Quality, Not Just Outcome: A Structural Scoring Framework for Selecting Coding-Agent Trajectories for Supervised Fine-Tuning
cs.AI
Submitted: 2026-10-09
Updated: 2026-10-09
Code: https://github.com/DuHeng0128/TQS
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- SWE-rebench: An Automated Pipeline for Task Collection and Decontaminated Evaluation of Software Engineering Agents
- Chain-of-Thought Unfaithfulness as Disguised Accuracy
- Beyond Quantity: Trajectory Diversity Scaling for Code Agents
- Agentic Reinforced Policy Optimization
- R2E-Gym: Procedural Environments and Hybrid Verifiers for Scaling Open-Weights SWE Agents
- Measuring Faithfulness in Chain-of-Thought Reasoning
- Rethinking the Role of Entropy in Optimizing Tool-Use Behaviors for Large Language Model Agents
- From Patches to Trajectories: Privileged Process Supervision for Software-Engineering Agents
- Lingma SWE-GPT: An Open Development-Process-Centric Language Model for Automated Software Improvement
- SWE-RL: Advancing LLM Reasoning via Reinforcement Learning on Open Software Evolution
- Agentless: Demystifying LLM-based Software Engineering Agents
- Qwen3 Technical Report
- SWE-smith: Scaling Data for Software Engineering Agents
- Building Coding Agents via Entropy-Enhanced Multi-Turn Preference Optimization
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
- Agents' Last Exam
- 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