Improvements in LLM Theory of Mind on static benchmarks do not reliably improve performance in dynamic, first-person human-AI interactions across goal-oriented and experience-oriented tasks.
arXiv preprint arXiv:2501.15355 , year=
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
representative citing papers
Evo-Memory is a new streaming benchmark and evaluation framework for self-evolving memory in LLM agents, unifying over ten memory modules and introducing the ReMem pipeline for continual improvement on multi-turn and reasoning datasets.
citing papers explorer
-
Does Theory of Mind Improvement Really Benefit Human-AI Interactions? Empirical Findings from Interactive Evaluations
Improvements in LLM Theory of Mind on static benchmarks do not reliably improve performance in dynamic, first-person human-AI interactions across goal-oriented and experience-oriented tasks.
-
Evo-Memory: Benchmarking LLM Agent Test-time Learning with Self-Evolving Memory
Evo-Memory is a new streaming benchmark and evaluation framework for self-evolving memory in LLM agents, unifying over ten memory modules and introducing the ReMem pipeline for continual improvement on multi-turn and reasoning datasets.