arXiv AI
Jul 3
Episodic-to-Semantic Consolidation Without Identity Drift
arXiv:2607. 01988v1 Announce Type: new Abstract: Long-running adaptive intelligent agents face a structural tension between knowledge consolidation and information integrity.
Epistemic Memory: A Validity Layer for Self-Maintaining Intelligent Systems
The paper introduces epistemic memory, a validity-maintenance layer for intelligent systems that tracks when stored knowledge remains applicable. It formalizes a dynamic epistemic quotient and shows that fixed semantic representations inevitably incur error as epistemic boundaries shift. The authors propose Observable Belief Memory (OBM), which combines current epistemic quotients, belief over quotient classes, and within-class provenance, and demonstrate that explicit epistemic tracking improves robustness under changing observation conditions.
Related stories
arXiv AI
Jun 16
The Missing Knowledge Layer in Cognitive Architectures for AI Agents
arXiv:2604. 11364v2 Announce Type: replace Abstract: The two most influential cognitive architecture frameworks for AI agents, CoALA [21] and JEPA [12], both lack an explicit Knowledge layer with its own persistence semantics.
arXiv AI
Jul 17
When Does Belief-Based Agent Memory Help? Reliability-Conditional Updating and Provenance-Capped Poisoning Defense
arXiv:2606. 22030v2 Announce Type: replace Abstract: We investigate when belief-based memory actually improves large language model (LLM) agents.
arXiv Computation and Language
5d ago
A State Change Is Local, Its Consequences Are Not: Dependency-Aware State Revision for Long-Term Agent Memory
The paper introduces StateGraph, a system for dependency-aware state revision in long-term agent memory. It constructs an evolving state dependency graph from interaction histories and uses counterfactual verification to determine which dependent states should be invalidated when an upstream fact changes. Evaluation on the new StateChangeBench benchmark shows StateGraph outperforms a CUPMem baseline, suggesting that explicit dependency tracking can improve selective memory revision under changing conditions.
arXiv AI
Oct 21
More Memory, Worse Agents: Error Reproduction and Anti-Persistence in LLM Agents
The paper investigates how large language model (LLM) agents can improve performance by storing and reusing experience in external memory. It identifies a problem called error reproduction, where mistakes in stored abstractions propagate through cycles of abstraction, execution, and re-abstraction, leading to persistent errors. To mitigate this, the authors propose Anti-Persistence, a memory design that retains raw trajectories and outcomes but reconstructs task-specific guidance on demand, discarding it after use. Experiments across multiple benchmarks show that Anti-Persistence yields higher held‑out success rates and lower LLM‑call costs compared to other memory designs, supporting the idea of separating experience accumulation from abstraction persistence.
arXiv AI
Jul 14
Replicating Belief, Not Bits: Epistemic State Replication for Agentic Systems
arXiv:2607. 09748v1 Announce Type: new Abstract: In distributed systems, the classical State Machine Replication (SMR) model assumes that correct replicas execute deterministic transitions to yield identical bitwise states.
arXiv AI
Oct 1
Beyond the Shadows of Plato's Cave: Evaluating False Memory in Autonomous Agents via Counterfactual Reasoning
The paper introduces FAME, a training‑free framework that evaluates false memory in autonomous agents by tracking how their internal beliefs shift under counterfactual scenarios. False memory, defined as biases arising from spurious correlations, environment shifts, or knowledge conflicts, is hard to detect with standard methods. FAME measures concept drift in hidden states, achieving AUROCs between 76.2% and 96.7% and outperforming baselines on benchmarks such as GSM‑Symbolic, GitChameleon, and BigBench‑Hard.
arXiv AI
Sep 1
Useful Memories Become Faulty When Continuously Updated by LLMs
arXiv:2605.12978v2 Announce Type: replace Abstract: Learning from past experience benefits from two complementary forms of memory: episodic traces -- raw trajectories of what happened -- and consolid...
arXiv AI
Oct 23
PreCoMem: Predictive Cognitive Memory for Self-Evolving Long-Term Dialogue Agents
PreCoMem introduces a memory consolidation framework for long‑horizon dialogue agents, inspired by predictive coding. It represents user memory as confidence‑weighted beliefs and uses an Effective Surprisal signal to decide whether to maintain, profile, or correct each belief. Experiments on LoCoMo, LongMemEval‑S, PersonaMem‑v2, and the new DiMoBench demonstrate state‑of‑the‑art accuracy and robust adaptation to non‑stationary belief drift without over‑reacting to noise.
arXiv AI
Sep 30
EquiMem: Calibrating Shared Memory in Multi-Agent Debate via Game-Theoretic Equilibrium
arXiv:2605.09278v2 Announce Type: replace Abstract: Multi-agent debate (MAD) systems increasingly rely on shared memory to support long-horizon reasoning, but this convenience opens a critical vulner...
arXiv AI
Oct 2
Beyond Memory: Harnessing Long-Horizon Agents with Explicit Belief States
Beyond Memory: Harnessing Long-Horizon Agents with Explicit Belief States introduces PoS, an inference-time framework that builds and maintains explicit belief states to guide large language model agents. Each belief state combines an estimate of the current world with unresolved task requirements, making clear what the agent still needs to learn and accomplish. PoS validates consistency, monitors task progress to detect Belief Trapping, and tailors recovery to the trapping pattern and unresolved requirements, achieving top performance across four benchmarks with all three LLM backbones.
arXiv AI
Oct 31
EpiAgent: Epistemic Self-Play for LLM Agents
EpiAgent introduces an explicit, learnable epistemic layer for large language model agents, enabling them to maintain and update beliefs about other agents’ private information. The framework splits the policy into Epistemic Update and Action Planning stages, optimized via a bi‑level Epistemic Self‑Play algorithm that rewards accurate belief predictions. Experiments in mixed and competitive settings show EpiAgent outperforms prompting and RL baselines, highlighting the benefits of dedicated epistemic training for belief inference and action planning.