Related papers: ReasoningBank: Scaling Agent Self-Evolving with Re…

Existing evaluations of agents with memory typically assess memorization and action in isolation. One class of benchmarks evaluates memorization by testing recall of past conversations or text but fails to capture how memory is used to…

Conversational agents powered by large language models (LLMs) with tool integration achieve strong performance on fixed task-oriented dialogue datasets but remain vulnerable to unanticipated, user-induced errors. Rather than focusing on…

Large Language Model (LLM)-based agents have fundamentally reshaped artificial intelligence by integrating external tools and planning capabilities. While memory mechanisms have emerged as the architectural cornerstone of these systems,…

This paper introduces RAISE (Reasoning and Acting through Scratchpad and Examples), an advanced architecture enhancing the integration of Large Language Models (LLMs) like GPT-4 into conversational agents. RAISE, an enhancement of the ReAct…

Building LLM-based agents has become increasingly important. Recent works on LLM-based agent self-evolution primarily record successful experiences as textual prompts or reflections, which cannot reliably guarantee efficient task…

User simulators serve as the critical interactive environment for agent post-training, and an ideal user simulator generalizes across domains and proactively engages in negotiation by challenging or bargaining. However, current methods…

We introduce \emph{Memento-Skills}, a generalist, continually-learnable LLM agent system that functions as an \emph{agent-designing agent}: it autonomously constructs, adapts, and improves task-specific agents through experience. The system…

Memory emerges as the core module in the Large Language Model (LLM)-based agents for long-horizon complex tasks (e.g., multi-turn dialogue, game playing, scientific discovery), where memory can enable knowledge accumulation, iterative…

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…

Large Language Models (LLMs) have demonstrated impressive capabilities across a wide range of NLP tasks, but they remain fundamentally stateless, constrained by limited context windows that hinder long-horizon reasoning. Recent efforts to…

Large language models (LLMs) have transformed AI research thanks to their powerful internal capabilities and knowledge. However, existing LLMs still fail to effectively incorporate the massive external knowledge when interacting with the…

AI agent frameworks operate in isolation, forcing agents to rediscover solutions and repeat mistakes across different systems. Despite valuable problem-solving experiences accumulated by frameworks like smolagents, OpenHands, and OWL, this…

Recent works have highlighted the significance of memory mechanisms in LLM-based agents, which enable them to store observed information and adapt to dynamic environments. However, evaluating their memory capabilities still remains…

Modern language agents must operate over long-horizon, multi-turn interactions, where they retrieve external information, adapt to observations, and answer interdependent queries. Yet, most LLM systems rely on full-context prompting,…

As Large Language Models (LLMs) move from curated training sets into open-ended real-world environments, a fundamental limitation emerges: static training cannot keep pace with continual deployment environment change. Scaling training-time…

Memory-augmented LLM agents offer an appealing shortcut to continual learning: rather than updating model parameters, they accumulate experience in external memory, seemingly sidestepping the stability-plasticity dilemma of parametric…

Large Language Models (LLMs) have demonstrated remarkable capabilities across a wide range of language tasks, yet complex multi-step reasoning remains a fundamental challenge. While Large Reasoning Models (LRMs) equipped with extended…

Language model agents excel in long-session planning and reasoning, but existing benchmarks primarily focus on goal-oriented tasks with explicit objectives, neglecting creative adaptation in unfamiliar environments. To address this, we…

Existing memory systems enable Large Language Models (LLMs) to support long-horizon human-LLM interactions by persisting historical interactions beyond limited context windows. However, while recent approaches have succeeded in constructing…

As data continues to grow in scale and complexity, preparing, transforming, and analyzing it remains labor-intensive, repetitive, and difficult to scale. Since data contains knowledge and AI learns knowledge from it, the alignment between…