Related papers: Episodic-Semantic Memory Architecture for Long-Hor…

Long-running autonomous AI agents suffer from a well-documented memory coherence problem: tool-execution success rates degrade 14 percentage points over 72-hour operation windows due to four compounding failure modes in existing flat-file…

Semantic caching significantly reduces computational costs and improves efficiency by storing and reusing large language model (LLM) responses. However, existing systems rely primarily on matching individual queries, lacking awareness of…

We present SCM (Sleep-Consolidated Memory), a research preview of a memory architecture for large language models that draws on neuroscientific principles to address a fundamental limitation in current systems: the absence of persistent,…

Multi-agent systems (MAS) built on large language models (LLMs) offer a promising path toward solving complex, real-world tasks that single-agent systems often struggle to manage. While recent advancements in test-time scaling (TTS) have…

Recent advanced LLM-powered agent systems have exhibited their remarkable capabilities in tackling complex, long-horizon tasks. Nevertheless, they still suffer from inherent limitations in resource efficiency, context management, and…

Recent advancements in large language models (LLMs) have greatly improved their capabilities on complex reasoning tasks through Long Chain-of-Thought (CoT). However, this approach often results in substantial redundancy, impairing…

As Large Language Models (LLMs) evolve from static dialogue interfaces to autonomous general agents, effective memory is paramount to ensuring long-term consistency. However, existing benchmarks primarily focus on casual conversation or…

Large Language Model (LLM)-based agents are increasingly deployed for complex, tool-based tasks where long-term memory is critical to driving actions. Existing benchmarks, however, primarily test a angent's ability to passively retrieve…

Current approaches to memory in Large Language Models (LLMs) predominantly rely on static Retrieval-Augmented Generation (RAG), which often results in scattered retrieval and fails to capture the structural dependencies required for complex…

Coding agents accumulate extensive context during long-running tasks, yet fixed context windows force practitioners to choose between truncation and task failure. While numerous memory condensation strategies have been proposed, from simple…

Multimodal Large Language Models (MLLMs) based agents have demonstrated remarkable potential in autonomous web navigation. However, handling long-horizon tasks remains a critical bottleneck. Prevailing strategies often rely heavily on…

Time Series Language Models (TSLMs) promise reasoning over real-world temporal data, but their ability to retrieve and reason over long time-series remains largely untested. We introduce TS-Haystack, a multi-domain retrieval benchmark with…

We propose a novel framework for summarizing structured enterprise data across multiple dimensions using large language model (LLM)-based agents. Traditional table-to-text models often lack the capacity to reason across hierarchical…

Processing long contexts presents a significant challenge for large language models (LLMs). While recent advancements allow LLMs to handle much longer contexts than before (e.g., 32K or 128K tokens), it is computationally expensive and can…

As Large Language Models (LLMs) evolve from text-completion tools into fully fledged agents operating in dynamic environments, they must address the challenge of continually learning and retaining long-term knowledge. Many biological…

Causal discovery through experimentation and intervention is fundamental to robust problem solving. It requires not just updating beliefs within a fixed framework but revising the hypothesis space itself, a capacity current AI agents lack…

Humans intuitively solve complex problems by flexibly shifting among reasoning modes: they plan, execute, revise intermediate goals, resolve ambiguity through associative judgment, and apply formal procedures to well-specified subproblems.…

Multi-agent large language model frameworks are promising for complex multi step reasoning, yet existing systems remain weak for scientific and knowledge intensive domains due to static prompts and agent roles, rigid workflows, and…

Reinforcement learning (RL) has become a pivotal component of large language model (LLM) post-training, and agentic RL extends this paradigm to operate as agents through multi-turn interaction and tool use. Scaling such systems exposes two…

The rise of AI-native Low-Code/No-Code (LCNC) platforms enables autonomous agents capable of executing complex, long-duration business processes. However, a fundamental challenge remains: memory management. As agents operate over extended…