Momento benchmark reveals current agents fail at multi-session tasks mainly by misestimating user state and treating old session history as current context instead of stale data needing re-validation.
Victor Barres, Honghua Dong, Soham Ray, Xujie Si, and Karthik Narasimhan
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CL 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
T1-Bench introduces a multi-domain benchmark for agentic LLM systems featuring 25 domains, interleaved scenarios, and both automatic and human evaluation.
citing papers explorer
-
Momento: Evaluating Persistent Memory and Reasoning with Multi-Session Agentic Conversations
Momento benchmark reveals current agents fail at multi-session tasks mainly by misestimating user state and treating old session history as current context instead of stale data needing re-validation.
-
T1-Bench: Benchmarking Multi-Scenario Agents in Real-World Domains
T1-Bench introduces a multi-domain benchmark for agentic LLM systems featuring 25 domains, interleaved scenarios, and both automatic and human evaluation.