13 papers
CalibForge: Adversarial Solver Calibration for Scaling Learnable Terminal Tasks
Fanzhe Meng, Guoxin Chen, Jiale Zhao +6
Training terminal agents requires executable and verifiable tasks that are not merely solvable, but appropriately challenging for learning. Executable validation establishes feasib…
DeNovoSWE: Scaling Long-Horizon Environments for Generating Entire Repositories from Scratch
Jiale Zhao, Guoxin Chen, Fanzhe Meng +4
As the capabilities of LLM-based code agents continue to advance, their expected role is expanding beyond localized bug fixing in existing codebases toward architecting and impleme…
EAPO: Enhancing Policy Optimization with On-Demand Expert Assistance
Siyao Song, Cong Ma, Zhihao Cheng +5
Large language models (LLMs) have recently advanced in reasoning when optimized with reinforcement learning (RL) under verifiable rewards. Existing methods primarily rely on outcom…
Toward Autonomous Long-Horizon Engineering for ML Research
Guoxin Chen, Jie Chen, Lei Chen +7
Agentic systems increasingly automate pieces of AI research. Yet turning underspecified research objectives into runnable, experimentally validated ML systems remains a central bot…
BeyondSWE: Can Current Code Agent Survive Beyond Single-Repo Bug Fixing?
Guoxin Chen, Fanzhe Meng, Jiale Zhao +12
Current code-agent benchmarks primarily evaluate localized issue resolution within a single target repository, leaving under-tested many software engineering tasks that require ext…
Immersion in the GitHub Universe: Scaling Coding Agents to Mastery
Jiale Zhao, Guoxin Chen, Fanzhe Meng +11
Achieving mastery in real world software engineering tasks is fundamentally bottlenecked by the scarcity of large scale, high quality training data. Scaling such data has been limi…