Showing cs.AIShow all
2 papers · 1 filter
cs.AI2026
SWE-Ladder: Learning to Localize, Reproduce, and Patch via Progressive Privileged Self-Distillation
Xudong Cai, Zhengxi Lu, Yuchen Yan +4
Resolving a repository-level issue typically requires a software-engineering (SWE) agent to localize the faulty code, reproduce the failure, and patch the code. Reinforcement learn…
cs.AI2025
LAPO: Internalizing Reasoning Efficiency via Length-Adaptive Policy Optimization
Xingyu Wu, Yuchen Yan, Shangke Lyu +7
Large reasoning models have achieved remarkable performance through extended chain-of-thought sequences, yet this computational freedom leads to excessive token generation even for…