ARSM: Auto-Regressive State Machine for Agentic Reasoning Compression
cs.CL
Submitted: 2026-09-26
Updated: 2026-09-26
Code: https://github.com/leo-xfm/ARSM
Terminology
Sources
- ReST meets ReAct: Self-Improvement for Multi-Step Reasoning LLM Agent
- Agent-FLAN: Designing Data and Methods of Effective Agent Tuning for Large Language Models
- AttentionRAG: Attention-Guided Context Pruning in Retrieval-Augmented Generation
- GLM-5: from Vibe Coding to Agentic Engineering
- Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning
- ACON: Optimizing Context Compression for Long-horizon LLM Agents
- Unlocking Context Constraints of LLMs: Enhancing Context Efficiency of LLMs with Self-Information-Based Content Filtering
- MemGPT: Towards LLMs as Operating Systems
- U-Fold: Dynamic Intent-Aware Context Folding for User-Centric Agents
- SWE-Pruner: Self-Adaptive Context Pruning for Coding Agents
- ContextBudget: Budget-Aware Context Management for Long-Horizon Search Agents
- Qwen2 Technical Report
- HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering
- AgentFold: Long-Horizon Web Agents with Proactive Context Management
- MEM1: Learning to Synergize Memory and Reasoning for Efficient Long-Horizon Agents
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