arXiv AI By Dimitris Panagopoulos, Adolfo Perrusqu\'ia, Yang Xing, Weisi Guo

Model-Free Runtime Measurement of Task-Relevant Information

Read the original on arXiv AI →

The paper introduces Acquisition‑State Telemetry (AST), a model‑free framework that monitors ongoing information gathering in autonomous systems. AST maps raw observations to task‑resolution coordinates and uses a fixed causal monitor to emit two real‑time signals: one indicating prospective progress on unresolved requirements, and another quantifying informational friction when new evidence yields little gain. Experiments across eight varied domains—ranging from search and rescue dialogue to robotic manipulation—show that the friction signal can distinguish unproductive stagnation from purposeful exploration and that penalizing friction in reinforcement learning leads to higher mission success under early‑termination constraints.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

arXiv AI
Sep 30

Seek Before You Move: Evidence Seeking for Progress Grounding in Vision-Language Navigation

SeekVLN is a new framework for Vision‑Language Navigation that addresses the problem of agents acting on insufficient evidence, termed Progress Myopia. It combines semantic progress reasoning with active evidence seeking, trained first with Future‑guided Reverse Generation to augment expert trajectories, and then refined via Counterfactual Contrastive Policy Optimization to reward beneficial seeking actions. Experiments on simulated benchmarks show significant gains, improving success rates by 12.7% on R2R‑CE and 7.5% on RxR‑CE, and real‑world tests demonstrate human‑like evidence‑seeking behavior.

By Zhimin Wang, Meiyuan Zhu, Duo Wu, Linjia Kang, Yajun Wang, Yuan Ni, Xiaohang Wang, Tianlu Pan, Jingyan Jiang, Yaowei Wang, Zhi Wang
arXiv AI
Oct 12

OGPO: Offline Goal-conditioned Policy Optimization for Recoverable Vision-Language-Action Models

OGPO is an Offline Goal‑conditioned Policy Optimization framework designed to improve Vision‑Language‑Action (VLA) models for robotic manipulation. It replaces traditional step‑wise action imitation with adaptive relabeling of trajectories using semantic key states and goal‑conditioned rewards, enabling policies to reach task‑progress states even from off‑demonstration states. Experiments on LIBERO, MetaWorld, LIBERO‑Plus, and the proposed LIBERO‑ReAct benchmark show that OGPO consistently outperforms standard supervised fine‑tuning in terms of robustness and recoverability under distribution shifts.

By Xule Gao, Xi Wang, Zehua Zang, Rui Wang, Changwen Zheng, Chuxiong Sun
arXiv AI
Aug 11

SCOUT: Self-Checking and Recovery-Aware Tool-Thought Agents for Ultra-Long Egocentric Video Reasoning

arXiv:2608. 07959v1 Announce Type: new Abstract: Ultra-long egocentric video understanding requires reasoning over temporally sparse evidence distributed across hours or days, challenging current multimodal models with limited context and the grounding of key video segments.

By Keyang Zhong, Kuo Wang, Peng Liu, Quanlong Zheng, Junlin Xie, Zhijia Liang, Yanhao Zhang, Guanbin Li
Hugging Face Trending Papers
Sep 10

2AM: Grounding Agent-Side Memory as Guidance for Steerable Action Models in Long-Horizon Manipulation

The paper introduces 2AM, a system that keeps task memory solely within a multimodal Agent while using a single RGB‑based, stateless Action Model to execute motions. By compiling interaction history into subtask language and optional 2D grasp/place/move hints, the Agent steers the Action Model, which is trained to tolerate imperfect guidance through dropout, noise, and jitter. On the LIBERO‑Mem benchmark, 2AM achieves 76.3% average completion without depth, geometry, or planners, vastly outperforming the best baseline.

arXiv AI
Jul 7

Cortex: A Bidirectionally Aligned Embodied Agent Framework for Long-horizon Manipulation

arXiv:2607. 05377v1 Announce Type: cross Abstract: While recent Vision-Language-Action (VLA) models show promise toward generalist manipulation policies, they struggle with long-horizon tasks due to their Markovian nature-relying solely on current observations.

By Jiaqi Peng, Xiqian Yu, Delin Feng, Yuqiang Yang, Wenzhe Cai, Jing Xiong, Ganlin Yang, Jinliang Zheng, Jiafei Cao, Xueyuan Wei, Jiangmiao Pang, Yuan Shen, Tai Wang