RippleCP: Measuring Counterfactual Checkpoint Advantage in Coding Agents

cs.AI

Submitted: 2026-10-06

Updated: 2026-10-06

Comments: 16 pages

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

Sources

• Crab: A Semantics-Aware Checkpoint/Restore Runtime for Agent Sandboxes
• DeltaBox: Scaling Stateful AI Agents with Millisecond-Level Sandbox Checkpoint/Rollback
• DART: Semantic Recoverability for Structured Tool Agents
• Resume Means Resume: A Machine-Checked Conformance Contract for Checkpoint, Interrupt, and Resume Semantics in Workflow Persistence Layers
• ACRFence: Preventing Semantic Rollback Attacks in Agent Checkpoint-Restore
• BEGIN AI TRANSACTION: Semantic Isolation for Durable AI Workflows
• StructAgent: Harness Long-horizon Digital Agents with Unified Causal Structure
• Training Deep Nets with Sublinear Memory Cost
• Causal Agent Replay: Counterfactual Attribution for LLM-Agent Failures
• Forgetting Only What Matters: Layer-Selective Unlearning toward Robust LLMs
• RAZOR: Ratio-Aware Layer Editing for Targeted Unlearning in Vision Transformers and Diffusion Models
• Embodied Foundation Models at the Edge: A Survey of Deployment Constraints and Mitigation Strategies
• CatRAG: Functor-Guided Structural Debiasing with Retrieval Augmentation for Fair LLMs
• Position: LLMs Must Use Functor-Based and RAG-Driven Bias Mitigation for Fairness
• PERSA: Reinforcement Learning for Professor-Style Personalized Feedback with LLMs
• Listening with Attention: Entropy-Guided Explainability for Transformer-Based Audio Models
• SafeCommit: Certifying When Memory-Grounded Agents May Safely Act

Related papers

• MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
• Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
• Agents' Last Exam
• The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
• MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
• Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems