arXiv subjects

Yixin Xiao

Publications and source records attributed to Yixin Xiao.

7 recordsLinked to original sources

arXiv2026

StageGuard: Learning Stage Transitions for Long-Horizon Robot Tasks via Agentic Distillation

Hierarchical planning frameworks combine skills from multiple robot control policies for long-horizon task execution, where determining when to terminate the current skill and advance to the next subtask is essential. Existing approaches often rely on pre-designed completion signal checkers that are hard to obtain in real-world execution. Large-scale vision-language models (VLMs) offer strong reasoning capabilities, but their decision boundaries are not inherently aligned with task completion criteria, while cloud deployment and lengthy reasoning introduce substantial latency, limiting real-time monitoring. We propose StageGuard, an agentic distillation framework for accurate and efficient stage-transition decisions. StageGuard combines teacher-model reasoning with demonstration trajectories to generate structured explanations of subtask completion and policy switching. A lightweight student VLM uses these explanations to generate compact self-explanations, which are used for supervised fine-tuning. We evaluate stage-transition prediction on trajectories from two benchmarks and assess closed-loop task success through integration into hierarchical robot control on BEHAVIOR-1K, with further validation on real robots. Results show substantial improvements in stage-transition prediction while supporting efficient online monitoring.

cs.RO↗

arXiv2026

Mem2Ego: Empowering Vision-Language Models with Global-to-Ego Memory for Long-Horizon Embodied Navigation

Recent advancements in Large Language Models (LLMs) and Vision-Language Models (VLMs) have made them powerful tools in embodied navigation, enabling agents to leverage commonsense and spatial reasoning for efficient exploration in unfamiliar environments. Existing LLM-based approaches convert global memory, such as semantic or topological maps, into language descriptions to guide navigation. While this improves efficiency and reduces redundant exploration, the loss of geometric information in language-based representations hinders spatial reasoning, especially in intricate environments. To address this, VLM-based approaches directly process ego-centric visual inputs to select optimal directions for exploration. However, relying solely on a first-person perspective makes navigation a partially observed decision-making problem, leading to suboptimal decisions in complex environments. In this paper, we present a novel vision-language model (VLM)-based navigation framework that addresses these challenges by adaptively retrieving task-relevant cues from a global memory module and integrating them with the agent's egocentric observations. By dynamically aligning global contextual information with local perception, our approach enhances spatial reasoning and decision-making in long-horizon tasks. The proposed method surpasses previous state-of-the-art approaches by a significant margin on both the HSSD and HM3D benchmarks and demonstrates strong performance on a real robot.

cs.RO↗

arXiv2026

Non-Hermitian Skin Effect from Radiative Coupling in a Reciprocal Chiral Medium

We find that long-range radiative coupling through a passive reciprocal chiral medium produces an unusual non-Hermitian skin effect in a chain of electric dipoles. Although the system is reciprocal, the chirality generates polarization-dependent phase accumulation and attenuation, leading to degenerate pairs of skin modes localized at opposite boundaries. We find that the skin mode profile consists of an exponential contribution from an isolated complex-$β$ pole and a longer-range tail proportional to $1/[n(\ln n)^2]$, where $n$ is the distance from the occupied boundary measured in lattice sites. Finite-chain calculations show that part of the OBC spectrum contracts toward the Bloch spectrum, whereas the number of boundary-localized modes remains extensive.

cond-mat.other↗

arXiv2026

RoboHarness: Memory-Driven Orchestration of Heterogeneous Robot Policies for Long-Horizon Planning

