Related papers: MemGym: a Long-Horizon Memory Environment for LLM …

Recent advancements in large language models (LLMs) underscore the need for more comprehensive evaluation methods to accurately assess their reasoning capabilities. Existing benchmarks are often domain-specific and thus cannot fully capture…

Long-term memory is essential for conversational agents to maintain coherence, track persistent tasks, and provide personalized interactions across extended dialogues. However, existing approaches as Retrieval-Augmented Generation (RAG) and…

Recent advancements in large language models (LLMs) have revealed their potential for achieving autonomous agents possessing human-level intelligence. However, existing benchmarks for evaluating LLM Agents either use static datasets,…

Inspired by the insights in cognitive science with respect to human memory and reasoning mechanism, a novel evolvable LLM-based (Large Language Model) agent framework is proposed as REMEMBERER. By equipping the LLM with a long-term…

Memory Gym presents a suite of 2D partially observable environments, namely Mortar Mayhem, Mystery Path, and Searing Spotlights, designed to benchmark memory capabilities in decision-making agents. These environments, originally with finite…

Maintaining consistency in long-term dialogues remains a fundamental challenge for LLMs, as standard retrieval mechanisms often fail to capture the temporal evolution of historical states. While memory-augmented frameworks offer a…

Long-context Large Language Models, despite their expanded capacity, require careful working memory management to mitigate attention dilution during long-horizon tasks. Yet existing approaches rely on external mechanisms that lack awareness…

As LLM-based agents are increasingly used in long-term interactions, cumulative memory is critical for enabling personalization and maintaining stylistic consistency. However, most existing systems adopt an ``all-or-nothing'' approach to…

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…

Existing memory benchmarks for LLM agents evaluate explicit recall of facts, yet overlook implicit memory where experience becomes automated behavior without conscious retrieval. This gap is critical: effective assistants must automatically…

LLM-powered agents face a persistent challenge: learning from their execution experiences to improve future performance. While agents can successfully complete many tasks, they often repeat inefficient patterns, fail to recover from similar…

Persistent Large Language Model (LLM) agents expose a critical governance gap in memory management. Standard Retrieval-Augmented Generation (RAG) frameworks treat memory as passive storage, lacking mechanisms to resolve contradictions,…

Large language model-based agents operating in long-horizon interactions require memory systems that support temporal consistency, multi-hop reasoning, and evidence-grounded reuse across sessions. Existing approaches largely rely on…

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…

Large Language Model (LLM)-based agents have achieved notable success on short-horizon and highly structured tasks. However, their ability to maintain coherent decision-making over long horizons in realistic and dynamic environments remains…

Real-world agents operate over long and evolving horizons, where information is repeatedly updated and may interfere across memories, requiring accurate recall and aggregated reasoning over multiple pieces of information. However, existing…

Large Language Models (LLMs) have demonstrated emergent common-sense reasoning and Theory of Mind (ToM) capabilities, making them promising candidates for developing coordination agents. This study introduces the LLM-Coordination Benchmark,…

Large language models (LLMs) have demonstrated strong potential in long-horizon decision-making tasks, such as embodied manipulation and web interaction. However, agents frequently struggle with endless trial-and-error loops or deviate from…

The process of creating training data to teach models is currently driven by humans, who manually analyze model weaknesses and plan how to create data that improves a student model. Approaches using LLMs as annotators reduce human effort,…

We present MobileGym, a browser-hosted, lightweight, fully controllable environment for everyday mobile use, targeting interaction fidelity without replicating proprietary backends. It enables two capabilities previously out of reach for…