Related papers: Constructing coherent spatial memory in LLM agents…

Mechanistic interpretability aims to reverse-engineer transformer computations by identifying causal circuits through activation patching. However, scaling these interventions across diverse prompts and task families produces…

Incremental learning is a machine learning approach that involves training a model on a sequence of tasks, rather than all tasks at once. This ability to learn incrementally from a stream of tasks is crucial for many real-world…

Prompting LLMs with bug-related context (e.g., error messages, stack traces) improves automated program repair, but many bugs still remain unresolved. In real-world projects, developers often rely on broader repository and project-level…

Dynamic scenes contain intricate spatio-temporal information, crucial for mobile robots, UAVs, and autonomous driving systems to make informed decisions. Parsing these scenes into semantic triplets <Subject-Predicate-Object> for accurate…

Visual navigation typically assumes the existence of at least one obstacle-free path between start and goal, which must be discovered/planned by the robot. However, in real-world scenarios, such as home environments and warehouses, clutter…

How do LLMs learn in-context? Is it by pattern-matching recent tokens, or by inferring latent structure? We probe this question using a toy graph random-walk across two competing graph structures. This task's answer is, in principle,…

Complex tasks are increasingly delegated to ensembles of specialized LLM-based agents that reason, communicate, and coordinate actions-both among themselves and through interactions with external tools, APIs, and databases. While persistent…

Coordinating multi-robot systems (MRS) to search in unknown environments is particularly challenging for tasks that require semantic reasoning beyond geometric exploration. Classical coordination strategies rely on frontier coverage or…

Large Language Models (LLMs) have shown strong capabilities in solving problems across domains, including graph-related tasks traditionally addressed by symbolic or algorithmic methods. In this work, we present a framework for structured…

Large language model (LLM)-based systems are becoming increasingly popular for solving tasks by constructing executable workflows that interleave LLM calls, information retrieval, tool use, code execution, memory updates, and verification.…

Current interactive LLM agents rely on goal-conditioned stepwise planning, where environmental understanding is acquired reactively during execution rather than established beforehand. This temporal inversion leads to Delayed Environmental…

The ability to perform effective planning is crucial for building an instruction-following agent. When navigating through a new environment, an agent is challenged with (1) connecting the natural language instructions with its progressively…

LLM-generated drafts often contain subtle factual or logical errors, yet prior work shows that models struggle to reliably integrate multi-turn feedback aimed at fixing them. We propose in-place feedback, an interaction paradigm in which…

Pre-explored Semantic Maps, constructed through prior exploration using visual language models (VLMs), have proven effective as foundational elements for training-free robotic applications. However, existing approaches assume the map's…

LLM routing has achieved promising results in integrating the strengths of diverse models while balancing efficiency and performance. However, to support more realistic and challenging applications, routing must extend into agentic LLM…

A critical component to enabling intelligent reasoning in partially observable environments is memory. Despite this importance, Deep Reinforcement Learning (DRL) agents have so far used relatively simple memory architectures, with the main…

Mobile robots are often tasked with repeatedly navigating through an environment whose traversability changes over time. These changes may exhibit some hidden structure, which can be learned. Many studies consider reactive algorithms for…

LLM-based search agents often concatenate the full interaction history into the context, producing long and noisy inputs, and increasing compute cost and GPU memory overhead. To address this issue, we propose MemSearcher, an agent framework…

Large Language Models (LLM) have emerged as a tool for robots to generate task plans using common sense reasoning. For the LLM to generate actionable plans, scene context must be provided, often through a map. Recent works have shifted from…

Exploration and goal-directed navigation in unknown layouts are central to inspection, logistics, and search-and-rescue. We ask whether large language models (LLMs) can function as \emph{text-only} controllers under partial observability --…