ObserverBench is a benchmark framework that evaluates whether internal mechanistic estimators—called observers—are suitable for guiding interventions, control, or safety actions in language models. It separates estimation accuracy from the loss incurred by the chosen action, demonstrating that accurate average estimates can still lead to poor decisions. Experiments on GPT‑2‑small, Qwen2.5‑7B, Gemma‑2‑9B‑it, and Qwen3.5‑9B show that observers trained on action loss tend to select lower‑loss actions, while traditional metrics like AUROC can rank monitors differently from deployment loss, highlighting the need for task‑specific evaluation.
ObserverBench is a benchmark framework that evaluates whether internal mechanistic estimators—called observers—are suitable for guiding interventions, control, or safety actions in language models. It separates estimation accuracy from the loss incurred by the chosen action, showing that accurate predictions do not always lead to better decisions. Experiments on GPT‑2‑small, Qwen2.5‑7B, Gemma‑2‑9B‑it, and Qwen3.5‑9B demonstrate that observers trained on action loss can reduce deployment loss, while traditional metrics like AUROC may rank monitors differently from actual performance.
By Vijay Erramilli
arXiv:2609.07944v1 Announce Type: new
Abstract: Existing causal-inference benchmarks for LLMs mostly score method descriptions or whether generated code runs, not whether the executed workflow recove...
By Yonghong Zhang, Ricardo Correia, Isabel M. Parra, Yong Xie
arXiv:2606. 02965v1 Announce Type: new Abstract: Benchmarks for autonomous agents measure whether agents complete tasks, yet this framing is systematically blind to whether an agent should have proceeded at all.
By Victor Ojewale, Suresh Venkatasubramanian
arXiv:2607. 08065v1 Announce Type: new Abstract: LLM-as-judge (Zheng et al.
By Kaihua Ding
Agent evaluations tell us that a model picked the wrong tool, but rarely why. We introduce canary tools: diagnostic probe tools planted in an agent's Model Context Protocol (MCP) tool set, each engineered to probe one specific tool-selection weakness.
arXiv:2608. 12489v1 Announce Type: new Abstract: Organizations decide whom to treat under a budget and want to know what a targeting rule would have earned before deploying it.
By Binshuang Li
arXiv:2608. 04719v1 Announce Type: new Abstract: Agent evaluations tell us that a model picked the wrong tool, but rarely why.
By Atul Anand, Sourav Chattaraj
arXiv:2608. 11727v1 Announce Type: new Abstract: When a coding agent obeys a rule, it may simply have been going to do that anyway.
By Zining Huang, Haoran Que, Hong Zeng, Ge Zhang, Zuo Wang, Jin Chen, Haodong Wang, Zhongfei Hou, Changxin Pu, Shen Yan, Wenhao Huang
The paper investigates the reliability of tool‑using agents, focusing on two failure modes: selecting the wrong tool and constructing incorrect arguments. It introduces a correct‑invocation rate metric to distinguish these errors and evaluates five open‑weight models on multi‑step tasks up to depth 8, finding that by depth 6 about 70% of a model’s clean‑context capability is lost due to earlier mistakes. The study reveals that exact‑match scoring against a fixed gold trajectory forces severity and recovery parameters to extreme values, and proposes a conditional‑on‑state scoring remedy that yields more realistic severity estimates.
By Afiya Noorain, Subhranshu Mohanty, Amritesh Banerjee, Abhijit Dasgupta
arXiv:2606. 11686v1 Announce Type: cross Abstract: End-to-end task-success is the dominant way to evaluate LLM agents, but one aggregate number tells you that an agent regressed, not where.
By Sawyer Zhang, Alexander Wang, Sophie Lei
arXiv:2607. 07097v1 Announce Type: new Abstract: Safety evaluations of multi-agent LLM systems often compare a direct prompt with a planner-executor pipeline and report the difference as a single "pipeline effect.
By Lifei Liu, Haoran Yu, Xiaochong Jiang, Su Wang, Pin Qian, Yihang Chen