Rollback the World, Keep the Reflection: Rollback-Induced Reflection for Long-Horizon LLM Agents

arXiv:2609.18304 · cs.CL, cs.RO · Submitted 2026-09-16 · Read on arXiv

cs.CL, cs.RO

Submitted: 2026-09-16

Updated: 2026-09-22

Comments: 12 pages

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

Terminology

• Benchmark — 9× in this paper · explained in 2 episodes
• Rollback-Induced Reflection — 8× in this paper
• Ablation — 3× in this paper · explained in 1 episode
• Large Language Model (LLM) — 3× in this paper · explained in 3 episodes
• Adam — 2× in this paper · explained in 2 episodes
• AI Agents — 1× in this paper · explained in 2 episodes
• Action Space — 1× in this paper · explained in 1 episode
• Affordance — 1× in this paper · explained in 1 episode
• Agentic System — 1× in this paper · explained in 2 episodes
• Chain-of-Thought Prompting — 1× in this paper · explained in 2 episodes
• Core — 1× in this paper · explained in 2 episodes
• Heterogeneous Graph — 1× in this paper · explained in 2 episodes
• Iterative Refinement — 1× in this paper · explained in 3 episodes
• LLM-as-a-Judge — 1× in this paper · explained in 3 episodes
• Multi-Agent System — 1× in this paper · explained in 6 episodes
• Provenance — 1× in this paper · explained in 3 episodes
• RAG — 1× in this paper · explained in 3 episodes
• Reinforcement Learning — 1× in this paper · explained in 4 episodes
• Verification — 1× in this paper · explained in 2 episodes

Sources

• Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory
• AgentScope 1.0: A Developer-Centric Framework for Building Agentic Applications
• Speculative Rollback Correction for Quality-Diverse Web Agent Imitation
• DeepSeek-V3 Technical Report
• ALFWorld: Aligning Text and Embodied Environments for Interactive Learning
• Qwen3 Technical Report
• DART: Semantic Recoverability for Structured Tool Agents
• ReAct: Synergizing Reasoning and Acting in Language Models
• Language Agent Tree Search Unifies Reasoning Acting and Planning in Language Models

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