Pdb or Not to Be: Comparing Debugging Interfaces With Pass X @ k
cs.AI, cs.SE
Submitted: 2026-11-05
Updated: 2026-11-05
Terminology
Sources
- On Randomness in Agentic Evals
- Evaluating Large Language Models Trained on Code
- TUMIX: Multi-Agent Test-Time Scaling with Tool-Use Mixture
- Debug2Fix: Can Interactive Debugging Help Coding Agents Fix More Bugs?
- SWE-Doctor: Guiding Software Engineering Agents with Runtime Diagnosis from Multi-Faceted Bug Reproduction Tests
- Agent That Debugs: Dynamic State-Guided Vulnerability Repair
- Stochasticity in Agentic Evaluations: Quantifying Inconsistency with Intraclass Correlation
- Nemotron 3 Ultra: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoning
- gpt-oss-120b & gpt-oss-20b Model Card
- Training Software Engineering Agents and Verifiers with SWE-Gym
- InspectCoder: Dynamic Analysis-Enabled Self Repair through interactive LLM-Debugger Collaboration
- SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering
- debug-gym: A Text-Based Environment for Interactive Debugging
- Does RL Expand the Capability Boundary of LLM Agents? A PASS@(k,T) Analysis
- Diversity Empowers Intelligence: Integrating Expertise of Software Engineering Agents
Related papers
- Multi-Objective Structured Pruning of LLMs for Latency and Model Size Optimization
- 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
- Embeddings for Preferences, Not Semantics
- Can We Trust Item Response Theory for AI Evaluation?
- Diagnosing Task Insensitivity in Language Agents