arXiv:2607. 20764v1 Announce Type: new Abstract: We introduce ARBIGRAPH, a benchmark generator for evaluating whether tool-assisted language agents can retain, update, compose, and discard task-relevant context across extended reasoning workflows.
arXiv:2608. 02650v1 Announce Type: new Abstract: Large language model (LLM) agents increasingly rely on external tools to complete complex real-world tasks.
arXiv:2605. 21850v2 Announce Type: replace-cross Abstract: Recent development of agents has renewed demand for long-context reasoning capacity of LLMs.
OS-Marathon is a new benchmark that tests computer‑use agents on vast‑horizon, repetitive tasks, covering 100 tasks across five scenarios and ten domains. The study shows that current state‑of‑the‑art agents perform poorly on these tasks, and that simply decomposing workflows into subtasks does not solve the problem. Introducing a cost‑friendly personalization method called GraphDemo, which adapts agents from a single human demonstration, improves performance, highlighting the value of human guidance for these challenging tasks.
arXiv:2603.18614v2 Announce Type: replace Abstract: Tool-augmented large language models (LLMs) must tightly couple multi-step reasoning with external actions, yet existing benchmarks often confound...
arXiv:2608. 10039v1 Announce Type: new Abstract: Agentic workflows have become an important abstraction for building reliable LLM-based automation systems by organizing large language models (LLMs), tools, and control logic into explicit execution structures.
The paper introduces Harness Primitives—reusable agent harness mechanisms mined from failed task trajectories—and a framework called STITCH that selects and composes these primitives into task‑specific harnesses at test time. This approach avoids generating or debugging harness code for each task, achieving up to 12‑point gains in task success over fixed harness baselines and outperforming human‑designed harnesses like Codex CLI. STITCH also demonstrates minimal test‑time overhead (2.7%) and scales efficiently with the size of the primitive library.
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. 12391v1 Announce Type: cross Abstract: Graph reasoning provides a promising testbed for evaluating the reasoning ability of large language models (LLMs), as graph instances can be programmatically generated, structurally controlled, and naturally scaled to long-input settings.
AnyAct introduces a universal action layer that consolidates diverse tool capabilities into a self‑evolving action space for AI agents operating in open‑world environments. It tackles the scale dilemma, tool non‑stationarity, and heterogeneous feedback by using hierarchical progressive retrieval and test‑time reliability evolution, while a heterogeneous observation grounding module unifies multi‑modal feedback. Evaluations on LiveMCPBench and the newly created OSMCP benchmark show state‑of‑the‑art performance, with significant gains in task success rate and reduced execution steps, especially for models with limited native capabilities.
arXiv:2607. 23678v1 Announce Type: new Abstract: Large language models (LLMs) enable autonomous agents for reasoning, planning, and tool use.
Large language model (LLM) agents often perform poorly on complex, long-horizon tasks because their context becomes increasingly cluttered over time. As interactions accumulate, detailed execution tra...
arXiv:2607. 05174v1 Announce Type: new Abstract: Language agents, i.