Related papers: MemMA: Coordinating the Memory Cycle through Multi…

The evolution of Large Language Model (LLM) agents towards System~2 reasoning, characterized by deliberative, high-precision problem-solving, requires maintaining rigorous logical integrity over extended horizons. However, prevalent memory…

Web agents powered by Large Language Models (LLMs) have demonstrated remarkable abilities in planning and executing multi-step interactions within complex web-based environments, fulfilling a wide range of web navigation tasks. Despite…

Large language models (LLMs) excel at many NLP tasks but struggle to sustain long-term interactions due to limited attention over extended dialogue histories. Retrieval-augmented generation (RAG) mitigates this issue but lacks reliable…

Large language models (LLMs) excel at single-turn reasoning but often lose accuracy and coherence over extended, multi-turn interactions. Recent evaluations such as TurnBench highlight recurring failure modes-reasoning bias, task drift,…

Large Language Models (LLMs) have made significant progress in open-ended dialogue, yet their inability to retain and retrieve relevant information from long-term interactions limits their effectiveness in applications requiring sustained…

Large language models (LLMs) have recently emerged as promising tools for solving challenging robotic tasks, even in the presence of action and observation uncertainties. Recent LLM-based decision-making methods (also referred to as…

Existing memory-augmented LLM agents often treat memory as a static repository with pre-defined representations and fixed retrieval pipelines, which is brittle in dynamic agentic environments where feedback, task variation, and…

Effectively processing long contexts remains a fundamental yet unsolved challenge for large language models (LLMs). Existing single-LLM-based methods primarily reduce the context window or optimize the attention mechanism, but they often…

Long-term memory is a critical capability for multimodal large language model (MLLM) agents, particularly in conversational settings where information accumulates and evolves over time. However, existing benchmarks either evaluate…

While Large Language Models (LLMs) have demonstrated potential in healthcare, they often struggle with the complex, non-linear reasoning required for accurate clinical diagnosis. Existing methods typically rely on static, linear mappings…

Recent works on context and memory benchmarking have primarily focused on conversational instances but the need for evaluating memory in dynamic enterprise environments is crucial for its effective application. We introduce MEMTRACK, a…

Large language model (LLM) agents increasingly rely on external memory systems to remain consistent across long-horizon interactions, but little empirical work has been done to understand the specific failure modes and design choices that…

Long-term conversational agents must decide which turns to store in external memory, yet recent systems rely on autoregressive LLM generation at every turn to make that decision. We present MemRouter, a write-side memory router that…

With the explosive growth of data, long-sequence modeling has become increasingly important in tasks such as natural language processing and bioinformatics. However, existing methods face inherent trade-offs between efficiency and memory.…

Reinforcement learning (RL) agents often suffer from high sample complexity in sparse or delayed reward settings due to limited prior structure. Large language models (LLMs) can provide subgoal decompositions, plausible trajectories, and…

Large Language Model-based agents(LLM-based agents) are increasingly deployed in customer service, yet they often forget across sessions, repeat errors, and lack mechanisms for continual self-improvement. This makes them unreliable in…

Memory is a fundamental component for enabling long-context LLM agents, supporting persistent state across interactions through a continuous serve-and-update lifecycle. Despite substantial prior work, existing systems suffer from…

Existing Multimodal Large Language Model (MLLM)-based agents face significant challenges in handling complex GUI (Graphical User Interface) interactions on devices. These challenges arise from the dynamic and structured nature of GUI…

Multi-agent reinforcement learning (MARL) extends (single-agent) reinforcement learning (RL) by introducing additional agents and (potentially) partial observability of the environment. Consequently, algorithms for solving MARL problems…

Recent advances in persona-centric memory have revealed the powerful capability of multi-agent systems in managing persona memory, especially in conversational scenarios. However, these complex frameworks often suffer from information loss…