The paper introduces Metacognitive Memory Policy Optimization (MMPO), a novel memory training approach that optimizes LLM memory not based on final task success, but on minimizing epistemic uncertaint…

The paper introduces 'layered mutability,' a framework for analyzing how persistent self-modifying AI agents drift away from intended behavior due to the accumulation of locally reasonable, uncoordina…

ExpGraph is a model-agnostic framework that uses a self-evolving experience graph to enable LLM agents to reuse past successful strategies and failure lessons, significantly improving performance acro…

The paper introduces MemCog, a Memory-as-Cognition system that integrates memory access directly into the reasoning process, significantly improving agent performance, especially in proactive memory r…

The paper proposes SCALE, a self-improving web agent framework that uses adversarial roles and graph exploration to autonomously discover agent limitations and enhance adaptability in complex web envi…

The paper introduces AGENTCL, a rigorous evaluation framework that uses controlled task streams to accurately measure an agent's ability to accumulate and reuse knowledge across multiple tasks, thereb…

The paper introduces Momento, a new benchmark that evaluates agentic AI's ability to maintain state and reason across multiple, disconnected sessions, revealing that current agents struggle with integ…

This survey establishes persistent, writable memory as an independent security problem for LLM agents, proposing a comprehensive framework for 'mnemonic sovereignty' to govern the entire memory lifecy…

The paper proposes MERIT, a dual-level, multi-horizon memory retrieval framework that significantly improves the performance of interactive text-to-SQL agents by providing both global and local memory…

MemPro introduces a system-level evolution framework that treats the entire memory construction-retrieval pipeline as an evolvable program, significantly improving long-horizon agent performance over…

MemGuard introduces a type-aware memory framework to prevent heterogeneous memory contamination in long-term memory-augmented LLMs, significantly improving memory reliability and efficiency.

The paper introduces Obsessive Experience Poisoning (OEP), a low-privilege black-box attack that poisons self-evolving LLM agents by generating locally correct but harmful experiences, causing dangero…

The paper proposes SAGE, a novelty-aware gate that efficiently controls memory updates in agentic LLMs by classifying new facts as clearly novel, clearly redundant, or uncertain, thereby significantly…

The paper introduces MineExplorer, a new benchmark in Minecraft, to evaluate the sustained open-world exploration capabilities of MLLM agents, finding that long-horizon coordination remains a signific…

MLEvolve is a novel self-evolving multi-agent framework that enables LLM agents to discover and optimize machine learning algorithms for complex, long-horizon tasks.

ElasticMem introduces a novel framework that treats memory as an elastic latent resource, allowing LLM agents to adaptively manage and inject variable-budget memories for improved performance in long-…

The paper introduces Unified Context Evolution (UCE), a gradient-free framework that externalizes and manages agent experience into a typed, evolving library, significantly improving performance on mu…

This paper introduces ATLAS, an active learning framework for discovering interpretable behavioral models in cognitive science.

The paper introduces Adaptive Context Management (AdaCoM), an external context manager that uses reinforcement learning to improve the performance of frozen LLM agents on long-horizon tasks by intelli…

The paper proposes FluxMem, a novel connectivity-evolving memory framework that models memory as a dynamic graph to improve LLM agent performance in complex, changing environments.