Related papers: Cross-Modal Memory Compression for Efficient Multi…

Recent advances in large language models (LLMs) enable agentic systems trained with reinforcement learning (RL) over multi-turn interaction trajectories, but practical deployment is bottlenecked by rapidly growing textual histories that…

Long-horizon agentic reasoning necessitates effectively compressing growing interaction histories into a limited context window. Most existing memory systems serialize history as text, where token-level cost is uniform and scales linearly…

Multi-Agent Debate has emerged as a promising framework for improving the reasoning quality of large language models through iterative inter-agent communication. However, broadcasting all agent messages at every round introduces noise and…

Autonomous LLM agents increasingly operate in long-horizon, interactive settings where success depends on reusing experience accumulated over extended histories. However, existing agent memory systems are fundamentally constrained by…

Large language models (LLMs) have recently demonstrated impressive capabilities in reasoning tasks. Currently, mainstream LLM reasoning frameworks predominantly focus on scaling up inference-time sampling to enhance performance. In…

Multi-agent debate has proven effective in improving large language models quality for reasoning and factuality tasks. While various role-playing strategies in multi-agent debates have been explored, in terms of the communication among…

In recent years, Large Language Models (LLMs) have demonstrated remarkable capabilities across diverse NLP tasks. Extensive research has explored how to enhance the logical reasoning abilities such as Chain-of-Thought, Chain-of-Thought with…

Retrieval-Augmented Generation (RAG) has emerged as a promising paradigm for improving the timeliness of knowledge updates and the factual accuracy of large language models. However, incorporating a large volume of retrieved documents…

The quadratic complexity of the attention module makes it gradually become the bulk of compute in Transformer-based LLMs during generation. Moreover, the excessive key-value cache that arises when dealing with long inputs also brings severe…

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…

Optimization modeling underpins real-world decision-making in logistics, manufacturing, energy, and public services, but reliably solving such problems from natural-language requirements remains challenging for current large language models…

Large Language Models (LLMs) face significant challenges in long-context processing, including quadratic computational costs, information forgetting, and the context fragmentation inherent in retrieval-augmented generation (RAG). We propose…

This paper presents a pilot study aimed at introducing multi-agent debate into multimodal reasoning. The study addresses two key challenges: the trivialization of opinions resulting from excessive summarization and the diversion of focus…

Over the recent twenty years, argumentation has received considerable attention in the fields of knowledge representation, reasoning, and multi-agent systems. However, argumentation in dynamic multi-agent systems encounters the problem of…

Large Language Models (LLMs) have shown remarkable reasoning capabilities in mathematical and scientific tasks. To enhance complex reasoning, multi-agent systems have been proposed to harness the collective intelligence of LLM agents.…

Unified models aim to support both understanding and generation by encoding images into discrete tokens and processing them alongside text within a single autoregressive framework. This unified design offers architectural simplicity and…

Multi-Agent Debate (MAD) is a collaborative framework in which multiple agents iteratively refine solutions through the generation of reasoning and alternating critique cycles. Current work primarily optimizes intra-round topologies and…

Long chains of thought (Long CoTs) are widely employed in multimodal reasoning models to tackle complex tasks by capturing detailed visual information. However, these Long CoTs are often excessively lengthy and contain redundant reasoning…

To tackle long-context reasoning tasks without the quadratic complexity of standard attention mechanisms, approaches based on agent memory have emerged, which typically maintain a dynamically updated memory when linearly processing document…

DeepSeek-OCR shows that rendered text can be reconstructed from a small number of vision tokens, sparking excitement about using vision as a compression medium for long textual contexts. But this pipeline requires rendering token embeddings…