pith. sign in

Agentrefine: Enhancing agent generalization through refinement tuning

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it

fields

cs.AI 1

years

2026 1

verdicts

UNVERDICTED 1

representative citing papers

From History to State: Constant-Context Skill Learning for LLM Agents

cs.AI · 2026-05-06 · unverdicted · novelty 6.0

Constant-context skill learning trains reusable task-family modules for LLM agents using a deterministic state block for progress tracking and subgoal rewards, achieving 89.6% unseen success on ALFWorld, 76.8% on WebShop, and 66.4% on SciWorld with Qwen3-8B while reducing prompt tokens 2-7x.

citing papers explorer

Showing 1 of 1 citing paper.

  • From History to State: Constant-Context Skill Learning for LLM Agents cs.AI · 2026-05-06 · unverdicted · none · ref 5

    Constant-context skill learning trains reusable task-family modules for LLM agents using a deterministic state block for progress tracking and subgoal rewards, achieving 89.6% unseen success on ALFWorld, 76.8% on WebShop, and 66.4% on SciWorld with Qwen3-8B while reducing prompt tokens 2-7x.