Breaking Babel: A Self-Evolving Multi-Agent System for Long-Form Subtitle Translation

arXiv:2609.38660 · cs.CL, cs.AI, cs.CV, cs.MA · Submitted 2026-09-29 · Read on arXiv

cs.CL, cs.AI, cs.CV, cs.MA

Submitted: 2026-09-29

Updated: 2026-10-01

Terminology

• Accuracy — 46× in this paper · explained in 1 episode
• Consistency — 34× in this paper · explained in 3 episodes
• Benchmark — 16× in this paper · explained in 2 episodes
• Fidelity — 9× in this paper · explained in 2 episodes
• Multi-Agent System — 7× in this paper · explained in 6 episodes
• LLM-as-a-Judge — 6× in this paper · explained in 3 episodes
• Self-Evolving Agents — 6× in this paper · explained in 2 episodes
• Verification — 6× in this paper · explained in 2 episodes
• Ablation — 5× in this paper · explained in 1 episode
• Adaptation — 5× in this paper · explained in 1 episode
• Alignment — 5× in this paper · explained in 1 episode
• Failure Modes — 5× in this paper · explained in 3 episodes
• Trace — 4× in this paper · explained in 2 episodes
• Adam — 3× in this paper · explained in 2 episodes
• Multidimensional Quality Metrics — 3× in this paper
• Agentic System — 2× in this paper · explained in 2 episodes
• Agentic Workflows — 2× in this paper · explained in 1 episode
• Fine-Tuning — 2× in this paper · explained in 5 episodes
• Generalization — 2× in this paper · explained in 13 episodes
• Robustness — 2× in this paper · explained in 5 episodes
• AI Agents — 1× in this paper · explained in 2 episodes
• Ablation study — 1× in this paper · explained in 1 episode
• Aggregation — 1× in this paper · explained in 1 episode
• Benchmarking — 1× in this paper · explained in 3 episodes
• Computational overhead — 1× in this paper · explained in 2 episodes
• Foundation Model — 1× in this paper · explained in 3 episodes
• Foundation Models — 1× in this paper · explained in 7 episodes
• In-Context Learning — 1× in this paper · explained in 4 episodes
• LLM judge — 1× in this paper · explained in 2 episodes
• Large Language Models (LLMs) — 1× in this paper · explained in 6 episodes
• Multi-Agent Framework — 1× in this paper · explained in 3 episodes
• Multi-agent Collaboration — 1× in this paper · explained in 2 episodes
• Multimodal Reasoning — 1× in this paper · explained in 5 episodes
• Reinforcement Learning — 1× in this paper · explained in 4 episodes
• Structural Constraints — 1× in this paper · explained in 2 episodes
• Unified Framework — 1× in this paper · explained in 5 episodes

Sources

• GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning
• SkillCraft: Can LLM Agents Learn to Use Tools Skillfully?
• From Utterance to Vividity: Training Expressive Subtitle Translation LLM via Adaptive Local Preference Optimization
• A Comprehensive Survey of Self-Evolving AI Agents: A New Paradigm Bridging Foundation Models and Lifelong Agentic Systems
• Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution
• A Survey of Self-Evolving Agents: What, When, How, and Where to Evolve on the Path to Artificial Super Intelligence
• EvoPrompt: Connecting LLMs with Evolutionary Algorithms Yields Powerful Prompt Optimizers
• Automated Design of Agentic Systems
• DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelines
• TACTIC: Translation Agents with Cognitive-Theoretic Interactive Collaboration
• DynaSaur: Large Language Agents Beyond Predefined Actions
• OpenAI GPT-5 System Card
• MAATS: A Multi-Agent Automated Translation System Based on MQM Evaluation
• Voyager: An Open-Ended Embodied Agent with Large Language Models
• EvoAgentX: An Automated Framework for Evolving Agentic Workflows
• DelTA: An Online Document-Level Translation Agent Based on Multi-Level Memory
• Evo-Memory: Benchmarking LLM Agent Test-time Learning with Self-Evolving Memory
• Qwen3-Omni Technical Report
• Qwen3 Technical Report
• SIPDO: Closed-Loop Prompt Optimization via Synthetic Data Feedback

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