Related papers: FLEX: Continuous Agent Evolution via Forward Learn…

Artificial intelligence progresses towards the "Era of Experience," where agents are expected to learn from continuous, grounded interaction. We argue that traditional Reinforcement Learning (RL), which typically represents value as a…

Large Language Models (LLMs) and LLM-based agents show great promise in accelerating scientific research. Existing benchmarks for measuring this potential and guiding future development continue to evolve from pure recall and rote knowledge…

Learning from experience is critical for building capable large language model (LLM) agents, yet prevailing self-evolving paradigms remain inefficient: agents learn in isolation, repeatedly rediscover similar behaviors from limited…

Evolution, the engine behind the survival and growth of life on Earth, operates through the population-based process of reproduction. Inspired by this principle, this paper formally defines a newly emerging problem -- the population-based…

Training large language model (LLM) agents to acquire necessary skills and perform diverse tasks within an environment is gaining interest as a means to enable open-endedness. However, creating the training dataset for their skill…

Autonomous agents powered by large language models (LLMs) have attracted significant research interest. However, the open-source community faces many challenges in developing specialized models for agent tasks, driven by the scarcity of…

Large language models (LLMs) are revolutionizing education, with LLM-based agents playing a key role in simulating student behavior. A major challenge in student simulation is modeling the diverse learning patterns of students at various…

We present Agent Lightning, a flexible and extensible framework that enables Reinforcement Learning (RL)-based training of Large Language Models (LLMs) for any AI agent. Unlike existing methods that tightly couple RL training with agent or…

LLM-based (Large Language Model) GUI (Graphical User Interface) agents can potentially reshape our daily lives significantly. However, current LLM-based GUI agents suffer from the scarcity of high-quality training data owing to the…

Associative learning--forming links between co-occurring items--is fundamental to human cognition, reshaping internal representations in complex ways. Testing hypotheses on how representational changes occur in biological systems is…

Humans generally acquire new skills without compromising the old; however, the opposite holds for Large Language Models (LLMs), e.g., from LLaMA to CodeLLaMA. To this end, we propose a new post-pretraining method for LLMs with an expansion…

Large Language Models (LLMs) have emerged as powerful tools for accelerating scientific discovery, yet their static knowledge and hallucination issues hinder autonomous research applications. Recent advances integrate LLMs into agentic…

Recent research looks to harness the general knowledge and reasoning of large language models (LLMs) into agents that accomplish user-specified goals in interactive environments. Vision-language models (VLMs) extend LLMs to multi-modal data…

This paper surveys the development of large language model (LLM)-based agents for question answering (QA). Traditional agents face significant limitations, including substantial data requirements and difficulty in generalizing to new…

We introduce a novel reinforcement learning framework of LLM agents named AGILE (AGent that Interacts and Learns from Environments) designed to perform complex conversational tasks with users, leveraging LLMs, memory, tools, and…

Large language models (LLMs) have recently gained much attention in building autonomous agents. However, the performance of current LLM-based web agents in long-horizon tasks is far from optimal, often yielding errors such as repeatedly…

The growing disparity between the exponential scaling of computational resources and the finite growth of high-quality text data now constrains conventional scaling approaches for large language models (LLMs). To address this challenge, we…

We design a large-language-model (LLM) agent system that extracts causal feedback fuzzy cognitive maps (FCMs) from raw text. The causal learning or extraction process is agentic both because of the LLM's semi-autonomy and because ultimately…

Designing proteins de novo with tailored structural, physicochemical, and functional properties remains a grand challenge in biotechnology, medicine, and materials science, due to the vastness of sequence space and the complex coupling…

Learning to manipulate objects efficiently, particularly those involving sustained contact (e.g., pushing, sliding) and articulated parts (e.g., drawers, doors), presents significant challenges. Traditional methods, such as robot-centric…