← Search

Sikuan Yan

2 accepted papers

2026

EchoRL: Reinforcement Learning via Rollout Echoing

ICML 2026poster

Reinforcement Learning with Verifiable Rewards is an effective route for post-training to strengthen the reasoning capability of large language models. However, as training proceeds, the learning signal can collapse thus makes the training gain become marginal and ineffective. Specifically, a growin…

Cited by 0SourceScholar
2025

TCP: a Benchmark for Temporal Constraint-Based Planning

EMNLP 2025

Temporal reasoning and planning are essential capabilities for large language models (LLMs), yet most existing benchmarks evaluate them in isolation and under limited forms of complexity. To address this gap, we introduce the Temporal Constraint-based Planning (TCP) benchmark, that jointly assesses