Related papers: Context, Reasoning, and Hierarchy: A Cost-Performa…

Large language models (LLMs), while promising, face criticisms for biases, hallucinations, and a lack of reasoning capability. This paper introduces SocraSynth, a multi-LLM agent reasoning platform developed to mitigate these issues.…

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…

Conversational assistants powered by large language models (LLMs) excel at tool-use tasks but struggle with adhering to complex, business-specific rules. While models can reason over business rules provided in context, including all…

Vision-language models (VLMs) have shown impressive capabilities in perceptual tasks, yet they degrade in complex multi-hop reasoning under multiplayer game settings with imperfect and deceptive information. In this paper, we study a…

Designing high-performance system heuristics is a creative, iterative process requiring experts to form hypotheses and execute multi-step conceptual shifts. While Large Language Models (LLMs) show promise in automating this loop, they…

Large Language Models (LLMs) have recently demonstrated impressive action sequence prediction capabilities but often struggle with dynamic, long-horizon tasks such as real-time strategic games. In a game such as StarCraftII (SC2), agents…

Coding agents accumulate extensive context during long-running tasks, yet fixed context windows force practitioners to choose between truncation and task failure. While numerous memory condensation strategies have been proposed, from simple…

We present a novel approach for efficient and reliable goal-directed long-horizon navigation for a multi-robot team in a structured, unknown environment by predicting statistics of unknown space. Building on recent work in…

Recent advances in large-scale language models (LLMs) have made multi-agent architectures attractive for challenging reasoning tasks. However, many existing systems rely on stochastic routing or ad-hoc heuristics, making their behavior…

Multi-agent systems extend large language models (LLMs) by decomposing tasks among specialized agents, but their distributed decision process creates new attack surfaces. We identify semantic hijacking, an attack in which harmful requests…

Despite the promise of Retrieval-Augmented Generation in grounding Multimodal Large Language Models with external knowledge, the transition to extensive contexts often leads to significant attention dilution and reasoning hallucinations.…

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…

Large reasoning models achieve remarkable performance through extensive chain-of-thought generation, yet they suffer from a critical inefficiency: applying uniformly extensive reasoning regardless of problem complexity. We present…

We introduce Lossless Context Management (LCM), a deterministic architecture for LLM memory that outperforms Claude Code on long-context tasks. When benchmarked using Opus 4.6, our LCM-augmented coding agent, Volt, achieves higher scores…

Service system performance depends on how participants respond to design choices, but modeling these responses is hard due to the complexity of human behavior. We introduce an LLM-powered multi-agent simulation (LLM-MAS) framework for…

The ability of Large Language Models (LLMs) to extract context from natural language problem descriptions naturally raises questions about their suitability in autonomous decision-making settings. This paper studies the behaviour of these…

Mathematical reasoning is a fundamental capability for large language models (LLMs), yet achieving high performance in this domain remains a significant challenge. The auto-regressive generation process often makes LLMs susceptible to…

Multimodal Large Language Models (MLLMs) have empowered embodied agents with remarkable capabilities in planning and reasoning. However, when facing ambiguous natural language instructions (e.g., "fetch the tool" in a cluttered room),…

As large language models (LLMs) are increasingly deployed as autonomous agents, understanding their cooperation and social mechanisms is becoming increasingly important. In particular, how LLMs balance self-interest and collective…

The dominant paradigm for building LLM based agents is the Agent Loop, an iterative cycle where a single language model decides what to do next by reading an ever growing context window. This paradigm has three structural weaknesses:…