The paper introduces a disclosure‑gated user simulator for companion‑agent evaluation, where information release is conditioned on the agent’s behavior through a five‑level gate system. The authors train the simulator on synthetic and real data, audit its performance, and demonstrate that it preserves ranking order and score stability across 12 tested systems. Their released simulator achieves a 0.993 correlation with the original benchmark’s simulator and outperforms prompting a frontier model, which only shifts scores upward without affecting rankings.
Using a large language model to play the user is now standard in scalable evaluation. It has a repeatedly diagnosed failure: the simulated user is excessively cooperative, so a system under test can s...
arXiv:2609.38043v1 Announce Type: new Abstract: Interactive agent benchmarks and multi-turn reinforcement learning increasingly place a second language model in the role of the user. This simulated u...
GAUGE is a new offline protocol that evaluates whether the common practice of using an LLM-as-a-judge to rank task‑oriented agents actually aligns with a verifiable reward. Across 25 agents from six providers on two benchmarks, GAUGE finds that user satisfaction scores are largely uncorrelated with task success, and that the judge’s ranking loses precision when agents are closely matched in performance. The study highlights a gap between ranking validity and construct validity in current evaluation practices.
arXiv:2606. 25760v1 Announce Type: new Abstract: Computer-use agents turn vision-language model (VLM) predictions into executable GUI clicks, so reliable uncertainty estimates are essential for rejection, calibration, miss-severity ranking, and spatial safety regions.
arXiv:2606. 14199v1 Announce Type: cross Abstract: Large language models are increasingly deployed as human simulators for interactive evaluation and social simulation.
arXiv:2607. 28074v1 Announce Type: cross Abstract: Computer-use agents learn from what their actions change, so training one needs applications it can act on, break and reset.
arXiv:2607. 02255v1 Announce Type: new Abstract: Memory for a long-horizon LLM agent is a contract about what each future decision is allowed to see.
arXiv:2610.03448v1 Announce Type: cross Abstract: LLM agents increasingly screen tool outputs with small prompt-injection detectors, and teams choose among detectors by their scores on public benchma...
arXiv:2607. 20436v1 Announce Type: cross Abstract: Safety evaluations often assume that behavior observed during testing reflects behavior in ordinary use, but fine-tuning can break this assumption.
arXiv:2608.21601v1 Announce Type: new Abstract: Benchmarks for scientific artificial intelligence are mostly written to be scored: multiple-choice questions, curated agent tasks with reference soluti...
arXiv:2604. 16706v2 Announce Type: replace Abstract: Automated evaluation of tool-using large language model (LLM) agents is widely assumed to be reliable, yet this assumption is rarely validated against human annotation.
The paper introduces Conservative Meta-Agent Search (CMAS), a method for adapting agent architectures in non‑stationary environments. CMAS retrieves archived designs, proposes typed graph edits, and evaluates them through paired shadow replay with variance‑penalized scoring and a simulated canary stage before promotion. Using the MetaInvest‑Bench simulator, CMAS reduces surrogate dynamic‑oracle regret and improves held‑out utility across 96 financial streams, while maintaining low false‑promotion rates and modest inference cost.