Deletion Sensitivity Is a Property of the Model: A Three-Condition Measurement over 72 Valid Experimental Cells
cs.CL, cs.AI, cs.SE
Submitted: 2026-11-09
Updated: 2026-11-13
Code: https://github.com/deepseek-ai/deepseek-harness
Terminology
Sources
- Reasoning Shift: How Context Silently Shortens LLM Reasoning
- When Can Agents Forget Their Reasoning? ICLR for Long-Horizon Agent Context Compression
- When Should Agents Think? Adaptive Reasoning via Cross-Turn Estimation
- Reasoning Models Don't Always Say What They Think
- LLMLingua: Compressing Prompts for Accelerated Inference of Large Language Models
- $\tau$-bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains
- LLMs Get Lost In Multi-Turn Conversation
- Measuring Faithfulness in Chain-of-Thought Reasoning
- Prompt Compression for Large Language Models: A Survey
- LLMLingua-2: Data Distillation for Efficient and Faithful Task-Agnostic Prompt Compression
- MINT: Evaluating LLMs in Multi-turn Interaction with Tools and Language Feedback
- Survey on Evaluation of LLM-based Agents
Related papers
- ALARM: Audio-Language Alignment for Reasoning Models
- ThinkSum: Probabilistic reasoning over sets using large language models
- Coherence boosting: When your pretrained language model is not paying enough attention
- From Facts to Insights: A Persona-Driven Dual Memory Framework and Dataset for Role-Playing Agents
- Improving General Role-Playing Agents via Psychology-Grounded Reasoning and Role-Aware Policy Optimization
- The Art of Asking: Multilingual Prompt Optimization for Synthetic Data