The paper introduces Portable Agent Memory, an open protocol designed to allow persistent, cryptographically-verified memory state to be reliably transferred between diverse and heterogeneous AI agent…

The paper introduces ClawCoin, a novel tokenized, compute-cost-indexed unit of account designed to solve the problem of non-transferable compute costs in decentralized AI agent economies.

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…

This paper systematically studies memory poisoning attacks in LLM agents, identifying multiple vulnerabilities and proposing a new benchmark to assess the risk.

This paper introduces the Always-On Evaluation Protocol (AOEP-v0) for evaluating always-on agents by focusing on state mutation and recovery obligations.

The paper introduces memorywire, a vendor-neutral JSON-Schema wire format and reference implementation designed to standardize and govern memory operations across disparate agent-memory frameworks.

This paper introduces Active Task Driving Memory (ATMem), an actively maintained execution state for mobile GUI agents, and STR-GRPO, an online reinforcement learning method that uses ATMem selectivel…

Proposed MemSyco-Bench benchmark for evaluating memory-induced sycophancy in agent systems, measuring when and how valid memories should be used.

The paper introduces memorywire, a vendor-neutral JSON-Schema 2020-12 wire format and reference implementation to standardize and govern agent memory operations across diverse, proprietary agent-memor…

MemLineage introduces a novel, cryptographically-backed defense mechanism that enforces a chain-of-custody for LLM agent memory, preventing untrusted or poisoned state from justifying sensitive action…

The paper introduces KTD-Fin, a novel benchmark that evaluates LLM trading agents by masking historical market data and decomposing returns, finding that LLM agents' profits are largely due to passive…

This paper analyzes memory poisoning attacks targeting multi-agent systems (MAS) powered by LLMs, proposing mitigation strategies across various memory types, especially focusing on secure design prin…

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…

The paper systematizes the interaction between autonomous AI agents and blockchain platforms using a bidirectional trust framework, identifying significant gaps in current standards and proposing a ta…

The paper introduces Trojan Hippo, a persistent memory attack that exfiltrates sensitive data from LLM agents by planting dormant payloads into long-term memory, and develops a comprehensive framework…

This paper proposes an organizational memory for LLM-based agents to access and share enterprise-specific procedural knowledge for reliable business process execution.

MemMark introduces a state-evolution attribution watermark that embeds owner-controlled signals into latent memory-write decisions, enabling robust provenance tracking for agent memory even when all t…

This survey analyzes the unique security threats posed by complex, multi-agent AI systems and proposes Confidential Computing (CC) using Trusted Execution Environments (TEEs) as a hardware-rooted defe…

MemMorph introduces a novel memory poisoning attack that biases LLM agent tool selection by injecting crafted records into the agent's long-term memory, achieving high success rates even against moder…