Related papers: Exploring Weaknesses in Function Call Models via R…

Large language model (LLM) agents are constrained by limited context windows, necessitating external memory systems for long-term information understanding. Current memory-augmented agents typically depend on pre-defined instructions and…

Data selection for finetuning Large Language Models (LLMs) can be framed as a budget-constrained optimization problem: maximizing a model's downstream performance under a strict training data budget. Solving this problem is generally…

Using large language models (LMs) for query or document expansion can improve generalization in information retrieval. However, it is unknown whether these techniques are universally beneficial or only effective in specific settings, such…

Reinforcement learning (RL) has demonstrated strong potential in training large language models (LLMs) capable of complex reasoning for real-world problem solving. More recently, RL has been leveraged to create sophisticated LLM-based…

Reinforcement Learning (RL) is an effective tool for controller design but can struggle with issues of robustness, failing catastrophically when the underlying system dynamics are perturbed. The Robust RL formulation tackles this by adding…

Large language models (LLMs) are incredible and versatile tools for text-based tasks that have enabled countless, previously unimaginable, applications. Retrieval models, in contrast, have not yet seen such capable general-purpose models…

The development of LLMs has greatly enhanced the intelligence and fluency of question answering, while the emergence of retrieval enhancement has enabled models to better utilize external information. However, the presence of noise and…

Efficiently acquiring external knowledge and up-to-date information is essential for effective reasoning and text generation in large language models (LLMs). Prompting advanced LLMs with reasoning capabilities to use search engines during…

Interactive digital agents (IDAs) leverage APIs of stateful digital environments to perform tasks in response to user requests. While IDAs powered by instruction-tuned large language models (LLMs) can react to feedback from interface…

While reinforcement learning (RL) has achieved notable success in various domains, training effective policies for complex tasks remains challenging. Agents often converge to local optima and fail to maximize long-term rewards. Existing…

While large language models (LLMs) have advanced the development of general-purpose agents, achieving robust generalization to unseen tasks remains a significant challenge. Current approaches typically rely on either fine-tuning or…

E-commerce platforms and payment solution providers face increasingly sophisticated fraud schemes, ranging from identity theft and account takeovers to complex money laundering operations that exploit the speed and anonymity of digital…

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…

Low-Altitude Economic Networking (LAENet) aims to support diverse flying applications below 1,000 meters by deploying various aerial vehicles for flexible and cost-effective aerial networking. However, complex decision-making, resource…

Adversarial attacking aims to fool deep neural networks with adversarial examples. In the field of natural language processing, various textual adversarial attack models have been proposed, varying in the accessibility to the victim model.…

Language model (LM) agents have gained significant attention for their ability to autonomously complete tasks through interactions with environments, tools, and APIs. LM agents are primarily built with prompt engineering or supervised…

Large Language Models (LLMs) offer a promising basis for creating agents that can tackle complex tasks through iterative environmental interaction. Existing methods either require these agents to mimic expert-provided trajectories or rely…

Reinforcement Learning (RL) methods have emerged as a popular choice for training an efficient and effective dialogue policy. However, these methods suffer from sparse and unstable reward signals returned by a user simulator only when a…

With the increasing power of computers and the rapid development of self-learning methodologies such as machine learning and artificial intelligence, the problem of constructing an automatic Financial Trading Systems (FTFs) becomes an…

Large language models (LLMs) trained via pretraining and supervised fine-tuning (SFT) can still produce harmful and misaligned outputs, or struggle in domains like math and coding. Reinforcement learning (RL)-based post-training methods,…