Memory-equipped LLM agents exhibit increasing safety violation rates as memory accumulates across independent tasks, termed temporal memory contamination, detected via a new trigger-probe protocol.
Are your agents upward deceivers?
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 4verdicts
UNVERDICTED 4roles
background 1polarities
background 1representative citing papers
ATBench is a new trajectory-level benchmark with 1,000 diverse and realistic scenarios for assessing safety in LLM agents.
Forage V2 enables agent organizations to grow knowledge from 0 to 54 entries over runs and transfer it so weaker models nearly match stronger ones in coverage, cost, and speed on open-world tasks.
Generative multi-agent systems exhibit emergent collusion and conformity behaviors that cannot be prevented by existing agent-level safeguards.
citing papers explorer
-
Remembering More, Risking More: Longitudinal Safety Risks in Memory-Equipped LLM Agents
Memory-equipped LLM agents exhibit increasing safety violation rates as memory accumulates across independent tasks, termed temporal memory contamination, detected via a new trigger-probe protocol.
-
ATBench: A Diverse and Realistic Agent Trajectory Benchmark for Safety Evaluation and Diagnosis
ATBench is a new trajectory-level benchmark with 1,000 diverse and realistic scenarios for assessing safety in LLM agents.
-
Forage V2: Knowledge Evolution and Transfer in Autonomous Agent Organizations
Forage V2 enables agent organizations to grow knowledge from 0 to 54 entries over runs and transfer it so weaker models nearly match stronger ones in coverage, cost, and speed on open-world tasks.
-
Emergent Social Intelligence Risks in Generative Multi-Agent Systems
Generative multi-agent systems exhibit emergent collusion and conformity behaviors that cannot be prevented by existing agent-level safeguards.