works on

From the 1 of 13 linked papers with an AI index.

collaborators

13 papers

cs.LG2026

TAPO: Transition-Aware Policy Optimization for LLM Agents

Cong Li, Peixi Peng, Yisen Zhao +4

The paper introduces TAPO, a training framework that augments reinforcement learning for large language model agents with action‑conditioned next‑observation prediction, improving…

cs.CL2026

Search-on-Graph-R1: Training Large Language Models to Search Knowledge Graphs with Reinforcement Learning

Jia Ao Sun, Hao Yu, Fengran Mo +4

Knowledge graph question answering (KGQA) requires navigating from topic entities to an answer several relations away. Recent methods prompt a frontier LLM to explore the graph thr…

cs.AI2026

Learning to Select, Not Relearn: Hard-Routed Mixtures of Reasoning LoRAs

Seyed Alireza Molavi, Zhan Su, Yan Hu +3

Composing independently trained LoRA adapters into a single large language model is useful for multi-domain adaptation, especially when the original training data cannot be shared.…

cs.LG2026

It Takes Two: Your GRPO Is Secretly DPO

Yihong Wu, Liheng Ma, Lei Ding +9

GRPO has emerged as a prominent reinforcement learning algorithm for post-training LLMs. Unlike critic-based methods, GRPO computes advantages by estimating the \emph{value baselin…

cs.CL2026

STOP: Structured On-Policy Pruning of Long-Form Reasoning in Low-Data Regimes

Chenjun Xu, Zhennan Zhou, Zhan Su +3

Long chain-of-thought (Long CoT) reasoning improves performance on multi-step problems, but it also induces overthinking: models often generate low-yield reasoning that increases i…

cs.AI2026

Efficient Data Selection for Multimodal Models via Incremental Optimization Utility

Jinhao Jing, Qiannian Zhao, Chao Huang +1

The scaling of Large Multimodal Models (LMMs) is constrained by the quality-quantity trade-off inherent in synthetic data. Previous approaches, such as LLM-as-a-Judge, have proven…