Related papers: DLLM-Searcher: Adapting Diffusion Large Language M…

The ReAct (Reasoning + Action) capability in large language models (LLMs) has become the foundation of modern agentic systems. Recent LLMs, such as DeepSeek-R1 and OpenAI o1/o3, exemplify this by emphasizing reasoning through the generation…

The rapid progress of Large Language Models (LLMs) has given rise to a new category of autonomous AI systems, referred to as Deep Research (DR) agents. These agents are designed to tackle complex, multi-turn informational research tasks by…

Despite their impressive capabilities, large language models (LLMs) often face challenges such as temporal misalignment and generating hallucinatory content. Enhancing LLMs with retrieval mechanisms to fetch relevant information from…

Rapidly evolving cyberattacks demand incident response systems that can autonomously learn and adapt to changing threats. Prior work has extensively explored the reinforcement learning approach, which involves learning response strategies…

Open-source pre-trained Large Language Models (LLMs) exhibit strong language understanding and generation capabilities, making them highly successful in a variety of tasks. However, when used as agents for dealing with complex problems in…

Large Language Models (LLMs), despite their remarkable capabilities, are prone to generating hallucinated or outdated content due to their static internal knowledge. While Retrieval-Augmented Generation (RAG) integrated with Reinforcement…

Recent search-augmented LLMs trained with reinforcement learning (RL) can interleave searching and reasoning for multi-hop reasoning tasks. However, they face two critical failure modes as the accumulating context becomes flooded with both…

The era of intelligent agents is upon us, driven by revolutionary advancements in large language models. Large Language Model (LLM) agents, with goal-driven behaviors and dynamic adaptation capabilities, potentially represent a critical…

The increasing penetration of distributed energy resources into active distribution networks (ADNs) has made effective ADN dispatch imperative. However, the numerous newly-integrated ADN operators, such as distribution system aggregators,…

Diffusion Language Models (DLMs) offer attractive advantages over Auto-Regressive (AR) models, such as full-attention parallel decoding and flexible generation. However, standard DLM training uses a static, single-step masked prediction…

Large Action Models (LAMs) for AI Agents offer incredible potential but face challenges due to the need for high-quality training data, especially for multi-steps tasks that involve planning, executing tool calls, and responding to…

Large Language Models have recently shown impressive capabilities in reasoning and code generation, making them promising tools for natural language interfaces to relational databases. However, existing approaches often fail to generalize…

Diffusion Large Language Models (dLLMs) have emerged as a promising alternative to auto-regressive (AR) models, offering greater expressive capacity and potential for parallel generation and faster inference. However, open-source dLLMs…

Due to the advantages in the cost-efficiency and reproducibility, user simulation has become a promising solution to the user-centric evaluation of information retrieval systems. Nonetheless, accurately simulating user search behaviors has…

Recent research on Reasoning of Large Language Models (LLMs) has sought to further enhance their performance by integrating meta-thinking -- enabling models to monitor, evaluate, and control their reasoning processes for more adaptive and…

Diffusion Large Language Models (dLLMs) represent a new paradigm beyond autoregressive modeling, offering competitive performance while naturally enabling a flexible decoding process. Specifically, dLLMs can generate tokens at arbitrary…

Leveraging more test-time computation has proven to be an effective way to boost the reasoning capabilities of large language models (LLMs). Among various methods, the verify-and-improve paradigm stands out for enabling dynamic solution…

Table Question Answering (TableQA) enables natural language interaction with structured tabular data. However, existing large language model (LLM) approaches face critical limitations: context length constraints that restrict data handling…

Large Language Models (LLMs) have emerged as powerful tools for accelerating scientific discovery, yet their static knowledge and hallucination issues hinder autonomous research applications. Recent advances integrate LLMs into agentic…

Auto-regressive models (ARMs) have established a dominant paradigm in language modeling. However, their strictly sequential decoding paradigm imposes fundamental constraints on both inference efficiency and modeling flexibility. To address…