Related papers: PRIME: Training Free Proactive Reasoning via Itera…
When developing reinforcement learning agents, the standard approach is to train an agent to converge to a fixed policy that is as close to optimal as possible for a single fixed reward function. If different agent behaviour is required in…
A central piece in enabling intelligent agentic behavior in foundation models is to make them capable of introspecting upon their behavior, reasoning, and correcting their mistakes as more computation or interaction is available. Even the…
We study a sequential mechanism design problem in which a principal seeks to elicit truthful reports from multiple rational agents while starting with no prior knowledge of agents' beliefs. We introduce Distributionally Robust Adaptive…
Large language model (LLM) agents are increasingly equipped with memory, which are stored experience and reusable guidance that can improve task-solving performance. Recent \emph{self-evolving} systems update memory based on interaction…
The hallmark of human intelligence is the self-evolving ability to master new skills by learning from past experiences. However, current AI agents struggle to emulate this self-evolution: fine-tuning is computationally expensive and prone…
Customizing robotic behaviors to be aligned with diverse human preferences is an underexplored challenge in the field of embodied AI. In this paper, we present Promptable Behaviors, a novel framework that facilitates efficient…
The humans are affective and cognitive beings relying on memories for their individual and social identities. Also, human dyadic bonds require some common beliefs such as empathetic behaviour for better interaction. In this sense, research…
Messaging patients is a critical part of healthcare communication, helping to improve things like medication adherence and healthy behaviors. However, traditional mobile message design has significant limitations due to its inability to…
Training large transformers using next-token prediction has given rise to groundbreaking advancements in AI. While this generative AI approach has produced impressive results, it heavily leans on human supervision. Even state-of-the-art AI…
We introduce a novel large language model (LLM)-driven agent framework, which iteratively refines queries and filters contextual evidence by leveraging dynamically evolving knowledge. A defining feature of the system is its decoupling of…
Operating LLMs as coordinated multi-agent research systems over multi-hour runs surfaces failure modes that single-shot evaluation cannot: upstream providers throttle without warning, sub-agents drift the task to fit accessible tools,…
Well-designed prompts can guide text-to-image models to generate amazing images. However, the performant prompts are often model-specific and misaligned with user input. Instead of laborious human engineering, we propose prompt adaptation,…
Retrieval-Augmented Generation (RAG) systems for Large Language Models (LLMs) hold promise in knowledge-intensive tasks but face limitations in complex multi-step reasoning. While recent methods have integrated RAG with chain-of-thought…
Recent advancements in agentic test-time scaling allow models to gather environmental feedback before committing to final actions. A key limitation of existing methods is that they typically employ undifferentiated exploration strategies,…
Text-to-image models have shown remarkable progress in generating high-quality images from user-provided prompts. Despite this, the quality of these images varies due to the models' sensitivity to human language nuances. With advancements…
Large-language-model (LLM)-based AI agents have recently showcased impressive versatility by employing dynamic reasoning, an adaptive, multi-step process that coordinates with external tools. This shift from static, single-turn inference to…
This work advances autonomous robot exploration by integrating agent-level semantic reasoning with fast local control. We introduce FARE, a hierarchical autonomous exploration framework that integrates a large language model (LLM) for…
Recent advancements in LLM agents are gradually shifting from reactive, text-based paradigms toward proactive, multimodal interaction. However, existing benchmarks primarily focus on reactive responses, overlooking the complexities of…
The confluence of Artificial Intelligence and Computational Psychology presents an opportunity to model, understand, and interact with complex human psychological states through computational means. This paper presents a comprehensive,…
Large reasoning models (LRMs) such as Claude 3.7 Sonnet and OpenAI o1 achieve strong performance on mathematical benchmarks using lengthy chain-of-thought (CoT) reasoning, but the resulting traces are often unnecessarily verbose. This…