The paper proposes TRACE, a trajectory risk-aware compression method, to effectively aggregate sparse and delayed safety evidence across long agent trajectories, achieving state-of-the-art performance…

The paper analyzes the failure modes of aggressive 2-bit quantization in large reasoning models, proposing lightweight controls like FP16 planning and loop rescue to restore accuracy and achieve pract…

The paper proposes HTP, a novel framework that leverages Large Language Models (LLMs) to first generate abstract travel patterns and then synthesize realistic GPS points, significantly improving traje…

This paper demonstrates that reasoning-enabled Vision-Language-Action (VLA) models for autonomous driving are highly vulnerable to realistic input perturbations, significantly compromising both reason…

This paper introduces MCTS-Guided Group Relative Policy Optimization (M-GRPO) to enhance LLM spatial reasoning by improving the decomposition of complex tasks into optimal sub-tasks.

The paper proposes a unified framework to evaluate how different types of memory transfer benefit multi-trajectory inference for tool-use LLM agents, finding that the optimal memory method depends cri…

The paper introduces Trajectory-aware OPD (TOPD), a method that uses near-future trajectory information to improve On-Policy Distillation by accurately identifying and guiding true reasoning divergenc…

The paper investigates how LLMs allocate their internal computational depth during multi-turn agentic planning, finding that agents progressively recruit deeper layers and shift toward corrective upda…

The paper proposes a dual-interventional framework to characterize how linguistic structures and contextual cues influence LLMs' spatial reasoning for navigation, finding that topological information…

The paper introduces VeriTrip, a new verifiable benchmark that evaluates travel planning agents' ability to perform evidence-grounded reasoning over complex, unstructured, and multimodal web data, rev…

The paper demonstrates that extended pure neural reasoning fails on complex, deterministic state-tracking tasks beyond a certain 'Deterministic Horizon,' necessitating the integration of external tool…

The paper introduces MeRa, a metric-space bias module, demonstrating that latent reasoning only improves spatial prediction when it is explicitly grounded in the underlying metric space.

The paper formally addresses the challenging question of cross-domain transferability of latent predictive models by proposing a structured framework that quantifies the relationship between source an…

Lodestar is a novel online learning-based request routing system that significantly improves LLM inference efficiency by dynamically assigning incoming requests to the optimal GPU instance to minimize…

TempoVLA is a novel Vision-Language-Action model that enables controllable execution speed for robot manipulation by explicitly conditioning the policy on the desired speed.

The paper introduces Sparse Memory-Efficient Training (SMET), a method that stabilizes and optimizes Dynamic Sparse Training (DST) for large language models, enabling stable and memory-efficient spars…

The paper argues that current embodied planning benchmarks prioritize superficial language prediction over true physical reasoning, introducing new benchmarks and a large-scale dataset to demonstrate…

The paper introduces Logit-aware Final-block Quantization (LFQ), an enhancement to block-wise quantization that quantizes the final Transformer block using a cross-entropy loss to significantly boost…

The paper proposes Continuous Reasoning for Vision-Language-Action (VLA) models, arguing that effective reasoning must be a shared, verifiable internal latent space rather than discrete text tokens, l…