The Model Knows When to Stop: Training-Free Early Stopping for Long-Context Reading

arXiv:2609.34590 · cs.CL, cs.LG · Submitted 2026-09-28 · Read on arXiv

cs.CL, cs.LG

Submitted: 2026-09-28

Updated: 2026-09-28

Code: https://github.com/mu18th/Answer-Convergence-Stopping

Terminology

• Accuracy — 57× in this paper · explained in 1 episode
• Benchmark — 14× in this paper · explained in 2 episodes
• Regret — 8× in this paper · explained in 3 episodes
• Frozen model — 7× in this paper · explained in 3 episodes
• Ablation — 6× in this paper · explained in 1 episode
• Decode — 3× in this paper · explained in 2 episodes
• Robustness — 3× in this paper · explained in 5 episodes
• Abstention — 2× in this paper · explained in 1 episode
• Answer-Convergence Stopping — 2× in this paper
• Ablation study — 1× in this paper · explained in 1 episode
• Adam — 1× in this paper · explained in 2 episodes
• Aggregation — 1× in this paper · explained in 1 episode
• Alignment — 1× in this paper · explained in 1 episode
• Consistency — 1× in this paper · explained in 3 episodes
• Core — 1× in this paper · explained in 2 episodes
• In-Context Learning — 1× in this paper · explained in 4 episodes
• King Abdullah University of Science and Technology — 1× in this paper
• Reinforcement Learning — 1× in this paper · explained in 4 episodes
• Transformer — 1× in this paper · explained in 2 episodes

Sources

• Let's Sample Step by Step: Adaptive-Consistency for Efficient Reasoning and Coding with LLMs
• Walking Down the Memory Maze: Beyond Context Limit through Interactive Reading
• BrowseComp-Plus: A More Fair and Transparent Evaluation Benchmark of Deep-Research Agent
• GridProbe: Posterior-Probing for Adaptive Test-Time Compute in Long-Video VLMs
• Gemma 3 Technical Report
• Language Models (Mostly) Know What They Know
• Kimi K2.5: Visual Agentic Intelligence
• Qwen2.5 Technical Report
• Qwen3 Technical Report
• The $\mathbf{Y}$-Combinator for LLMs: Solving Long-Context Rot with $\lambda$-Calculus
• When to Memorize and When to Stop: Gated Recurrent Memory for Long-Context Reasoning
• MemAgent: Reshaping Long-Context LLM with Multi-Conv RL-based Memory Agent
• Recursive Language Models
• Chain of Agents: Large Language Models Collaborating on Long-Context Tasks

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