Related papers: Just Enough Shifts: Mitigating Over-Refusal in Ali…

As agentic AI becomes more widespread, agents with distinct and possibly conflicting goals will interact in complex ways. These multi-agent interactions pose a fundamental challenge, particularly in social dilemmas, where agents' individual…

The difficulty and expense of obtaining large-scale human responses make Large Language Models (LLMs) an attractive alternative and a promising proxy for human behavior. However, prior work shows that LLMs often produce homogeneous outputs…

Pretrained language models demonstrate strong performance in most NLP tasks when fine-tuned on small task-specific datasets. Hence, these autoregressive models constitute ideal agents to operate in text-based environments where language…

We consider an improper reinforcement learning setting where a learner is given $M$ base controllers for an unknown Markov decision process, and wishes to combine them optimally to produce a potentially new controller that can outperform…

Safety-aligned language models often refuse cybersecurity requests whose wording resembles misuse, even when the task is authorized and defensive. This makes security evaluation ambiguous: a failed answer may reflect missing capability or…

Action-constrained reinforcement learning (ACRL) is a generic framework for learning control policies with zero action constraint violation, which is required by various safety-critical and resource-constrained applications. The existing…

Large language model agents now act on codebases, browsers, operating systems, calendars, files, and tool ecosystems, but their evaluations often collapse behavior into final task success. AgentAtlas reframes agent evaluation as a…

Language agents have demonstrated autonomous decision-making abilities by reasoning with foundation models. Recently, efforts have been made to train language agents for performance improvement, with multi-step reasoning and action…

Large language models (LLMs) have significantly improved their reasoning and decision-making capabilities, as seen in methods like ReAct. However, despite its effectiveness in tackling complex tasks, ReAct faces two main challenges: losing…

Current safety alignment of foundation models largely follows a \emph{one-size-fits-all} paradigm, applying the same refusal policy across users and contexts. As a result, models may refuse requests that are unsafe for general users but…

A major challenge in autonomous vehicle research is modeling agent behaviors, which has critical applications including constructing realistic and reliable simulations for off-board evaluation and forecasting traffic agents motion for…

Large language models (LLMs) frequently refuse to respond to pseudo-malicious instructions: semantically harmless input queries triggering unnecessary LLM refusals due to conservative safety alignment, significantly impairing user…

In order to be deployed safely, Large Language Models (LLMs) must be capable of dynamically adapting their behavior based on their level of knowledge and uncertainty associated with specific topics. This adaptive behavior, which we refer to…

Large Language Model (LLM) agents are commonly tuned with supervised finetuning on ReAct-style expert trajectories or preference optimization over pairwise rollouts. Most of these methods focus on imitating specific expert behaviors or…

Large language models show promise for financial decision-making, yet deploying them as autonomous trading agents raises fundamental challenges: how to adapt instructions when rewards arrive late and obscured by market noise, how to…

Column Type Annotation (CTA) is a fundamental step towards enabling schema alignment and semantic understanding of tabular data. Existing encoder-only language models achieve high accuracy when fine-tuned on labeled columns, but their…

Language models are aligned to emulate the collective voice of many, resulting in outputs that align with no one in particular. Steering LLMs away from generic output is possible through supervised finetuning or RLHF, but requires…

Adapting Large Language Models (LLMs) to downstream tasks using Reinforcement Learning (RL) has proven to be an effective approach. However, LLMs do not inherently define the structure of an agent for RL training, particularly in terms of…

Recent advancements in large language models (LLMs) have demonstrated that fine-tuning and human alignment can render LLMs harmless. In practice, such "harmlessness" behavior is mainly achieved by training models to reject harmful requests,…

Large Language Models (LLMs) have demonstrated exceptional abilities across a broad range of language-related tasks, including generating solutions to complex reasoning problems. An effective technique to enhance LLM performance is…