AgingBench demonstrates multi-dimensional degradation in deployed AI agents through four aging mechanisms diagnosed by temporal graphs and counterfactual probes across hundreds of runs.
From Lossy to Verified: A Provenance-Aware Tiered Memory for Agents.arXiv preprint arXiv:2602.17913
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
years
2026 5representative citing papers
MemMark enables snapshot-only attribution for agent long-term memory by embedding signals via keyed distribution-preserving sampling at memory-write decisions, recovering 40-bit payloads with near-baseline utility.
MemoRepair formalizes the cascade update problem in agentic memory and solves it via a min-cut reduction that eliminates invalidated memory exposure to 0% while recovering 91-94% of valid successors at 57-76% of baseline repair cost.
EMBER learns to retain budgeted, source-backed evidence capsules so long-horizon agents recover answer-relevant facts without rereading the full history.
TrustMem introduces a verifier for memory update transitions and preference-guided RL to cut omission, corruption, and hallucination rates in LLM agent memory while reaching SOTA on MemoryAgentBench and HaluMem.
citing papers explorer
-
Your Agents Are Aging Too: Agent Lifespan Engineering for Deployed Systems
AgingBench demonstrates multi-dimensional degradation in deployed AI agents through four aging mechanisms diagnosed by temporal graphs and counterfactual probes across hundreds of runs.
-
MemMark: State-Evolution Attribution Watermarking for Agent Long-Term Memory Systems
MemMark enables snapshot-only attribution for agent long-term memory by embedding signals via keyed distribution-preserving sampling at memory-write decisions, recovering 40-bit payloads with near-baseline utility.
-
MEMOREPAIR: Barrier-First Cascade Repair in Agentic Memory
MemoRepair formalizes the cascade update problem in agentic memory and solves it via a min-cut reduction that eliminates invalidated memory exposure to 0% while recovering 91-94% of valid successors at 57-76% of baseline repair cost.
-
EMBER: Efficient Memory via Budgeted Evidence Retention for Long-Horizon Agents
EMBER learns to retain budgeted, source-backed evidence capsules so long-horizon agents recover answer-relevant facts without rereading the full history.
-
TRUSTMEM: Learning Trustworthy Memory Consolidation for LLM Agents with Long-Term Memory
TrustMem introduces a verifier for memory update transitions and preference-guided RL to cut omission, corruption, and hallucination rates in LLM agent memory while reaching SOTA on MemoryAgentBench and HaluMem.