Completed Pairs Hide Capped Failures: A ReVerPi Case Study of Selective Context Projection
cs.AI
Submitted: 2026-09-25
Updated: 2026-09-25
Code: https://github.com/earendil-works/pi
Project page: https://nvlabs.github.io/SoL-Pi
Terminology
Sources
- SoL-Pi: Recursively Scaling Auto-Research Loops for Efficient Agent Harness
- The Complexity Trap: Simple Observation Masking Is as Efficient as LLM Summarization for Agent Context Management
- Toward Reliable Context Compression for Long-Horizon Agents: An Empirical Study of Execution Instability
- MemGPT: Towards LLMs as Operating Systems
- Unlocking Context Constraints of LLMs: Enhancing Context Efficiency of LLMs with Self-Information-Based Content Filtering
- ACON: Optimizing Context Compression for Long-horizon LLM Agents
- AI Agents That Matter
- Token Reduction Is Not Cost Reduction
- Deep Reinforcement Learning at the Edge of the Statistical Precipice
- Distribution-Free, Risk-Controlling Prediction Sets
- Time-uniform, nonparametric, nonasymptotic confidence sequences
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
- 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
- VSAL: A Vision Solver with Adaptive Layouts for Graph Property Detection