Related papers: TAPE: Tool-Guided Adaptive Planning and Constraine…

Diffusion models achieve strong generative performance but remain slow at inference due to the need for repeated full-model denoising passes. We present Token-Adaptive Predictor (TAP), a training-free, probe-driven framework that adaptively…

Retrieval-augmented generation (RAG) has been extensively employed to mitigate hallucinations in large language models (LLMs). However, existing methods for multi-hop reasoning tasks often lack global planning, increasing the risk of…

Current robots are capable of computing plans to accomplish complex tasks. However, real-world environments are inherently open and dynamic, and unforeseen situations frequently arise during plan execution, such as jamming doors and fallen…

This paper proposes a novel planning framework to handle a multi-agent pathfinding problem under team-connected communication constraint, where all agents must have a connected communication channel to the rest of the team during their…

Recent advances in large language models (LLMs) have popularized test-time scaling, where models generate additional reasoning tokens before producing final answers. These approaches have demonstrated significant performance improvements on…

Pre-trained large language models (LLMs) capture procedural knowledge about the world. Recent work has leveraged LLM's ability to generate abstract plans to simplify challenging control tasks, either by action scoring, or action modeling…

Large language models (LLMs) exhibit failure modes on seemingly trivial tasks. We propose a formalisation of LLM interaction using a deterministic multi-tape Turing machine, where each tape represents a distinct component: input characters,…

Ensembling large language models (LLMs) can effectively combine diverse strengths of different models, offering a promising approach to enhance performance across various tasks. However, existing methods typically rely on fixed weighting…

Large Language Models (LLMs) have demonstrated exceptional abilities in reasoning for task planning. However, challenges remain under-explored for parallel schedules. This paper introduces a novel paradigm, plan-over-graph, in which the…

Out-of-distribution generalization in reinforcement learning is hard to diagnose when benchmark shifts mix dynamics, observations, goals, and rewards. We address this with Tape, a controlled benchmark that isolates latent rule-shift in…

Large language model (LLM) agents have shown increasing promise for collaborative task completion. However, existing multi-agent frameworks often rely on static workflows, fixed roles, and limited inter-agent communication, reducing their…

We address the challenge of multi-agent cooperation, where agents achieve a common goal by cooperating with decentralized agents under complex partial observations. Existing cooperative agent systems often struggle with efficiently…

Large Language Model-based agents have garnered significant attention and are becoming increasingly popular. Furthermore, planning ability is a crucial component of an LLM-based agent, which generally entails achieving a desired goal from…

Autonomous agents, which perceive environments and take actions to achieve goals, have become increasingly feasible with the advancements in large language models (LLMs). However, current powerful agents often depend on sophisticated prompt…

Agents aspire to eliminate the need for task-specific prompt crafting through autonomous reason-act-observe loops. Still, they are commonly instructed to follow a task-specific plan for guidance, e.g., to resolve software issues following…

Vision-language-action (VLA) models are effective as end-to-end motion planners, but can be brittle when evaluated in closed-loop settings due to being trained under traditional imitation learning framework. Existing closed-loop supervision…

In this paper, we introduce a multi-robot system that integrates mapping, localization, and task and motion planning (TAMP) enabled by 3D scene graphs to execute complex instructions expressed in natural language. Our system builds a shared…

Large Language Models (LLMs) often do not perform well on queries that require the aggregation of information across texts. To better evaluate this setting and facilitate modeling efforts, we introduce TACT - Text And Calculations through…

This paper addresses the limitations of a single agent in task decomposition and collaboration during complex task execution, and proposes a multi-agent architecture for modular task decomposition and dynamic collaboration based on large…

Language Agent could be endowed with different mechanisms for autonomous task accomplishment. Current agents typically rely on fixed mechanisms or a set of mechanisms activated in a predefined order, limiting their adaptation to varied…