← Back to all news
arXiv AI By Naen Xu, Wanqing Cui, Yibo Hu, Shixin Hong, Hengyu An, Meiguang Jin, Junfeng Ma, Tianyu Du

StateTree: Enhancing Long-Term Dialogue Reasoning via Reinforcement Learning

Read the original on arXiv AI →

StateTree is a reinforcement learning approach that improves long‑term dialogue reasoning by building a tree‑structured auxiliary task from limited dialogue data. The method embeds key‑value records across multiple sessions into a binary tree, requiring the model to traverse from root to leaf, retrieve records, compare timestamps, and identify a target question among distractors. Curriculum RL training increases tree depth, and a compositional variant trains the model to combine partial reasoning fragments, enabling cross‑session retrieval, temporal reasoning, knowledge updates, and multi‑hop reasoning while generalizing from 10K‑token to 128K‑token contexts.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

Related stories

arXiv Computation and Language
Sep 15

Where to Look and What to Use: Retrieve-Localize-Generate for Long-Term Conversational Memory Question Answering

arXiv:2609.07093v2 Announce Type: replace Abstract: Retrieval-augmented generation (RAG) enables large language models (LLMs) to answer questions by accessing external knowledge and has been widely a...

By Yifan Wang, Xinkui Lin, Yongxiu Xu, Shen Gao, Ruochen Yang, Kun Huang, Yubin Wang, Jie Wu, Wei Liu, Jian Luan, Hongbo Xu, Shuo Shang
llmsragnlpbenchmarks
More like this →
arXiv AI
Aug 6

Chained Recursive Language Models for Multi-Iteration Reasoning

arXiv:2608. 05124v1 Announce Type: cross Abstract: Long context reasoning in large language models (LLMs) is usually constrained by the fact that a single inference trajectory has to simultaneously explore the context, store intermediate state, verify evidence, and produce the final answer.

By Purbesh Mitra, Sennur Ulukus
llms
More like this →
arXiv AI
Sep 10

Difficulty-Adaptive Tree-Structured Policy Optimization for Expanding Reasoning Coverage in RLVR

The paper introduces DATPO, a Difficulty‑Adaptive Sentence‑entropy‑guided Tree‑structured Policy Optimization method designed to improve reasoning coverage in Reinforcement Learning with Verifiable Rewards (RLVR). It builds on three design principles: adaptive difficulty rollouts, tree‑based rollouts, and sentence‑entropy‑guided forking to enhance semantic diversity. Experiments on mathematical reasoning benchmarks show that DATPO outperforms existing baselines, particularly in pass@k, leading to better test‑time scaling performance.

By Youngjun Yu, Sanghwan Jang, Hwanjo Yu
reinforcement-learningbenchmarks
More like this →