A training-free, model-agnostic dashboard that exposes per-block context state (tokens, age, budget) with lossless archive/recovery improves long-horizon tool-agent performance on LOCA-Bench, BrowseComp-Plus, and GAIA.
Lost in the maze: Overcoming context limitations in long-horizon agentic search
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
years
2026 4representative citing papers
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.
SlimSearcher reduces tool-call rounds by 17-58% on GAIA, BrowseComp and XBenchDeepSearch while maintaining accuracy via Pareto filtration in SFT and Adaptive Reward Gating in RL.
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
-
LLM Agents Are Latent Context Managers: Eliciting Self-Managed Context via State Proprioception
A training-free, model-agnostic dashboard that exposes per-block context state (tokens, age, budget) with lossless archive/recovery improves long-horizon tool-agent performance on LOCA-Bench, BrowseComp-Plus, and GAIA.
-
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.
-
SlimSearcher: Training Efficiency-Aware Web Agents via Adaptive Reward Gating
SlimSearcher reduces tool-call rounds by 17-58% on GAIA, BrowseComp and XBenchDeepSearch while maintaining accuracy via Pareto filtration in SFT and Adaptive Reward Gating in RL.
-
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.