Switch-SWE: Do Coding Agents Hold Focus When Switching Between Unfinished Tasks?
cs.CL
Submitted: 2026-11-01
Updated: 2026-11-01
Code: https://github.com/Miraclecsc/Switch-SWE
Terminology
Sources
- Why Struggle with Continuous Latents? Interpretable Discrete Latent Reasoning via Rendered Compression
- Evaluating Large Language Models Trained on Code
- Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory
- SWE-Marathon: Can Agents Autonomously Complete Ultra-Long-Horizon Software Work?
- DeepSWE: Measuring Frontier Coding Agents on Original, Long-Horizon Engineering Tasks
- CORPGEN: Simulating Corporate Environments with Autonomous Digital Employees in Multi-Horizon Task Environments
- ChainSWE: Benchmarking Coding Agents on Multi-Bug Software Maintenance
- Handoff Debt: The Rediscovery Cost When Coding Agents Take Over Interrupted Tasks
- SWE-EVO: Benchmarking Coding Agents in Long-Horizon Software Evolution Scenarios
- The Complexity Trap: Simple Observation Masking Is as Efficient as LLM Summarization for Agent Context Management
- SWE-Lancer: Can Frontier LLMs Earn $1 Million from Real-World Freelance Software Engineering?
- MemGPT: Towards LLMs as Operating Systems
- SWE-INTERACT: Reimagining SWE Benchmarks as User-Driven Long-Horizon Coding Sessions
- SWE-PolyBench: A multi-language benchmark for repository level evaluation of coding agents
- SWE-Touch: Benchmarking Coding Agents When Users Touch the Code
- SWE-Together: Evaluating Coding Agents in Interactive User Sessions
- Agentless: Demystifying LLM-based Software Engineering Agents
- SWE-bench Multimodal: Do AI Systems Generalize to Visual Software Domains?
- SWE Context Bench: A Benchmark for Context Learning in Coding
- When Users Change Their Mind: Evaluating Interruptible Agents in Long-Horizon Web Navigation
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