arXiv:2606. 01416v1 Announce Type: new Abstract: Tool-augmented large language model (LLM) agents rely on orchestration layers that coordinate planning, retrieval, tool invocation, validation, memory, and recovery.
arXiv:2607. 02873v1 Announce Type: cross Abstract: Large language model agents driving security tool suites over the Model Context Protocol are increasingly common.
The paper introduces Growing Harness, a training method that transforms recurring control logic in large language model agents into reusable executable code, reducing reliance on the model for task-specific decisions. By using strategy-free scaffolds, failure-guided code repair, and success-first gating, the approach learns a shared harness that improves performance across multiple benchmarks and model sizes. Experiments on BrowseComp-Plus and WebArena-Verified show significant gains in success rates and substantial reductions in LLM calls and inference cost compared to traditional tool‑calling agents.
arXiv:2608.25920v2 Announce Type: replace Abstract: As large language model (LLM)-based multi-agent systems (MASs) are increasingly applied to long-horizon complex tasks, their reliability has emerge...
UniACE is a unified framework that standardizes the evaluation of large language model (LLM) agents by representing each benchmark as an instruction–tool–environment triplet and running models through a shared, task‑agnostic harness in isolated runtimes. It preserves native success criteria, offers an offline mode for dynamic‑resource tasks, and standardizes efficiency metrics, execution records, and failure attribution. Applying UniACE to 7 benchmarks across 24 domains and 15 models revealed significant score shifts, ranking reversals, and sensitivity to evidence representation, highlighting the impact of evaluation configuration on reported agent performance.
ToolRobustBench is a stage-wise diagnostic benchmark designed to evaluate and diagnose failures in tool‑calling agents, which are large language models that select tools, provide structured arguments, and interpret tool feedback. The benchmark aligns four perturbation families—tool‑interface, user‑intent, tool‑output/observation, and runtime‑environment—with the tool‑use pipeline, attributing failures to specific stages such as tool selection, schema grounding, argument binding, and feedback handling. Experiments across 15,456 instances, 7 models, and 16 local tools reveal that while overall performance is high, robustness degrades significantly, especially under tool‑output/observation perturbations, and mixed‑family perturbations produce non‑additive failure patterns.
arXiv:2608. 02645v1 Announce Type: cross Abstract: Large Language Model (LLM) agents rely on external tools to perform multistage tasks.
Self-correction is particularly useful when a failure constrains the next repair. Coding agents benefit from this property because compilers, tests, and execution traces turn many failures into typed recovery signals, but broad language-agent tasks often expose only a coarse task failure.
ParaRecover is a new process-level benchmark designed to evaluate error localization and recovery in multi-turn parallel tool-use agents. It contains 10,626 instances across two difficulty levels, built on a taxonomy of 14 error types that cover planning dependencies, tool selection, and argument matching. The benchmark introduces the SDE rubric, which assesses structural integrity, diagnostic reasoning, and evolutionary strategy during agent execution, and demonstrates that it can guide improvements in agents’ reflective recovery capabilities.
arXiv:2606. 05806v1 Announce Type: new Abstract: Existing benchmarks evaluate Tool-Integrated Reasoning (TIR) in LLMs on idealized ''happy paths'', largely overlooking real-world tool failures.
arXiv:2608. 05263v1 Announce Type: new Abstract: Multi-agent orchestration frameworks are moving from demos to production, yet benchmarks typically report task accuracy without diagnosing why a pipeline failed, where a cascade began, or which routing decision caused the breakdown.
arXiv:2607. 11098v1 Announce Type: cross Abstract: Tool-using LLM agents are mostly evaluated assuming all tools work.
arXiv:2607. 16215v1 Announce Type: new Abstract: Existing guardrail systems for large language model agents operate as binary classifiers that block unsafe content, leaving organizations to discard failing outputs and retry from scratch.