arXiv:2606. 22030v2 Announce Type: replace Abstract: We investigate when belief-based memory actually improves large language model (LLM) agents.
By Pranav Singh
The paper introduces the Distributed‑Evidence Paradox, where long‑running LLM agents compress past interactions into persistent memories that may not be fully supported by the interaction history. It defines three key requirements—evidence scope, compositional validity, and admission reliability—and proposes DerivAudit, a framework that checks whether a memory is truly supported by the available history. Experiments on two memory corpora show that expanding the evidence base can recover support for many memories, yet many remain unsupported, and broader evidence alone does not guarantee reliable admission.
By Hongjun Liu, Chen Zhao
arXiv:2608.21230v1 Announce Type: cross
Abstract: Persistent memory makes false information durable: once a false statement is stored, it can be retrieved into future sessions that match it. We measu...
By Arulnidhi Karunanidhi
arXiv:2608. 19701v1 Announce Type: new Abstract: Long-term multi-agent systems continuously accumulate the memories produced by different agents.
By Chenchen Lin, Wenhao Yuan, Xuehe Wang, Edith Cheuk Han Ngai
The paper introduces Audience‑Bound Persistent Memory, a system that tracks the audience of each memory item and enforces authorization throughout the memory lifecycle. Each item carries the audience present at recording, and derived items are partitioned or suppressed based on the intersection of source audiences, expanding only through explicit grants. The authors implement the approach in two reference architectures—a flat store and a relationship graph—and evaluate it on 10,000 multi‑party histories, showing that no forbidden items entered any context while unscoped retrieval exposed forbidden items in 82% of cases, and that entitled recall matched policy‑equivalent baselines and outperformed unscoped retrieval by 0.30 Recall@5.
By Sibo Liu
The paper introduces ClaimReceipt, a specification and verifier that checks whether a claim in an agent evaluation can be recomputed from retained evidence (sufficiency) and whether the evidence covers the entire experiment set (coverage). Using the CR‑2 verifier on 1,392 historical records, the authors demonstrate accurate reproduction of audit verdicts, non‑redundant field groups, and zero false positives on semantic faults. In a prospective CR‑3 run, the system correctly flags missing receipts and preserves coverage when private evidence is withheld, while adding minimal overhead to inference time and transaction size.
By Peiying Zhu, Sidi Chang