4 papers
Counterfactual Rollout Replay: Forkable Environments as Free Process Rewards for Software Engineering Agents
Yuanhao Li, Hongbo Wang, Xuhong Chen +2
Outcome-only reinforcement learning gives software engineering (SWE) agents a terminal success signal but little direct guidance about intermediate decisions. We introduce Counterf…
BoostAPR: Boosting Automated Program Repair via Execution-Grounded Reinforcement Learning with Dual Reward Models
Yuanhao Li, Hongbo Wang, Xiaotang Shang +3
Reinforcement learning for program repair is hindered by sparse execution feedback and coarse sequence-level rewards that obscure which edits actually fix bugs. We present BoostAPR…
Reflection-Driven Self-Improving Language Model Agents for Adaptive RAN Slicing
Yuanhao Li, Haozhe Wang, Geyong Min +2
Adaptive control in AI-native networks remains challenging because tasks such as dynamic Radio Access Network (RAN) slicing require persistent trade-off decisions among spectrum ef…
DRAFT-RL: Multi-Agent Chain-of-Draft Reasoning for Reinforcement Learning-Enhanced LLMs
Yuanhao Li, Mingshan Liu, Hongbo Wang +3
Large Language Models (LLMs) have shown impressive capabilities in multi-step reasoning and problem-solving.Recent works introduce multi-agent reflection frameworks where multiple…