Long-horizon robotic tasks require diverse capabilities that no single policy can reliably provide. Heterogeneous policies offer complementary strengths, but orchestrating them requires reasoning over uncertain capability boundaries and cross-policy distribution mismatch, which are largely overlooked by existing planning methods built on homogeneous, predefined skills with fixed applicability. We propose RoboHarness, a unified framework that encapsulates independently developed robot control systems as reusable agentic skills. Although instantiated in this work with VLAs, RL policies, and task-and-motion planning (TAMP) systems, RoboHarness is designed as a general framework compatible with a broader range of robot policies, such as navigation policies, model predictive controllers, and world-action models. RoboHarness uses multi-modal execution memory and online evidence to characterize policy capability boundaries for capability-aware decomposition and routing. To stabilize policy handoffs, its Memory Bridge retrieves execution trajectories associated with the next policy, estimates its in-distribution state region, and guides the robot toward that region without joint policy retraining. Extensive experiments on three public benchmarks, 500 customized tasks, and 135 real-robot experiments demonstrate effective capability-aware routing and stable policy orchestration, yielding substantial improvements in zero-shot long-horizon planning and out-of-distribution robustness.

cs.RO↗

arXiv2026

One Demo Is All It Takes: Planning Domain Derivation with LLMs from A Single Demonstration

Pre-trained large language models (LLMs) show promise for robotic task planning but often struggle to guarantee correctness in long-horizon problems. Task and motion planning (TAMP) addresses this by grounding symbolic plans in low-level execution, yet it relies heavily on manually engineered planning domains. To improve long-horizon planning reliability and reduce human intervention, we present Planning Domain Derivation with LLMs (PDDLLM), a framework that automatically induces symbolic predicates and actions directly from demonstration trajectories by combining LLM reasoning with physical simulation roll-outs. Unlike prior domain-inference methods that rely on partially predefined or language descriptions of planning domains, PDDLLM constructs domains without manual domain initialization and automatically integrates them with motion planners to produce executable plans, enhancing long-horizon planning automation. Across 1,200 tasks in nine environments, PDDLLM outperforms six LLM-based planning baselines, achieving at least 20\% higher success rates, reduced token costs, and successful deployment on multiple physical robot platforms.

cs.RO↗

arXiv2025

Unconventional topological edge states in one-dimensional gapless systems stemming from nonisolated hypersurface singularities

Topologically protected edge states have been extensively studied in systems characterized by the topological invariants in band gaps (also called line gaps). In this study, we unveil a whole new form of edge states that transcends the established paradigms of band-gap topology. In contrast to the traditional stable edge states in topological insulators with specific band gaps, the one-dimensional systems we investigate are inherently gapless with the Brillouin zones being mapped to the loops encircling hypersurface singularities in a higher-dimensional space with parity-time symmetry. These hypersurface singularities are nonisolated degeneracies embedded entirely on exceptional surfaces, rendering the energy gaps in our systems inevitably closed at the intersections of the Brillouin zone loop and the exceptional surfaces. Unexpectedly, such gapless systems still afford topologically protected edge states at system boundaries, challenging the conventional understanding based on band gaps. To elucidate the existence of these edge states in the absence of a band-gap-based invariant, we propose a theoretical framework based on eigen-frame rotation and deformation that incorporates non-Bloch band theory. Finally, we experimentally demonstrate this new form of topological edge states with nonreciprocal circuits for the first time. Our work constitutes a major advance that extends topological edge states from gapped phases to gapless phases, offering new insights into topological phenomena.

cond-mat.mes-hall↗

arXiv2022

Topological classification for intersection singularities of exceptional surfaces in pseudo-Hermitian systems

Exceptional points play a pivotal role in the topology of non-Hermitian systems, and significant advances have been made in classifying exceptional points and exploring the associated phenomena. Exceptional surfaces, which are hypersurfaces of exceptional degeneracies in parameter space, can support hypersurface singularities, such as cusps, intersections and swallowtail catastrophes. Here we topologically classify the intersection singularity of exceptional surfaces for a generic pseudo-Hermitian system with parity-time symmetry. By constructing the quotient space under equivalence relations of eigenstates, we reveal that the topology of such gapless structures can be described by a non-Abelian free group on three generators. Importantly, the classification predicts a new kind of non-Hermitian gapless topological phase and can systematically explain how the exceptional surfaces and their intersections evolve under perturbations with symmetries preserved. Our work opens a new pathway for designing systems with robust topological phases, and provides inspiration for applications such as sensing and lasing which can utilize the special properties inherent in exceptional surfaces and intersections.

cond-mat.mtrl-sci↗