Related papers: When Should an AI Workflow Release? Always-Valid I…

We introduce self-invoking code generation, a new task designed to evaluate the progressive reasoning and problem-solving capabilities of LLMs. In this task, models are presented with a base problem and a related, more complex problem. They…

The rise of Large Language Models (LLMs) as coding agents promises to accelerate software development, but their impact on generated code reproducibility remains largely unexplored. This paper presents an empirical study investigating…

Augmenting Large Language Models (LLMs) with external tools enables them to execute complex, multi-step tasks. However, tool learning is hampered by the static synthetic data pipelines where data generation and model training are executed…

Since the release of OpenAI's ChatGPT, generative language models have attracted extensive public attention. The increased usage has highlighted generative models' broad utility, but also revealed several forms of embedded bias. Some is…

The automated generation of agentic workflows is a promising frontier for enabling large language models (LLMs) to solve complex tasks. However, our investigation reveals that the robustness of agentic workflow remains a critical,…

An increasing number of NLP applications interact with large language models (LLMs) through black-box APIs, making prompt engineering critical for controlling model outputs. While recent Automatic Prompt Optimization (APO) methods…

Reinforcement learning with verifiable rewards (RLVR) has advanced the reasoning capabilities of large language models. However, existing methods rely solely on outcome rewards, without explicitly optimizing verification or leveraging…

The shift toward interacting with frozen, "black-box" Large Language Models (LLMs) has transformed prompt engineering from a heuristic exercise into a critical optimization challenge. We propose a Reinforcement Learning (RL) framework for…

High Performance Computing (HPC) systems rely on fixed user-provided estimates of job time limits. These estimates are often inaccurate, resulting in inefficient resource use and the loss of unsaved work if a job times out shortly before…

As a simple technique to accelerate inference of large-scale pre-trained models, early exiting has gained much attention in the NLP community. It allows samples to exit early at internal classifiers without passing through the entire model.…

Reinforcement learning with verifiable rewards (RLVR) enhances the reasoning of large language models (LLMs), but standard RLVR often depends on human-annotated answers or carefully curated reward specifications. In machine-checkable…

Recommender systems continually retrain on user reactions to their own predictions, creating AI feedback loops that amplify biases and diminish fairness over time. Despite this well-known risk, most bias mitigation techniques are tested…

Collaborative Qualitative Analysis (CQA) can enhance qualitative analysis rigor and depth by incorporating varied viewpoints. Nevertheless, ensuring a rigorous CQA procedure itself can be both demanding and costly. To lower this bar, we…

White-box test generator tools rely only on the code under test to select test inputs, and capture the implementation's output as assertions. If there is a fault in the implementation, it could get encoded in the generated tests. Tool…

Verifiers can improve language model capabilities by scoring and ranking responses from generated candidates. Currently, high-quality verifiers are either unscalable (e.g., humans) or limited in utility (e.g., tools like Lean). While LM…

AI-generated clinical notes are increasingly used in healthcare, but evaluating their quality remains a challenge due to high subjectivity and limited scalability of expert review. Existing automated metrics often fail to align with…

AI deployment in sensitive domains such as health care, credit, employment, and criminal justice is often treated as unsafe to authorize until model internals can be explained. This often leads to an excessive reliance on mechanistic…

With the growing adoption of Large Language Models (LLMs) in automating complex, multi-agent workflows, organizations face mounting risks from errors, emergent behaviors, and systemic failures that current evaluation methods fail to…

The rapid evolution to autonomous, agentic AI systems introduces significant risks due to their inherent unpredictability and emergent behaviors; this also renders traditional verification methods inadequate and necessitates a shift towards…

Online learning methods, like the seminal Passive-Aggressive (PA) classifier, are still highly effective for high-dimensional streaming data, out-of-core processing, and other throughput-sensitive applications. Many such algorithms rely on…