A belief-state context manager trained with reinforcement learning and three auxiliary losses improves LLM tool invocation under dynamic user intent changes, per a new synthetic benchmark and two external benchmarks.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
IACM-RL: Intent-Aware Context Management and Reinforcement Learning for Complex Tool Invocation under Dynamic Intent Fluctuations
A belief-state context manager trained with reinforcement learning and three auxiliary losses improves LLM tool invocation under dynamic user intent changes, per a new synthetic benchmark and two external benchmarks.