SWE-Prime: Fewer Trajectories, Better Performance

arXiv:2608.27449 · cs.SE, cs.AI, cs.CL · Submitted 2026-08-27 · Read on arXiv

cs.SE, cs.AI, cs.CL

Submitted: 2026-08-27

Updated: 2026-08-27

Terminology

• Benchmark — 13× in this paper · explained in 2 episodes
• Redundancy — 10× in this paper · explained in 2 episodes
• Verification — 4× in this paper · explained in 2 episodes
• Consistency — 3× in this paper · explained in 3 episodes
• Fine-Tuning — 3× in this paper · explained in 5 episodes
• Clustering — 2× in this paper · explained in 2 episodes
• Foundation Model — 2× in this paper · explained in 3 episodes
• Foundation Models — 2× in this paper · explained in 7 episodes
• Generalization — 2× in this paper · explained in 13 episodes
• Supervised Fine-Tuning (SFT) — 2× in this paper · explained in 8 episodes
• Verifier — 2× in this paper · explained in 2 episodes
• AI Agents — 1× in this paper · explained in 2 episodes
• Adam — 1× in this paper · explained in 2 episodes
• Alignment — 1× in this paper · explained in 1 episode
• Benchmarking — 1× in this paper · explained in 3 episodes
• Calibration — 1× in this paper · explained in 7 episodes
• Core — 1× in this paper · explained in 2 episodes
• Embeddings — 1× in this paper · explained in 2 episodes
• Grounding — 1× in this paper · explained in 3 episodes
• Instruction Tuning — 1× in this paper · explained in 2 episodes
• Multi-Agent Framework — 1× in this paper · explained in 3 episodes
• Regularization — 1× in this paper · explained in 3 episodes
• Representation Learning — 1× in this paper · explained in 2 episodes
• Synthetic Data Generation — 1× in this paper · explained in 5 episodes

Sources

• SWE-rebench: An Automated Pipeline for Task Collection and Decontaminated Evaluation of Software Engineering Agents
• Training LLM-Based Agents with Synthetic Self-Reflected Trajectories and Partial Masking
• SWE-Bench Pro: Can AI Agents Solve Long-Horizon Software Engineering Tasks?
• GLM-4.5: Agentic, Reasoning, and Coding (ARC) Foundation Models
• SWE-Factory: Your Automated Factory for Issue Resolution Training Data and Evaluation Benchmarks
• R2E-Gym: Procedural Environments and Hybrid Verifiers for Scaling Open-Weights SWE Agents
• PhoenixRepair: Rethinking Repair Strategy Exploration in Software Agents
• Advances and Frontiers of LLM-based Issue Resolution in Software Engineering: A Comprehensive Survey
• SWE-Next: Scalable Real-World Software Engineering Tasks for Agents
• Let's Verify Step by Step
• Training Software Engineering Agents and Verifiers with SWE-Gym
• Qwen3 Technical Report
• SERA: Soft-Verified Efficient Repository Agents
• SWE-Master: Unleashing the Potential of Software Engineering Agents via Post-Training
• SWE-Lego: Pushing the Limits of Supervised Fine-tuning for Software Issue Resolving
• Solving math word problems with process- and outcome-based feedback
• Towards an Understanding of Context Utilization in Code Intelligence
• Reducing Cost of LLM Agents with Trajectory Reduction
• ToolMind Technical Report: A Large-Scale, Reasoning-Enhanced Tool-Use Dataset
• SWE-smith: Scaling Data for Software Engineering Agents

Related papers

• Falsification-Based Verification of LLM-Generated Optimization Models: Sound Test Batteries and Their Detection Limits
• GitSkills: A Dataset of Agent Skills on GitHub
• SABER: Benchmarking Operational Safety of LLM Coding Agents in Stateful Project Workspaces
• PackMonitor: Enabling Zero Package Hallucinations Through Decoding-Time Monitoring
• IntentCoding: Amplifying User Intent in Code Generation
• Incentives and Outcomes in Bug Bounties