The performance bottleneck of agents is increasingly shifting from model capability to the robustness of their execution processes. Tools play a central role as the primary interface through which agents interact with external environments, yet existing methods rarely focus on ensuring robust tool use across diverse runtime conditions.
arXiv:2608. 03403v1 Announce Type: new Abstract: The performance bottleneck of agents is increasingly shifting from model capability to the robustness of their execution processes.
Self-evolving agents can continually improve their behavior, while tools define the executable action space through which they interact with the environment. However, exposing the full tool library to...
arXiv:2607. 14159v1 Announce Type: new Abstract: An agent harness is the external control layer that turns a base LLM into an executable agent by managing context, tools, orchestration, memory, decoding, and output handling.
arXiv:2602. 07883v3 Announce Type: replace Abstract: LLM-powered agentic systems excel at complex long-horizon tasks, but remain constrained by static configurations fixed before execution.
arXiv:2607. 01084v1 Announce Type: new Abstract: While Large Language Model (LLM) agents demonstrate proficiency in static benchmarks, their deployment in real-world scenarios is hindered by the dynamic nature of user queries, tool sets, and interaction dynamics.
HarnessEvolve is a self‑evolving framework that improves agent harnesses—prompts, skills, tools, and execution logic—by learning from reference trajectories. It separates execution, evaluation, optimization, and gating into independent modules, addressing credit assignment failure, shortcut learning, and catastrophic forgetting. The approach uses reference trajectories to extract error signals, applies quality and performance gates to candidate updates, and validates updates on held‑out data, consistently outperforming state‑of‑the‑art baselines across diverse benchmarks.
The paper introduces KNOWS, a benchmark for evaluating web agents that act as assistants by retrieving, synthesizing, and presenting information across complex, multi-step browser tasks. It outlines a task design rubric, evaluation protocol combining deterministic checks with LLM judgments, and reports that current agents achieve only modest success, with the best performing agent succeeding on less than 3% of tasks. The study highlights significant gaps in agents’ tool use, visual understanding, and long‑horizon reasoning.
arXiv:2608. 15071v1 Announce Type: new Abstract: Learning from experience is critical for developing capable, self-improving large language model (LLM) agents.
arXiv:2609.33772v2 Announce Type: replace Abstract: Executable environments are critical for post-training agents on tasks that require tool use and multi-step interaction, but constructing executabl...
arXiv:2512. 07287v3 Announce Type: replace-cross Abstract: As intents unfold and environments change, multi-turn agents face continuously shifting decision contexts.
ToolCUA is an end‑to‑end agent that learns to optimally orchestrate GUI actions and tool calls for Computer Use Agents. It introduces a staged training pipeline that first scales interleaved GUI‑tool trajectories from static GUI data, then bootstraps decision making with single‑turn reinforcement learning, and finally refines performance via online agentic RL guided by a tool‑efficient path reward. On the OSWorld‑MCP benchmark, ToolCUA achieves 46.85% accuracy, a 66% relative improvement over the baseline and a 3.9% gain over GUI‑only models, setting a new state of the art for comparable‑scale models.
OpenClaw has emerged as a leading agent framework for complex task automation, yet it faces insufficient cross-platform GUI interaction support and a well-built self-evolution mechanism. These flaws limit its adaptation to diverse device ecosystems and prevent performance improvements through continuous learning from execution experience.