In long-term interactions with large language model (LLM) agents, users reveal habits through their choices and actions. These habits capture implicit user information that agents must infer across co
HABIT-Bench evaluates whether LLM agent memory systems can infer implicit user habits from sparse dialogue evidence and apply them correctly across long-term interactions.
In long-term interactions with large language model (LLM) agents, users reveal habits through their choices and actions. These habits capture implicit user information that agents must infer across conversations. However, individual observations may provide only partial evidence about a habit or when it applies. Retaining past interactions alone does not ensure that agents can infer habits and apply them appropriately. We introduce HABIT-Bench to evaluate how well agent memory systems infer habits from weak evidence and apply them to later requests. We construct synthetic user histories from task-oriented dialogue data and controlled habit graphs. The histories span hundreds of sessions…
Summary and abstract excerpt via Hugging Face Papers ↗ · arXiv.
HABIT-Bench: Evaluating Habit Induction from Longitudinal Weak Evidence in Agent Memory was first seen on Hugging Face · Daily papers on Oct 28, 2026. Since then it has appeared in 20 checks on 2 different days. Its best position was #5 of 30, reached on Oct 28, 09:28 UTC. It dropped off the list after Oct 29, 19:28 UTC.
Position on Hugging Face · Daily papers at every check (lower is better).
Best rank per day (UTC).
Platform metric as reported by Hugging Face.
Archived daily, weekly and monthly lists that include this entry.
Not at the moment. It was last on the list on Oct 29, 19:28 UTC, after 2 days of trending.
#5 on Hugging Face · Daily papers, on Oct 28, 09:28 UTC. Trendoday checks this list every 120 minutes.
It was first seen on Oct 28, 2026 and has been on the list on 2 days (20 checks) since.