14 papers
CoLT: Teaching Multi-Modal Models to Think with Chain of Latent Thoughts
Lianyu Hu, Shengqian Qin, Zeqin Liao +4
Chain-of-thought (CoT) reasoning has enabled multi-modal large language models (MLLMs) to tackle complex visual reasoning tasks by generating explicit intermediate reasoning steps…
CoEvoT: Co-Evolving Chain-of-Thought Prompting for Graph-LLM Reasoning
Haohua Niu, Xingtong Yu, Yang Liu +6
Graph learning under distribution shift presents a persistent challenge, where models adapt to new graphs with limited or even no supervision. Recent graph--LLM approaches move tow…
Temporal-Aware Reasoning Optimization for Video Temporal Grounding
Minghang Zheng, Zihao Yin, Yi Yang +2
Multi-modal Large Language Models (MLLMs) have achieved remarkable progress in video temporal grounding with reinforcement learning for generating reasoning paths. However, existin…
Bridging the Agent-World Gap: Text World Models for LLM-based Agents
Yixia Li, Hongru Wang, Peng Lai +13
Large language model (LLM)-based agents are increasingly used in interactive textual environments, from web navigation and code editing to tool use and long-horizon dialogue. Yet m…
InA-Probe: Instruction-Aware Active Probing for Time Series Forecasting with LLMs
Peiliang Gong, Emadeldeen Eldele, Chenyu Liu +8
Large Language Models (LLMs) have recently demonstrated impressive potential for time series forecasting. However, existing methods predominantly rely on passive modality alignment…
TVI-CoT: Text-Visual Interleaved Chain-of-Thought Reasoning for Multimodal Understanding
Lianyu Hu, Xiaoyu Ma, Zeqin Liao +1
Chain-of-thought (CoT) reasoning has proven effective for enhancing problem-solving in large language models. However, when applied to multimodal LLMs (MLLMs), existing CoT approac…
$OneMillion-Bench: How Far are Language Agents from Human Experts?
Qianyu Yang, Yang Liu, Jiaqi Li +19
As language models (LMs) evolve from chat assistants to long-horizon agents capable of multi-step reasoning and tool use, existing benchmarks remain largely confined to structured…
Counterfactual Credit Policy Optimization for Multi-Agent Collaboration
Zhongyi Li, Wan Tian, Jinju Chen +4
Collaborative multi-agent large language models (LLMs) can solve complex reasoning tasks by decomposing roles, but reinforcement learning for such systems is limited by credit assi…
DynaTokens: Controlling Token Dynamics for Continual Video-Language Understanding
Toan Nguyen, Yang Liu, Celso De Melo +1
Continual VideoQA with multimodal LLMs remains challenging because sequential adaptation induces task interference, while storing task-specific prompts becomes impractical as task…
Native Parallel Reasoner: Reasoning in Parallelism via Self-Distilled Reinforcement Learning
Tong Wu, Yang Liu, Jun Bai +6
We introduce Native Parallel Reasoner (NPR), a teacher-free framework that enables Large Language Models (LLMs) to self-evolve genuine parallel reasoning capabilities. NPR transfor…
Make an Offer They Can't Refuse: Grounding Bayesian Persuasion in Real-World Dialogues without Pre-Commitment
Buwei He, Yang Liu, Zhaowei Zhang +6
Large language models (LLMs) still struggle with strategic persuasion, largely because existing approaches either neglect information asymmetry or rely on unrealistic pre-commitmen…
Understanding and Leveraging the Expert Specialization of Context Faithfulness in Mixture-of-Experts LLMs
Jun Bai, Minghao Tong, Yang Liu +2
Context faithfulness is essential for reliable reasoning in context-dependent scenarios. However, large language models often struggle to ground their outputs in the provided conte…
RuleReasoner: Reinforced Rule-based Reasoning via Domain-aware Dynamic Sampling
Yang Liu, Jiaqi Li, Zilong Zheng
Rule-based reasoning is acknowledged as one of the fundamental problems of reasoning. While recent studies show that large reasoning models (LRMs) have remarkable reasoning capabil…
ReflectEvo: Improving Meta Introspection of Small LLMs by Learning Self-Reflection
Jiaqi Li, Xinyi Dong, Yang Liu +6
We present a novel pipeline, ReflectEvo, to demonstrate that small language models (SLMs) can enhance meta introspection through reflection learning. This process iteratively gener…