Related papers: Beyond pass@1: A Reliability Science Framework for…

Existing agent-safety evaluation has focused mainly on externally induced risks. Yet agents may still enter unsafe trajectories under benign conditions. We study this complementary but underexplored setting through the lens of…

Autonomous agents based on Large Language Models (LLMs) are increasingly being utilized in complex software systems. However, reliability remains a significant challenge due to unpredictable failures such as hallucinations, execution…

Multi-Agent Reinforcement Learning (MARL) has shown clear effectiveness in coordinating multiple agents across simulated benchmarks and constrained scenarios. However, its deployment in real-world multi-agent systems (MAS) remains limited,…

Many AI alignment discussions of "runaway optimisation" focus on RL agents: unbounded utility maximisers that over-optimise a proxy objective (e.g., "paperclip maximiser", specification gaming) at the expense of everything else. LLM-based…

Context: ChatGPT and other large language models (LLMs) are widely used across healthcare, business, economics, engineering, and software engineering (SE). Despite their popularity, concerns persist about their reliability, especially their…

The prevailing assumption of an exponential decay in large language model (LLM) reliability with sequence length, predicated on independent per-token error probabilities, posits an inherent limitation for long autoregressive outputs. Our…

Modern language agents must operate over long-horizon, multi-turn interactions, where they retrieve external information, adapt to observations, and answer interdependent queries. Yet, most LLM systems rely on full-context prompting,…

As LLM agents transition from short, static problem solving to executing complex, long-horizon tasks in dynamic environments, the ability to handle user interruptions, such as adding requirement or revising goals, during mid-task execution…

LLM agents increasingly run inside execution harnesses that dispatch tools, allocate resources, and route messages between specialized components. However, a harness can return a correct, benign answer over a trajectory that accesses…

Large Language Model (LLM)-based agents are increasingly deployed for complex, tool-based tasks where long-term memory is critical to driving actions. Existing benchmarks, however, primarily test a angent's ability to passively retrieve…

Redundancy is widely used to sustain service continuity in programmable and virtualized networks; however, replicated functions often share platforms, software stacks, and control dependencies, making them vulnerable to correlated failures.…

Existing benchmarks for frontier models often test specialized, "PhD-level" knowledge that is difficult for non-experts to grasp. In contrast, we present a benchmark with 613 problems based on the NPR Sunday Puzzle Challenge that requires…

Recent work shows that fine-tuned Large Language Models (LLMs) can achieve high valid plan rates on PDDL planning tasks. However, it remains unclear whether this reflects transferable planning competence or domain-specific memorization. In…

With the rapid iteration of Multi-modality Large Language Models (MLLMs) and the evolving demands of the field, the number of benchmarks produced annually has surged into the hundreds. The rapid growth has inevitably led to significant…

We argue that current evaluation frameworks for large language models (LLMs) suffer from four systematic failures that make them structurally inadequate for deployed, agentic systems: distributional, temporal, scope, and process invalidity.…

Large Language Models (LLMs) effectiveness is usually evaluated by means of benchmarks such as MMLU, ARC-C, or HellaSwag, where questions are presented in their original wording, thus in a fixed, standardized format. However, real-world…

Recent progress in multimodal foundation models has enabled Vision-Language Agents (VLAs) to decompose complex visual tasks into executable tool-based plans. While recent benchmarks have begun to evaluate iterative self-correction, its…

Existing benchmarks for LLM-based vulnerability detection compress model performance into a single metric, which fails to reflect the distinct priorities of different stakeholders. For example, a CISO may emphasize high recall of critical…

Recent advancements in large language models (LLMs) have shown promise in feature engineering for tabular data, but concerns about their reliability persist, especially due to variability in generated outputs. We introduce a multi-level…

Autonomous agents powered by large language models (LLMs) are increasingly deployed in real-world applications requiring complex, long-horizon workflows. However, existing benchmarks predominantly focus on atomic tasks that are…