Long-horizon LLM agents require reinforcement learning methods that can assign credit to intermediate decisions under sparse and delayed rewards. Recent group-based methods such as GiGPO improve over trajectory-level GRPO by constructing step-level advantages at repeated anchor states. However, we show that such dense credit can be statistically unreliable: under limited rollouts, rare but lucky actions may receive overly large advantages, producing divergent anchor bias and late-stage training oscillation. We propose Evidence-Calibrated Policy Optimization (ECPO), a critic-free policy optimization algorithm that calibrates step-level credit before policy updates. ECPO combines Evidence-Calibrated Action Advantage, which groups rollouts by canonical actions and shrinks low-count estimates, with Variance-Gated Credit Weighting, which suppresses anchor states dominated by within-action noise. Experiments on ALFWorld and WebShop with Qwen2.5-1.5B/7B show that ECPO consistently outperforms strong baselines, improving GiGPO by +5.2/+7.3 success points on ALFWorld/WebShop with Qwen2.5-1.5B while adding only 0.1% additional advantage-computation overhead.

Machine-generated text (MGT) detection is critical for regulating online information ecosystems, yet existing detectors often fail under limited fresh supervision and humanization-oriented attacks. We study this problem as few-shot robustness recovery under evolving generators, domains, and attack patterns, and use threat modeling to diagnose detector failures from an attacker’s viewpoint. We identify unstable local boundary estimation as a key failure mode: under scarce supervision, humanized MGT can induce prediction flips, logit drift, and clean–adversarial representation misalignment. To address this issue, we propose RAG-GuidEd Attacker Strengthens ConTrastive Few-shot Detector (REACT), a threat-aware few-shot robustness framework. REACT uses a dynamic retrieval-guided attacker to generate boundary-oriented humanized rewrites from extreme positive–negative anchors, and trains the detector with a pairwise boundary contrastive objective to stabilize clean–adversarial local geometry. Alternating attacker–detector updates further form a co-evolutionary curriculum. Experiments on 4 datasets with 4 shot sizes and 3 random seeds show that REACT improves average detection F1 by 4.95 points over 8 SOTA detectors and reduces average attack success rate under 4 strong attacks by 3.66 percentage points.