Related papers: SpecBench: Measuring Reward Hacking in Long-Horizo…

Automatically compiling open-source software (OSS) projects is a vital, labor-intensive, and complex task, which makes it a good challenge for LLM Agents. Existing methods rely on manually curated rules and workflows, which cannot adapt to…

As benchmarks grow in complexity, many apparent agent failures are not failures of the agent at all - they are failures of the benchmark itself: broken specifications, implicit assumptions, and rigid evaluation scripts that penalize valid…

Reinforcement Learning from Human Feedback (RLHF) remains vulnerable to reward hacking, where models exploit spurious correlations in learned reward models to achieve high scores while violating human intent. Existing mitigations rely on…

To identify safety violations, auditors often search over large sets of agent traces. This search is difficult because failures are often rare, complex, and sometimes even adversarially hidden and only detectable when multiple traces are…

Current benchmarks for coding evaluate language models (LMs) on concrete, well-specified tasks such as fixing specific bugs or writing targeted tests. However, human programmers do not spend all day incessantly addressing isolated tasks.…

The advances made by Large Language Models (LLMs) have led to the pursuit of LLM agents that can solve intricate, multi-step reasoning tasks. As with any research pursuit, benchmarking and evaluation are key corner stones to efficient and…

Coding agents powered by large language models are increasingly expected to perform realistic software maintenance tasks beyond isolated issue resolution. Existing benchmarks have shifted toward realistic software evolution, but they rarely…

Reward models are key in reinforcement learning from human feedback (RLHF) systems, aligning the model behavior with human preferences. Particularly in the math domain, there have been plenty of studies using reward models to align policies…

As large language models (LLMs) continue to advance in programming tasks, LLM-driven coding systems have evolved from one-shot code generation into complex systems capable of iterative improvement during inference. However, existing code…

The emergence of reinforcement learning in post-training of large language models has sparked significant interest in reward models. Reward models assess the quality of sampled model outputs to generate training signals. This task is also…

AI agents have become surprisingly proficient at software engineering over the past year, largely due to improvements in reasoning capabilities. This raises a deeper question: can these systems extend their capabilities to automate AI…

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…

Enterprise agents increasingly operate inside scoped retrieval systems, delegated workflows, and policy-constrained evidence environments. In these settings, access control can be enforced correctly while the system still produces an answer…

In practice, rigorous reasoning is often a key driver of correct code, while Reinforcement Learning (RL) for code generation often neglects optimizing reasoning quality. Bringing process-level supervision into RL is appealing, but it faces…

This paper presents insights from evaluating 16 frontier large language models (LLMs) on the WebApp1K benchmark, a test suite designed to assess the ability of LLMs to generate web application code. The results reveal that while all models…

The increasing autonomy of Large Language Models (LLMs) necessitates a rigorous evaluation of their potential to aid in cyber offense. Existing benchmarks often lack real-world complexity and are thus unable to accurately assess LLMs'…

Spatial transcriptomics assays are rapidly increasing in scale and complexity, making computational analysis a major bottleneck in biological discovery. Although frontier AI agents have improved dramatically at software engineering and…

As agentic AI systems increasingly operate autonomously, establishing trust through verifiable evaluation becomes critical. Yet existing benchmarks lack the transparency and auditability needed to assess whether agents behave reliably. We…

Today's AI models learn primarily through mimicry and refining, so it is not surprising that they struggle to solve problems beyond the limits set by existing data. To solve novel problems, agents should acquire skills for exploring and…

Large reasoning models such as OpenAI o1 and DeepSeek-R1 have demonstrated remarkable performance in complex reasoning tasks. A critical component of their training is the incorporation of reference-based reward systems within reinforcement…