arXiv:2607. 06624v1 Announce Type: new Abstract: We present AgentLens, a production-assessed benchmark for interactive code agents.
arXiv:2606. 13608v1 Announce Type: new Abstract: Agent systems are advancing quickly across domains, but their evaluation remains fragmented.
The paper argues that evaluating agents as fixed models is insufficient, proposing instead to treat them as configurable systems. Using a new benchmark of four scientific tasks, the authors analyze how five configuration aspects—task information, reasoning, self‑verification, time budget, and backbone model—affect performance, noting that about 54% of outcome variance arises from run‑to‑run differences even with the same settings. The study finds that providing more task information has the strongest impact, while interactions among settings (e.g., extra time only helps with adequate information or model capability) and the choice of verification tools significantly shape agent behavior.
As Large Language Models (LLMs) evolve into autonomous agents, the need for unified evaluation infrastructure becomes critical. However, current evaluation pipelines remain highly fragmented and tightly coupled, hindering reproducibility and causing redundant engineering.
arXiv:2602. 22480v4 Announce Type: replace Abstract: An important emerging application of coding agents is agent harness optimization: the iterative improvement of a target agent by editing and evaluating its code.
arXiv:2512. 04123v4 Announce Type: replace-cross Abstract: LLM-based agents already operate in production across many industries, yet we lack an understanding of what technical methods make deployments successful.
arXiv:2510. 09801v3 Announce Type: replace Abstract: While benchmarks measure the accuracy of LLM-powered agents, they mostly assume full automation, failing to represent the collaborative nature of real-world use cases.
arXiv:2608. 06329v1 Announce Type: cross Abstract: Task-oriented conversational agents are evaluated using curated or automatically generated benchmarks, yet benchmark quality is rarely assessed.
arXiv:2606. 17799v1 Announce Type: cross Abstract: Coding agents have become a major mode of software engineering, but the benchmarks we use to compare them were designed in a pre-agent era: they collapse model, harness, and environment into a single end-to-end score, typically computed against one reference solution, with no component-level signal for iteration.
arXiv:2607. 13705v1 Announce Type: new Abstract: As Large Language Models (LLMs) evolve into autonomous agents, the need for unified evaluation infrastructure becomes critical.
The paper presents EvalAgent, an AI assistant that automates agent evaluation by encoding domain expertise into evaluation skills such as procedural instructions, reusable code, and dynamic API retrieval. EvalAgent constructs a trace-based pipeline that outputs metrics, executable code, and reports, and is evaluated using a new meta-evaluation framework and AgentEvalBench. Results show that EvalAgent improves the Eval@1 metric from 17.5% to 65% and receives 79.5% human expert preference, while ablation studies confirm the importance of evaluation skills.
Harbor Adapters is a unified evaluation infrastructure that ports over 80 agentic benchmarks, enabling arbitrary agents to be tested across complex environments. The authors performed a large‑scale evaluation of 8 models on 54 benchmarks, using Terminus‑2 and three native harnesses, revealing detailed agent capabilities and failure modes. They also created Harbor‑Index, a curated set of 82 challenging tasks from 29 benchmarks, designed to be affordable yet comprehensive, with the best model achieving a 28.0% pass rate.
The paper introduces RuVerBench, a benchmark with 2,458 instances for evaluating the reliability of Large Language Models acting as judges (LaaJ) in verifying rubric compliance within agentic scenarios such as deep research and agentic coding. It systematically meta‑evaluates frontier LLMs, revealing that even the most advanced models perform well yet still produce substantial noise. The study also examines how prompt design, batching, and majority voting affect verification accuracy, noting that weaker models are more prompt‑sensitive, batched verification trades accuracy for efficiency, and majority voting offers diminishing returns.