Haoru Tan

Haoru Tan has 2 papers in our library, in 2026; often with Jiaya Jia, Sitong Wu, Wenhu Zhang.

2 papers in our library · 2026

The profile is the library's match of the name; two people with one name are not always told apart.

Affiliations

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine.

Of its works in our library, with the number of works on each.

The most cited first (OpenAlex and our library).

SearchGym: Bootstrapping Real-World Search Agents via Cost-Effective and High-Fidelity Environment Simulation (2026)
Training LLM search agents with reinforcement learning creates a trade-off. Live commercial search APIs are realistic but expensive. Offline snapshots such as Wikipedia are cheap, but they often disagree with dataset labels. That mismatch produces faulty rewards, which can punish correct answers or reward lucky…
TRAC: Teacher-Guided Token Reward with Adaptive Calibration for Robust Policy Optimization (2026)
Reinforcement learning for LLM reasoning usually depends on a single correctness signal at the end of a solution.

7 co-authors with a page, the most papers together first.

Where their works here were published, the most works first, with the editions of those that have a page.

Updated 2 November 2026