables efficient, step-level reinforcement learning for training computer use agents by decoupling environment interaction from policy…

The paper introduces Momento, a new benchmark that evaluates agentic AI's ability to maintain state and reason across multiple, disconnected sessions, revealing that current agents struggle with integ…

The paper introduces MindClaw, a closed-loop framework that enables embodied agents to perform real-time mental-state reasoning and intervene with precision, significantly outperforming standard VLM b…

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 Canonical-Context On-Policy Distillation (CCOPD) to improve multi-turn language model performance by mitigating 'self-anchored drift,' ensuring consistent answers regardless of wh…

The paper introduces SPADE-Bench, a new benchmark designed to rigorously evaluate 'agent deception'—the divergence between an agent's reported plan and its actual executed actions—which is a critical…

The paper introduces new benchmarks for complex asynchronous planning and demonstrates that general constraint satisfaction formalizers (like CP-SAT) significantly outperform direct LLM planning or tr…

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…

The paper introduces Graph-Distance Contribution Reward (GDCR) and Step Advantage Policy Optimization (SAPO) to provide fine-grained, step-level credit assignment for agentic search by modeling world…

The paper introduces CV-Arena, a large-scale open benchmark for instructional computer vision, demonstrating that professional-grade image editing requires advanced capabilities in physical reasoning…