TEPA: Revoking Stale Memories for Conflict-Robust Language Agents
Long-term memory enables language agents to reuse past facts, preferences, and task experience. Persistence also creates a central falsifiability problem: when the world changes, stale memories can remain retrievable and pollute the prompt. We characterize this failure mode as memory pollution: degradation caused by active memories that newer conflicting evidence has superseded. We introduce TEPA, a revocable evidence-memory mechanism that makes validity an explicit state of memory. TEPA represe
Record details
Published: 7 August 2026
Source: arXiv cs.AI
Category: Research
Topics: Agents & autonomy
Retrieved: 10 August 2026
Related evidence
These records share source-supplied organisations, an exact publisher byline, automatic topics or regions. The reason is shown on every link; related does not mean supporting, agreeing with or verifying this record.
CoBa: Cost-Effective Test-Time Scaling via Compute-Balanced Routing
arXiv cs.AI · 7 August 2026
Fisher-R1: Training LLM Agents for Reliable Hypothesis Testing
arXiv cs.AI · 7 August 2026
PsychoAgent: An Affect-Sensitive Cognitive Architecture for Conflict-Aware Memory in LLM Agents
arXiv cs.HC · 7 August 2026
Blast Radius
arXiv cs.AI · 7 August 2026
ResidencyRL: Reinforcement Learning in Simulated Clinical Environments
arXiv · 7 August 2026
SkillProx: Self-Evolving Agent Skills via Proximal Textual Gradient Descent
arXiv cs.AI · 7 August 2026
How to cite this record
ethics.ai (7 August 2026), “TEPA: Revoking Stale Memories for Conflict-Robust Language Agents,” evidence record 17915, https://ethics.ai/record/17915 (originally published by arXiv cs.AI).
Use and limitations
This page is a stable index and citation surface for a source record. ethics.ai did not author the underlying report and has not independently verified every claim. Automatic topics may be imperfect. For consequential use, quote and cite the original publisher.