activity
20242026
collaborators
Showing cs.LGShow all

6 papers · 1 filter

cs.LG2026

ADWIN: Adaptive Windows for Horizon-Aware On-Policy Distillation

Kun Liang, Chenming Tang, Clive Bai +3

On-policy distillation (OPD) transfers reasoning behavior by training a student on teacher feedback along student-generated trajectories, but standard full-rollout training ties ev…

cs.LG2026

RLVR Datasets and Where to Find Them: Tracing Data Lineage for Better Training Data

Hsiu-Yuan Huang, Weijie Liu, Chenming Tang +5

The proliferation of Reinforcement Learning from Verifiable Rewards (RLVR) datasets has exacerbated provenance collapse due to unclear lineage among existing datasets. To bridge th…

cs.LG2026

Democratizing Tool Learning with Environments Fully Simulated by a Free 8B Language Model

Chenming Tang, Hsiu-Yuan Huang, Weijie Liu +3

Reinforcement learning (RL) has become a prevalent paradigm for training tool calling agents, which typically requires online interactive environments. Existing approaches either r…

cs.LG2026

ORBIT: On-policy Exploration-Exploitation for Controllable Multi-Budget Reasoning

Kun Liang, Clive Bai, Xin Xu +5

Recent Large Reasoning Models (LRMs) achieve strong performance by leveraging long-form Chain-of-Thought (CoT) reasoning, but uniformly applying overlong reasoning at inference tim…

cs.LG2026

Do Not Step Into the Same River Twice: Learning to Reason from Trial and Error

Chenming Tang, Hsiu-Yuan Huang, Weijie Liu +3

Reinforcement learning with verifiable rewards (RLVR) has significantly boosted the reasoning capability of language models (LMs). However, existing RLVR approaches train LMs based…

cs.LG2026

Think Outside the Policy: In-Context Steered Policy Optimization

Hsiu-Yuan Huang, Chenming Tang, Weijie Liu +3

Existing Reinforcement Learning from Verifiable Rewards (RLVR) methods, such as Group Relative Policy Optimization (GRPO), have achieved remarkable progress in improving the reason…