Related papers: Sample-Efficient Online Learning in LM Agents via …

Memory capacity is a critical factor determining the performance of Vision-Language-Action (VLA) models in long-horizon manipulation tasks. Existing memory-augmented architectures primarily rely on linear or flat storage, lacking structural…

Static "human data" faces inherent limitations: it is expensive to scale and bounded by the knowledge of its creators. Continuous learning from "experience data" - interactions between agents and their environments - promises to transcend…

Critique-guided reinforcement learning (RL) has emerged as a powerful paradigm for training LLM agents by augmenting sparse outcome rewards with natural-language feedback. However, current methods often rely on static or offline critic…

Hindsight Experience Replay (HER) is a technique used in reinforcement learning (RL) that has proven to be very efficient for training off-policy RL-based agents to solve goal-based robotic manipulation tasks using sparse rewards. Even…

Research on large language models (LLMs) has shown remarkable performance in domains such as mathematics, programming, and literary creation. However, most studies have focused on semantic memory-based question answering, neglecting LLMs'…

Natural language instruction following is paramount to enable collaboration between artificial agents and human beings. Natural language-conditioned reinforcement learning (RL) agents have shown how natural languages' properties, such as…

Recent progress on large language models (LLMs) has enabled dialogue agents to generate highly naturalistic and plausible text. However, current LLM language generation focuses on responding accurately to questions and requests with a…

Reinforcement learning methods have been used to compute dialog policies from language-based interaction experiences. Efficiency is of particular importance in dialog policy learning, because of the considerable cost of interacting with…

Error attribution in Large Language Model (LLM) multi-agent systems presents a significant challenge in debugging and improving collaborative AI systems. Current approaches to pinpointing agent and step level failures in interaction traces…

Agent memory has been touted as a dimension of growth for LLM-based applications, enabling agents that can accumulate experience, adapt across sessions, and move beyond single-shot question answering. The current generation of agent memory…

Standard reinforcement learning (RL) for large language model (LLM) agents typically optimizes extrinsic rewards, prioritizing isolated task completion over continual adaptation. Consequently, agents often converge to suboptimal policies…

The past years have seen Large Language Models (LLMs) strive not only as generative models but also as agents solving textual sequential decision-making tasks. When facing complex environments where their zero-shot abilities are…

Large Language Models (LLMs) have demonstrated remarkable performance across a wide range of reasoning tasks. Recent methods have further improved LLM performance in complex mathematical reasoning. However, when extending these methods…

Large language models (LLMs) have been increasingly used to interact with external environments (e.g., games, compilers, APIs) as goal-driven agents. However, it remains challenging for these language agents to quickly and efficiently learn…

The popularity of Large Language Models (LLMs) have unleashed a new age ofLanguage Agents for solving a diverse range of tasks. While contemporary frontier LLMs are capable enough to power reasonably good Language agents, the closed-API…

Large Language Models (LLMs) have become integral components in various autonomous agent systems. In this study, we present an exploration-based trajectory optimization approach, referred to as ETO. This learning method is designed to…

Test-time reinforcement learning generates multiple candidate answers via repeated rollouts and performs online updates using pseudo-labels constructed by majority voting. To reduce overhead and improve exploration, prior work introduces…

CLI agents are the closest thing language models have to an embodied setting: the model emits commands, the terminal executes them, and the returned stream -- stdout, errors, files, logs, and traces -- records the consequences. We argue…

Large Language Models have demonstrated profound utility in the medical domain. However, their application to autonomous Electronic Health Records~(EHRs) navigation remains constrained by a reliance on curated inputs and simplified…

Bidirectional models are considered essential for strong text embeddings. Recent approaches to adapt autoregressive language models (LMs) into strong text embedding models have largely had the requirement to modify the LM architecture to be…