Related papers: EvolveTool-Bench: Evaluating the Quality of LLM-Ge…

The ability to use, understand, and create tools is a hallmark of human intelligence, enabling sophisticated interaction with the physical world. For any general-purpose intelligent agent to achieve true versatility, it must also master…

Large Language Models (LLM) are increasingly used for software development, yet existing benchmarks for LLM-based coding assistance do not reflect the constraints of High Energy Physics (HEP) and High Performance Computing (HPC) software.…

The emergence of large language models (LLMs) has significantly pushed the frontiers of program synthesis. Advancement of LLM-based program synthesis calls for a thorough evaluation of LLM-generated code. Most evaluation frameworks focus on…

Modern Large Language Model (LLM) agents promise end to end assistance with real-world software tasks, yet existing benchmarks evaluate LLM agents almost exclusively in pre-baked environments where every dependency is pre-installed. To fill…

The rapid proliferation of large language models (LLMs) has intensified the requirement for reliable safety evaluation to uncover model vulnerabilities. To this end, numerous LLM safety evaluation benchmarks are proposed. However, existing…

How to evaluate the coding abilities of Large Language Models (LLMs) remains an open question. We find that existing benchmarks are poorly aligned with real-world code repositories and are insufficient to evaluate the coding abilities of…

As LLM-based agents increasingly rely on external tools, it is important to evaluate their ability to sustain tool-grounded reasoning beyond familiar workflows and short-range interactions. We introduce AgentEscapeBench, an…

In this work, we make the first attempt to evaluate LLMs in a more challenging code generation scenario, i.e. class-level code generation. We first manually construct the first class-level code generation benchmark ClassEval of 100…

LLM agents are increasingly deployed as executable systems that use tools, modify workspaces, and produce concrete artifacts. In such workflows, performance depends not only on the base model, but also on the harness: the system layer that…

The increasing complexity of computer science research projects demands more effective tools for deploying code repositories. Large Language Models (LLMs), such as Anthropic Claude and Meta Llama, have demonstrated significant advancements…

Artificial Intelligence (AI)-driven code generation tools are increasingly used throughout the software development lifecycle to accelerate coding tasks. However, the security of AI-generated code using Large Language Models (LLMs) remains…

Evaluating Large Language Models (LLMs) with respect to real-world code complexity is essential. Otherwise, there is a risk of overestimating LLMs' programming abilities based on simplistic benchmarks, only to be disappointed when using…

We introduce ETOM, a five-level benchmark for evaluating multi-hop, end-to-end tool orchestration by LLM agents within a hierarchical Model-Context Protocol (MCP) ecosystem. Existing benchmarks often assess tools in isolation, overlooking…

The issue-resolving task, where a model generates patches to fix real-world bugs, has emerged as a critical benchmark for evaluating the capabilities of large language models (LLMs). While SWE-bench and its variants have become standard in…

Large Language Models (LLMs) are rapidly becoming ubiquitous both as stand-alone tools and as components of current and future software systems. To enable usage of LLMs in the high-stake or safety-critical systems of 2030, they need to…

Tool-integrated LLMs can retrieve, compute, and take real-world actions via external tools, but reliability remains a key bottleneck. We argue that failures stem from both tool-use accuracy (how well an agent invokes a tool) and intrinsic…

Large Language Models (LLMs), with their exceptional ability to handle a wide range of tasks, have driven significant advancements in tackling reasoning and planning tasks, wherein decomposing complex problems into executable workflows is a…

The rapid advancement of Large Language Models (LLMs) poses a significant challenge to existing mathematical reasoning benchmarks. However, these benchmarks tend to become easier over time as LLMs can learn from the published benchmarks.…

We present two comprehensive benchmarks to evaluate the performance of language models in coding assistance tasks, covering code writing, debugging, code review, and conceptual understanding. Our main contribution includes two curated…

Agent Skills are structured packages of procedural knowledge that augment LLM agents at inference time. Despite rapid adoption, there is no standard way to measure whether they actually help. We present SkillsBench, a benchmark of 86 tasks…