The RSI Tax: When Recursive Self-Improvement Is Not Worth the Cost
cs.LG
Submitted: 2026-11-10
Updated: 2026-11-10
Terminology
Sources
- Terminal-Bench: Benchmarking Agents on Hard, Realistic Tasks in Command Line Interfaces
- APEX-Agents
- Continual Learning Exam: Benchmarking Long-Horizon RSI and Experiential Learning in LLM Agents
- SEA-Eval: A Benchmark for Evaluating Self-Evolving Agents Beyond Episodic Assessment
- ContinualSkillBench: Can LLM Agents Truly Evolve Their Capabilities?
- EvoSkill: Automated Skill Discovery for Multi-Agent Systems
- Meta-Harness: End-to-End Optimization of Model Harnesses
- RRSI: Regularized Recursive Self-Improvement of Agent Harnesses
- HarnessPro: Recursive Harness Self-Improvement with Pareto Optimization for Performance-Cost Trade-offs
- Rethinking the Evaluation of Harness Evolution for Agents
- Agent Plasticity: Measuring Self-Improvement Through Experience
- How Do AI Agents Spend Your Money? Analyzing and Predicting Token Consumption in Agentic Coding Tasks
- SkillOpt: Executive Strategy for Self-Evolving Agent Skills
- TTHE: Test-Time Harness Evolution
- ServeLearnBench: How Well Can Agents Self-Improve from Serving Experience?
- EvoArena: Tracking Memory Evolution for Robust LLM Agents in Dynamic Environments
- Are Self-Evolving Agents Continual Learners?
- EvoSkill v2: Fully Agentic Skill Evolution from Benchmark Adaptation to a Stateful Evolver
- Token Reduction Is Not Cost Reduction
Related papers
- A Physics-Regulated Neural Framework for Learning 3D Grain Growth Dynamics
- FlexMoE: Learning One-for-All Multi-Budget Expert Pruning for Flexible MoE Deployment
- OptiMind: Improving Small Language Models for Optimization Modeling through Formulation Guidance and Multi-Turn Learning
- Staying in the Sweet Spot: Boost Reasoning Evolution via Responsive Rollout Difficulty Manipulation
- Examining the Impact of Data and Training Methods on Emergent and Subliminal Misalignment
- Rethinking Black-Box On-Policy Distillation: A Rubric-based Analysis