Framing LLM agent loops as a Context Gathering Decision Process POMDP yields a predicate-based belief state that boosts multi-hop reasoning up to 11.4% and an exhaustion gate that cuts token use up to 39% with no performance loss.
Lost in the maze: Overcoming context limitations in long-horizon agentic search
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.AI 2years
2026 2representative citing papers
Longer action horizons bottleneck LLM agent training through instability, but training with reduced horizons stabilizes learning and enables better generalization to longer horizons.
citing papers explorer
-
The Context Gathering Decision Process: A POMDP Framework for Agentic Search
Framing LLM agent loops as a Context Gathering Decision Process POMDP yields a predicate-based belief state that boosts multi-hop reasoning up to 11.4% and an exhaustion gate that cuts token use up to 39% with no performance loss.
-
On Training Large Language Models for Long-Horizon Tasks: An Empirical Study of Horizon Length
Longer action horizons bottleneck LLM agent training through instability, but training with reduced horizons stabilizes learning and enables better generalization to longer horizons.