LLM agents

TokenCast: Predicting Token Usage During LLM Agent Execution

TokenCast predicts LLM agent token usage from call counts, context growth, and cost residuals, improving budge…

SparseEngine: An Inference Engine That Prioritizes Sparsity

SparseEngine unifies 15 sparse KV-cache methods for long-context LLM agents, adds Chain Cache and prefix pruni…

SLCA-GRPO: Addressing Cross-Segment Credit Misassignment in Tool-Calling Reinforcement Learning

SLCA-GRPO separates tool and summary credit, improving success, cutting tool turns, and avoiding extra rollout…

Revisiting World Modeling for LLM Agents through an Agent-Editing World Model

AEWM shifts long-horizon LLM agent world modeling from predicting observations to editing reasoning and action…

Training Language Models for Belief Revision in Effective Long-Horizon Decision-Making

ABBEL is a new training framework that lets LLM agents maintain memory-efficient natural-language belief state…