相关论文: ProMAS: Proactive Error Forecasting for Multi-Agen…
Deploying large language model (LLM)-driven conversational agents in enterprise settings requires prompts that are simultaneously correct at launch and resilient to the non-deterministic behavioral drift that characterizes production LLM…
In reasoning tasks, even a minor error can cascade into inaccurate results, leading to suboptimal performance of large language models in such domains. Earlier fine-tuning approaches sought to mitigate this by leveraging more precise…
Fitting complex patterns in the training data, such as reasoning and commonsense, is a key challenge for language pre-training. According to recent studies and our empirical observations, one possible reason is that some easy-to-fit…
Advanced large language model agents typically adopt self-reflection for improving performance, where agents iteratively analyze past actions to correct errors. However, existing reflective approaches are inherently retrospective: agents…
Real-world dialogue usually unfolds as an infinite stream. It thus requires bounded-state memory mechanisms to operate within an infinite horizon. However, existing read-then-think memory is fundamentally misaligned with this setting, as it…
Recent advances in Large Language Models (LLMs) have catalyzed the development of multi-agent systems (MAS) for complex reasoning tasks. However, existing MAS typically rely on pre-defined or pre-compiled communication topologies, which…
Large Reasoning Models (LRMs) represent a breakthrough in AI problem-solving capabilities, but their effectiveness in interactive environments can be limited. This paper introduces and analyzes overthinking in LRMs. A phenomenon where…
Recent advances have shown that optimizing prompts for Large Language Models (LLMs) can significantly improve task performance, yet many optimization techniques rely on heuristics or manual exploration. We present LatentPrompt, a…
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…
We propose an extension to the OWASP Multi-Agentic System (MAS) Threat Modeling Guide, translating recent anticipatory research in multi-agent security (MASEC) into practical guidance for addressing challenges unique to large language model…
We present Context, the intelligence layer of the Magarshak Architecture, which replaces reactive query-response chatbots with proactive goal-directed agents that advance shared tasks without waiting for user prompts. The architecture rests…
This paper introduces PROTEUS, a fully automated system that produces data-driven hypotheses from raw data files. We apply PROTEUS to clinical proteogenomics, a field where effective downstream data analysis and hypothesis proposal is…
A critical limitation in large-scale multi-agent systems is the cascading of errors. And without intermediate verification, downstream agents exacerbate upstream inaccuracies, resulting in significant quality degradation. To bridge this…
We formulate and analyze a simplest Markov decision process model for intrusion tolerance problems, assuming that (i) each attack proceeds through one or more steps before the system's security fails, (ii) defensive responses that target…
Large Language Models (LLMs) have achieved remarkable reliability and advanced capabilities through extended test-time reasoning. However, extending these capabilities to Multi-modal Large Language Models (MLLMs) remains a significant…
Standard masked discrete diffusion models face limitations in reasoning tasks due to their inability to correct their own mistakes on the masking path. Since they rely on a fixed number of denoising steps, they are unable to adjust their…
The rapid emergence of new entities -- driven by cultural shifts, evolving trends, and personalized user data -- poses a significant challenge for existing Speech Large Language Models (Speech LLMs). While these models excel at general…
Large language models (LLMs) solve complex problems by generating multi-step reasoning traces. Yet these traces are typically analyzed from only one of two perspectives: the sequence of tokens across different reasoning steps in the…
The integration of large language models (LLMs) with external tools has significantly expanded the capabilities of AI agents. However, as the diversity of both LLMs and tools increases, selecting the optimal model-tool combination becomes a…
Multi-agent language systems are often built as hand-designed workflows, where agents are assigned semantic roles and communication protocols are specified in advance. We propose NeuroMAS, a method that first treats a multi-agent language…