Related papers: Dynamic Attentional Context Scoping: Agent-Trigger…

This paper studies fully decentralized cooperative multi-agent reinforcement learning, where each agent solely observes the states, its local actions, and the shared rewards. The inability to access other agents' actions often leads to…

Long-horizon tasks that require sustained reasoning and multiple tool interactions remain challenging for LLM agents: small errors compound across steps, and even state-of-the-art models often hallucinate or lose coherence. We identify…

Large Language Model (LLM) agents struggle with long-horizon software engineering tasks due to "Context Bloat." As interaction history grows, computational costs explode, latency increases, and reasoning capabilities degrade due to…

LLM-based multi-agent systems have demonstrated remarkable performance on complex tasks through collaborative reasoning. However, these systems tend to rapidly accumulate extremely long conversation histories during interaction. As…

Advanced Driver Assistance Systems (ADAS) increasingly rely on learning-based perception, yet safety-relevant failures often arise without component malfunction, driven instead by partial observability and semantic ambiguity in how risk is…

Despite the rapid progress of open-domain generation-based conversational agents, most deployed systems treat dialogue contexts as single-turns, while systems dealing with multi-turn contexts are less studied. There is a lack of a reliable…

Single-agent systems (SAS) have become the default pattern for LLM-driven scientific workflows, but routing planning, tool use, and synthesis through a single context window comes with a well-known cost: as tool specifications and…

Sensory inference under conditions of uncertainty is a major problem in both machine learning and computational neuroscience. An important but poorly understood aspect of sensory processing is the role of active sensing. Here, we present a…

Sensory inference under conditions of uncertainty is a major problem in both machine learning and computational neuroscience. An important but poorly understood aspect of sensory processing is the role of active sensing. Here, we present a…

Multi-agent systems (MAS) powered by large language models suffer from severe token inefficiency arising from two compounding sources: (i) unstructured parallel execution, where all agents activate simultaneously irrespective of input…

Long-context understanding is crucial for many NLP applications, yet transformers struggle with efficiency due to the quadratic complexity of self-attention. Sparse attention methods alleviate this cost but often impose static, predefined…

While training models and labeling data are resource-intensive, a wealth of pre-trained models and unlabeled data exists. To effectively utilize these resources, we present an approach to actively select pre-trained models while minimizing…

Complex, non-linear tasks challenge LLM-enhanced multi-agent systems (MAS) due to partial observability and suboptimal coordination. We propose Orchestrator, a novel MAS framework that leverages attention-inspired self-emergent coordination…

Large Language Models (LLMs) face computational inefficiencies and redundant processing when handling long context inputs, prompting a focus on compression techniques. While existing semantic vector-based compression methods achieve…

Communication and interaction among agents have been the subject of extensive investigation since many years. Commitment-based communication, where communicating agents are seen as a debtor agent who is committed to a creditor agent to…

Multi-Agent Discussion (MAD) has garnered increasing attention very recently, where multiple LLM instances collaboratively solve problems via structured discussion. However, we find that current MAD methods easily suffer from discussion…

Dynamic Algorithm Configuration (DAC) addresses the challenge of dynamically setting hyperparameters of an algorithm for a diverse set of instances rather than focusing solely on individual tasks. Agents trained with Deep Reinforcement…

Contextual-LAS (CLAS) has been shown effective in improving Automatic Speech Recognition (ASR) of rare words. It relies on phrase-level contextual modeling and attention-based relevance scoring without explicit contextual constraint which…

Active search refers to the problem of efficiently locating targets in an unknown environment by actively making data-collection decisions, and has many applications including detecting gas leaks, radiation sources or human survivors of…

Research interest in autonomous agents is on the rise as an emerging topic. The notable achievements of Large Language Models (LLMs) have demonstrated the considerable potential to attain human-like intelligence in autonomous agents.…