Related papers: Latent-DARM: Bridging Discrete Diffusion And Autor…

Retrieval-Augmented Generation (RAG) lifts the factuality of Large Language Models (LLMs) by injecting external knowledge, yet it falls short on problems that demand multi-step inference; conversely, purely reasoning-oriented approaches…

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…

Large language model (LLM) agents often rely on long sequences of low-level textual actions, resulting in large effective decision horizons and high inference cost. While prior work has focused on improving inference efficiency through…

External memory is a key component of modern large language model (LLM) systems, enabling long-term interaction and personalization. Despite its importance, memory management is still largely driven by hand-designed heuristics, offering…

Deep research agents, powered by Large Language Models (LLMs), are rapidly advancing; yet, their performance often plateaus when generating complex, long-form research reports using generic test-time scaling algorithms. Drawing inspiration…

Multi-agent systems (MAS) powered by large language models (LLMs) hold significant promise for solving complex decision-making tasks. However, the core process of collaborative decision-making (CDM) within these systems remains…

Multi-robot task planning requires decomposing natural-language instructions into executable actions for heterogeneous robot teams. Conventional Planning Domain Definition Language (PDDL) planners provide rigorous guarantees but struggle to…

Discrete Diffusion Language Models (DLMs) offer a promising non-autoregressive alternative for text generation, yet effective mechanisms for inference-time control remain relatively underexplored. Existing approaches include sampling-level…

Despite the significant improvements achieved by large language models (LLMs) in English reasoning tasks, these models continue to struggle with multilingual reasoning. Recent studies leverage a full-parameter and two-stage training…

Autoregressive models (ARMs) are hindered by slow sequential inference. While masked diffusion models (MDMs) offer a parallel alternative, they suffer from critical drawbacks: high computational overhead from precluding Key-Value (KV)…

Large language models (LLMs) have shown impressive capabilities, but still struggle with complex reasoning tasks requiring multiple steps. While prompt-based methods like Chain-of-Thought (CoT) can improve LLM reasoning at inference time,…

Multi-agent debate (MAD) is an emerging approach to improving the reasoning capabilities of large language models (LLMs). Existing MAD methods rely on multiple rounds of interaction among agents to reach consensus, and the final output is…

Large Language Models (LLMs) exhibit substantial parameter redundancy, particularly in Feed-Forward Networks (FFNs). Existing pruning methods suffer from two primary limitations. First, reliance on dataset-specific calibration introduces…

While language reasoning models excel in many tasks, visual reasoning remains challenging for current large multimodal models (LMMs). As a result, most LMMs default to verbalizing perceptual content into text, a strong limitation for tasks…

This study proposes a multi-agent language framework that enables continual strategy evolution without fine-tuning the language model's parameters. The core idea is to liberate the latent vectors of abstract concepts from traditional static…

The rise of multi-agent systems powered by large language models (LLMs) and specialized reasoning agents exposes fundamental limitations in today's data management architectures. Traditional databases and data fabrics were designed for…

Watermarking (WM) is a critical mechanism for detecting and attributing AI-generated content. Current WM methods for Large Language Models (LLMs) are predominantly tailored for autoregressive (AR) models: They rely on tokens being generated…

The integration of Large Language Models (LLMs) into healthcare is constrained by knowledge limitations, hallucinations, and a disconnect from Evidence-Based Medicine (EBM). While Retrieval-Augmented Generation (RAG) offers a solution,…

Recent advances in large language models (LLMs) have demonstrated the power of reasoning through self-generated chains of thought. Multiple reasoning agents can collaborate to raise joint reasoning quality above individual outcomes.…

While Diffusion Large Language Models (dLLMs) have emerged as a promising non-autoregressive paradigm comparable to autoregressive (AR) models, their faithfulness, specifically regarding hallucination, remains largely underexplored. To…