Related papers: STAR-P\'olyaMath: Multi-Agent Reasoning under Pers…
Recent progress in multimodal reasoning has enabled agents that interpret imagery, connect it with language, and execute structured analytical tasks. Extending these capabilities to remote sensing remains challenging, as models must reason…
AI has proven highly successful at urban planning analysis -- learning patterns from data to predict future conditions. The next frontier is AI-assisted decision-making: agents that recommend sites, allocate resources, and evaluate…
Large Language Models (LLMs) often struggle with computational efficiency and error propagation in multi-step reasoning tasks. While recent advancements on prompting and post-training have enabled LLMs to perform step-wise reasoning, they…
The rise of Large Reasoning Models (LRMs) signifies a paradigm shift toward advanced computational reasoning. Yet, this progress disrupts traditional agent frameworks, traditionally anchored by execution-oriented Large Language Models…
Large language models (LLMs) face persistent challenges when handling long-context tasks, most notably the lost in the middle issue, where information located in the middle of a long input tends to be underutilized. Some existing methods…
The advancement of artificial intelligence toward agentic science is currently bottlenecked by the challenge of ultra-long-horizon autonomy, the ability to sustain strategic coherence and iterative correction over experimental cycles…
We introduce AgenticSimLaw, a role-structured, multi-agent debate framework that provides transparent and controllable test-time reasoning for high-stakes tabular decision-making tasks. Unlike black-box approaches, our courtroom-style…
Software Engineering (SE) agents have shown promising abilities in supporting various SE tasks. Current SE agents remain fundamentally reactive, making decisions mainly based on conversation history and the most recent response. However,…
As an agent-level reasoning and coordination paradigm, Multi-Agent Debate (MAD) orchestrates multiple agents through structured debate to improve answer quality and support complex reasoning. However, existing research on MAD suffers from…
Clinical decision-making requires nuanced reasoning over heterogeneous evidence and traceable justifications. While recent LLM multi-agent systems (MAS) show promise, they largely optimise for outcome accuracy while overlooking…
Despite recent advances in AI, the development of systems capable of executing complex, multi-step reasoning tasks involving multiple tools remains a significant challenge. Current benchmarks fall short in capturing the real-world…
Multi-agent systems powered by large language models have demonstrated remarkable capabilities across diverse domains, yet existing automated design approaches seek monolithic solutions that fail to adapt resource allocation based on query…
Large reasoning models have demonstrated strong problem-solving abilities, yet real-world tasks often require external tools and long-horizon interactions. Existing agent frameworks typically follow predefined workflows, which limit…
We introduce QwenLong-L1.5, a model that achieves superior long-context reasoning capabilities through systematic post-training innovations. The key technical breakthroughs of QwenLong-L1.5 are as follows: (1) Long-Context Data Synthesis…
Large language models (LLMs) demonstrate impressive reasoning abilities, but translating reasoning into actions in the real world remains challenging. In particular, it remains unclear how to complete a given task provably within a minimum…
Chain-of-thought prompting has popularized step-by-step reasoning in large language models, yet model performance still degrades as problem complexity and context length grow. By decomposing difficult tasks with long contexts into shorter,…
Large Language Models (LLMs) have been successful in mathematical reasoning tasks such as formal theorem proving when integrated with interactive proof assistants like Lean. Existing approaches involve training or fine-tuning an LLM on a…
LLM-based multi-agent systems (MAS) have emerged as an effective paradigm for complex and long-horizon tasks. However, in real-world tasks, MAS often exhibit various failures during execution and such failures are difficult to eliminate…
We envision a continuous collaborative learning system where groups of LLM agents work together to solve reasoning problems, drawing on memory they collectively build to improve performance as they gain experience. This work establishes the…
Large language models have demonstrated remarkable capabilities across diverse reasoning tasks, yet their performance on algorithmic reasoning remains limited. To handle this limitation, we propose PRIME (Policy-Reinforced Iterative…