Skip to content

Author

Xinran Chen

We have 5 of 81 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#artificial intelligence Preprint Sep 2026

SWRouter: Similarity-Contractive Window Routing for Multi-Turn Large Language Model Conversations

This paper proposes SWRouter, a Similarity-Contractive Window Router for multi-turn large language model routing that combines a similarity-based context segmentation mechanism for prompt construction with a dual-metric evaluation framework that decouples construction accuracy from router performance.

Yu Wang, Yuchen Li, Rui Kong et al. · 0 citations
Jul 2026

STAMP: Provenance-Guided Credit Assignment for Deep Search Agents

STAMP is proposed, in which a reference-based verifier judges whether each cited document supports an entity or relation in a training-time evidence graph, and first-exposure attribution traces each supported citation back to the action that first surfaced it.

Ke Xu, Han Xu, Xin-Ran Chen et al. · 1 citation
#artificial intelligence Preprint Feb 2026

Not All Preferences Deserve Gradients: Understanding Gradient Utility in Offline Reasoning Alignment

SAGE (Stability-Aware Gradient Efficiency), which maintains difficulty-stratified candidate pools refreshed during training and selects pairs within each pool by a forward-pass signal-to-curvature score, outperforms full-data and size-matched baselines while producing substantially smoother optimization trajectories.

Hui Wu, Hengyi Cai, Jin-Man Zhao et al. · 0 citations
Jul 2026

SCOPE-RL: Optimizing Reasoning Paths Before and After Success

SCOPE-RL improves average accuracy by up to 11.2 pp and reduces reasoning tokens by up to 27.1% over outcome-only GRPO, indicating that reward-signal densification is complementary to policy-update-level RLVR advances.

Xiaojia Liu, Han Xu, Jianqiang Xia et al. · 0 citations
Preprint Aug 2026

TurnSight: Turn-Level Hindsight Self-Distillation for Tool-Integrated Reasoning

TurnSight is proposed, a turn-level hindsight self-distillation framework that derives supervision directly from execution-conditioned hindsight and selects reliable supervision through cross-horizon directional agreement.

Changle Qu, Sun-Hao Dai, Hengyi Cai et al. · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.