TextualRL: Textual Reinforcement Learning for Context Management

arXiv:2610.18216 · cs.CL, cs.AI · Submitted 2026-10-13 · Read on arXiv

cs.CL, cs.AI

Submitted: 2026-10-13

Updated: 2026-10-13

Code: https://github.com/ECNU-ICALK/TextualRL

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Reinforcement Learning — 1× in this paper · explained in 4 episodes

Sources

• Trace2Skill: Distill Trajectory-Local Lessons into Transferable Agent Skills
• SkillOpt: Executive Strategy for Self-Evolving Agent Skills
• DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
• EvoSkill: Automated Skill Discovery for Multi-Agent Systems
• ReAct: Synergizing Reasoning and Acting in Language Models
• SearchQA: A New Q&A Dataset Augmented with Context from a Search Engine
• OfficeQA Pro: An Enterprise Benchmark for End-to-End Grounded Reasoning
• LiveMathematicianBench: A Live Benchmark for Research-Level Mathematical Reasoning with Proof Sketches
• ALFWorld: Aligning Text and Embodied Environments for Interactive Learning

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering