The Handoff Tax: Continuing Non-Native Trajectories in LLM Agents
cs.AI
Submitted: 2026-08-25
Updated: 2026-08-25
Code: https://github.com/swe-agent/mini-swe-agent
Terminology
Sources
- AutoMix: Automatically Mixing Language Models
- FrugalGPT: How to Use Large Language Models While Reducing Cost and Improving Performance
- Training Verifiers to Solve Math Word Problems
- Hybrid LLM: Cost-Efficient and Quality-Aware Query Routing
- R2V Agent: Teaching SLMs When to Ask for Help
- RouterBench: A Benchmark for Multi-LLM Routing System
- LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code
- Handoff Debt: The Rediscovery Cost When Coding Agents Take Over Interrupted Tasks
- Evaluating Performance Drift from Model Switching in Multi-Turn LLM Systems
- UCCI: Calibrated Uncertainty for Cost-Optimal LLM Cascade Routing
- LLMs Get Lost In Multi-Turn Conversation
- RouteLLM: Learning to Route LLMs with Preference Data
- Gorilla: Large Language Model Connected with Massive APIs
- ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs
- Toolformer: Language Models Can Teach Themselves to Use Tools
- SWE-Router: Routing in Multi-turn Agentic Software Engineering Tasks
- C3PO: Optimized Large Language Model Cascades with Probabilistic Cost Constraints for Reasoning
- OpenHands: An Open Platform for AI Software Developers as Generalist Agents
- BrowseComp: A Simple Yet Challenging Benchmark for Browsing Agents
- TheAgentCompany: Benchmarking LLM Agents on Consequential Real World Tasks
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