Related papers: Budget-Aware Agentic Routing via Boundary-Guided T…
Autonomous driving has made significant strides through data-driven techniques, achieving robust performance in standardized tasks. However, existing methods frequently overlook user-specific preferences, offering limited scope for…
Recent studies have uncovered the potential of Large Language Models (LLMs) in addressing complex sequential decision-making tasks through the provision of high-level instructions. However, LLM-based agents lack specialization in tackling…
The rapid advancement of large language models (LLMs) and domain-specific AI agents has greatly expanded the ecosystem of AI-powered services. User queries, however, are highly diverse and often span multiple domains and task types,…
This position paper argues that agentic AI systems should be designed and evaluated as \emph{marginal token allocation economies} rather than as text generators priced by the unit. We follow a single request -- a developer asking a coding…
Despite rapid development, large language models (LLMs) still encounter challenges in multi-turn decision-making tasks (i.e., agent tasks) like web shopping and browser navigation, which require making a sequence of intelligent decisions…
We propose a novel adaptive approximation approach for test-time resource-constrained prediction. Given an input instance at test-time, a gating function identifies a prediction model for the input among a collection of models. Our…
Safe reinforcement learning (RL) agents accomplish given tasks while adhering to specific constraints. Employing constraints expressed via easily-understandable human language offers considerable potential for real-world applications due to…
Agentic search requires large language models (LLMs) to perform multi-step search to solve complex information-seeking tasks, imposing unique challenges on their reasoning capabilities. However, what constitutes effective reasoning for…
Skill routing is an important component in large-scale conversational systems. In contrast to traditional rule-based skill routing, state-of-the-art systems use a model-based approach to enable natural conversations. To provide supervision…
Large language model (LLM) agents learn by interacting with environments, but long-horizon training remains fundamentally bottlenecked by sparse and delayed rewards. Existing methods typically address this challenge through post-hoc credit…
We investigated Agentic RL with large language models on the \textsc{TravelPlanner} benchmark. Our approach, \textsc{Planner-R1}, achieved a \textbf{56.9\%} final-pass rate with only 180 training queries, a $2.7\times$ improvement over…
Proactive large language model (LLM) agents aim to actively plan, query, and interact over multiple turns, enabling efficient task completion beyond passive instruction following and making them essential for real-world, user-centric…
Coordinating multiple autonomous agents in shared environments under decentralized conditions is a long-standing challenge in robotics and artificial intelligence. This work addresses the problem of decentralized goal assignment for…
Multimodal large language models (MLLMs) have advanced rapidly, yet heterogeneity in architecture, alignment strategies, and efficiency means that no single model is uniformly superior across tasks. In practical deployments, workloads span…
Large Language Models (LLMs) have achieved significant advances in reasoning tasks. A key approach is tree-based search with verifiers, which expand candidate reasoning paths and use reward models to guide pruning and selection. Although…
Mobile agentic AI is extending autonomous capabilities to resource-constrained platforms such as edge robots and unmanned aerial vehicles (UAVs), where strict size, weight, power, and cost (SWAP-C) constraints and intermittent wireless…
Large Language Model (LLM) agents represent a promising shift in human-AI interaction, moving beyond passive prompt-response systems to autonomous agents capable of reasoning, planning, and goal-directed action. While LLM agents are…
The availability of a wide range of large language models (LLMs) embedded in various agentic systems has significantly increased the potential of model selection strategies to improve the cost-performance tradeoff. Existing strategies…
Stepwise model routing improves the efficiency of Large Reasoning Models (LRMs) by assigning each reasoning step to a suitable model. Recent methods formulate routing as a sequential decision process and train the router with reinforcement…
Training large language model agents on tasks at the frontier of their capabilities is key to unlocking advanced reasoning. We introduce a data synthesis approach inspired by the educational theory of the Zone of Proximal Development (ZPD),…