# When Stale Constraints Go Unchecked: Budgeted Verification Failures in Inherited Agent Memory arXiv: https://arxiv.org/abs/2608.25553 ยท HTML: https://mlsanity.com/paper/2608.25553/ ## Key facts - Cited by 3 papers in the map (data through 14 Oct 2026). - Placed in Agent memory systems, one of 16 directions in LLM agents and tool use. - Builds on 28 of its 57 references that are in the map. - First posted on arXiv 26 Aug 2026. ## Placed in - LLM agents and tool use / [Agent memory systems](https://mlsanity.com/agents/agent-memory-systems/) ## Builds on (most cited first, 28 of 28) - [Generative Agents: Interactive Simulacra of Human Behavior](https://mlsanity.com/paper/2304.03442/) (2023) - [LongMemEval: Benchmarking Chat Assistants on Long-Term Interactive Memory](https://mlsanity.com/paper/2410.10813/) (2024) - [Active Retrieval Augmented Generation](https://mlsanity.com/paper/2305.06983/) (2023) - [Zep: A Temporal Knowledge Graph Architecture for Agent Memory](https://mlsanity.com/paper/2501.13956/) (2025) - [Adaptive Chameleon or Stubborn Sloth: Revealing the Behavior of Large Language Models in Knowledge Conflicts](https://mlsanity.com/paper/2305.13300/) (2023) - [Evaluating Memory in LLM Agents via Incremental Multi-Turn Interactions](https://mlsanity.com/paper/2507.05257/) (2025) - [STALE: Can LLM Agents Know When Their Memories Are No Longer Valid?](https://mlsanity.com/paper/2605.06527/) (2026) - [From Agent Traces to Trust: A Survey of Evidence Tracing and Execution Provenance in LLM Agents](https://mlsanity.com/paper/2606.04990/) (2026) - [From Recall to Forgetting: Benchmarking Long-Term Memory for Personalized Agents](https://mlsanity.com/paper/2604.20006/) (2026) - [From Untrusted Input to Trusted Memory: A Systematic Study of Memory Poisoning Attacks in LLM Agents](https://mlsanity.com/paper/2606.04329/) (2026) - [Supersede: Diagnosing and Training the Memory-Update Gap in LLM Agents](https://mlsanity.com/paper/2606.27472/) (2026) - [Securing LLM-Agent Long-Term Memory Against Poisoning: Non-Malleable, Origin-Bound Authority with Machine-Checked Guarantees](https://mlsanity.com/paper/2606.24322/) (2026) - [From Lossy to Verified: A Provenance-Aware Tiered Memory for Agents](https://mlsanity.com/paper/2602.17913/) (2026) - [Temporal Validity in Retrieval Memory: Eliminating Stale-Fact Errors for AI Agents over Evolving Knowledge](https://mlsanity.com/paper/2606.26511/) (2026) - [Inference-Time Budget Control for LLM Search Agents](https://mlsanity.com/paper/2605.05701/) (2026) - [Auditing Provenance Sensitivity in LLM Agent Action Selection](https://mlsanity.com/paper/2607.20827/) (2026) - [Failing to Falsify: Evaluating and Mitigating Confirmation Bias in Language Models](https://mlsanity.com/paper/2604.02485/) (2026) - [Reliable Post-Retrieval Assembly for Agent Memory: Separating Evidence Extraction from Policy Execution](https://mlsanity.com/paper/2606.01435/) (2026) - [Governance Decay: How Context Compaction Silently Erases Safety Constraints in Long-Horizon LLM Agents](https://mlsanity.com/paper/2606.22528/) (2026) - [When Memory Becomes Authority: Benchmarking Authority Collapse at the Memory Consolidation Boundary](https://mlsanity.com/paper/2608.01679/) (2026) - [Verify Before You Commit: Towards Faithful Reasoning in LLM Agents via Self-Auditing](https://mlsanity.com/paper/2604.08401/) (2026) - [When Does Belief-Based Agent Memory Help? Reliability-Conditional Updating and Provenance-Capped Poisoning Defense](https://mlsanity.com/paper/2606.22030/) (2026) - [Omission Constraints Decay While Commission Constraints Persist in Long-Context LLM Agents](https://mlsanity.com/paper/2604.20911/) (2026) - [TEPA: Revoking Stale Memories for Conflict-Robust Language Agents](https://mlsanity.com/paper/2608.07429/) (2026) - [Selection Integrity for LLM Graph Memory: An Accumulability Criterion for Information-Flow-Blind Retrieval](https://mlsanity.com/paper/2606.12290/) (2026) - [AllocBench: Measuring Online Tool Allocation Capability in LLM Agents](https://mlsanity.com/paper/2607.23332/) (2026) - [Belief-Guided Inference Control for Large Language Model Services via Verifiable Observations](https://mlsanity.com/paper/2604.27536/) (2026) - [Heteroskedastic Signals in Budgeted LLM Verification: Structural Heterogeneity Limits Optimization Gains](https://mlsanity.com/paper/2606.15841/) (2026) ## Built on by (most cited first, 3 of 3) - [What It Costs to Compose, Rebuild, and Correct Precomputed Memory](https://mlsanity.com/paper/2608.30647/) (2026) - [A Benchmark and Diagnostic Study of Epistemic Admission in Shared Agent Memory](https://mlsanity.com/paper/2609.30813/) (2026) - [Plan Pointers and Record-Directive Form in Budgeted Verification of Inherited Agent Memory](https://mlsanity.com/paper/2609.03450/) (2026) ## Abstract (arXiv) Provenance links keep the evidence behind an inherited belief reachable; an agent with a verification budget must still choose which links to inspect. We study a consolidated memory that states a decision constraint and whose source record has since been superseded by a record that withdraws it: provenance is immutable, the current record has changed, and the memory is stale. In a controlled six-memory scenario with a budget of two records, sixteen language models rarely re-verified a constraint that read as settled: they inspected its provenance path in about one episode in five and, once the constraint had been superseded, produced stale-consistent decisions in 77.3%, 74.7% and 74.7% of episodes across a primary run, a replication and a held-out domain. Re-assigning one of the same two slots to the critical path removed most of them: +74.0, +72.7 and +61.3 points (positive in every model), +80.7 in a prospectively frozen interleaved replication with a repaired non-critical control, and +62.0 on a panel of 10 models from 9 organisations; a corrected re-run of the held-out scenario gave +73.3. The forced-critical policy uses experimenter knowledge of the critical path: it quantifies how much stale-decision risk the same budget can recover and is not a scheduler. Two further deposited experiments locate the failure and a remedy: in this store the constraint's path is selected in 17.0% of episodes at two slots and 88.7% at four of six (above uniform allocation), and at two slots a one-sentence, target-blind rule (prefer memories that state a limit on a candidate direction) moved the agent's own allocation onto the constraint's path and recovered the oracle contrast on decisions (+89.3 points) where that constraint limits the tempting action, while a content-free freshness cue did not materially redirect allocation and a content-matched control rule changed neither selection nor decisions.