RedAct redacts agent traces to drop normalized skill transfer below the no-skill baseline on CapTraceBench while preserving audit evidence and adding detectable behavioral watermarks.
Daya Guo, Dejian Yang, Haowei Zhang, and Junxiao Song
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
representative citing papers
Budget-matched evaluations and partial-prompt contamination probes show several RLVR reasoning gaps shrink or vanish once budgets, prompts, and dataset versions are controlled.
citing papers explorer
-
RedAct: Redacting Agent Capability Traces for Procedural Skill Protection
RedAct redacts agent traces to drop normalized skill transfer below the no-skill baseline on CapTraceBench while preserving audit evidence and adding detectable behavioral watermarks.
-
Position: The Hidden Costs and Measurement Gaps of Reinforcement Learning with Verifiable Rewards
Budget-matched evaluations and partial-prompt contamination probes show several RLVR reasoning gaps shrink or vanish once budgets, prompts, and dataset versions are controlled.