Partial Observability

Follow this topic Ask about this topic

Recent momentum

-67%

5 papers in the last 28 days · 0.1% of indexed attention

Twelve weeks of publication activity for this topic as it is defined today.

Weekly history

Recent digests

What was published in this topic, kept on the site without email delivery.

Period ending 2026-09-21

2 new papers

A weekly snapshot of new work published in Partial Observability.

Period ending 2026-09-14

3 new papers

A weekly snapshot of new work published in Partial Observability.

Period ending 2026-09-07

3 new papers

A weekly snapshot of new work published in Partial Observability.

104 papers

Latest in Partial Observability

Browse all topics →

The Behavioral Credibility Trilemma: When Calibrated Autonomy Becomes Impossible
May 25, 2026Lauri Lovén, Nam Do, Hassan Mehmood +2Scalable Oversight Autonomy
When Does Adaptive Guidance Help? Belief-Aware Privileged Distillation for Autonomous Driving Under Partial Observability
May 24, 2026Mehmet HaklidirAutonomous Driving Partial Observability
Streaming Reinforcement Learning under Partial Observability with Real-Time Recurrent Learning
May 23, 2026Noah Farr, Aryaman Reddi, Carlo D'Eramo +1Deep Reinforcement Learning Learning-Augmented Algorithms
AI-Driven Adaptive Adversaries and the Erosion of Cryptographic Trust in Public Key Systems
May 23, 2026Petar RadanlievDiffie-Hellman Adversarial Training
Agentic CLEAR: Automating Multi-Level Evaluation of LLM Agents
May 21, 2026Asaf Yehudai, Lilach Eden, Michal Shmueli-ScheuerAgentic Evaluations Agentic Systems
Scaling Observation-aware Planning in Uncertain Domains
May 21, 2026Adrian Zvizdenco, Arthur Conrado Veiga Bosquetti, Alberto Lluch Lafuente +1Partially Observable Markov Decision Process Partial Observability
Short-Term-to-Long-Term Memory Transfer for Knowledge Graphs under Partial Observability
May 21, 2026Taewoon Kim, Vincent François-Lavet, Michael CochezHierarchical Graph Memory Temporal Knowledge Graphs
Learning Lifted Action Models from Traces with Minimal Information About Actions and States
May 18, 2026Jonas Gösgens, Niklas Jansen, Hector GeffnerPartial Observability Action Space
Action-Conditioned Risk Gating for Safety-Critical Control under Partial Observability
May 14, 2026Yushen Liu, Yin-Jen Chen, Ziyi Chen +4Belief Space Safety-Critical Scenarios
Vision-Based Runtime Monitoring under Varying Specifications using Semantic Latent Representations
May 13, 2026Bardh Hoxha, Oliver Schön, Hideki Okamoto +2Runtime Enforcement Partial Observability
Enabling Performant and Flexible Model-Internal Observability for LLM Inference
May 11, 2026Nengneng Yu, Sixian Xiong, Yibo Zhao +2LLM Inference Efficiency Inference Workloads
An Uncertainty-Aware Resilience Micro-Agent for Causal Observability in the Computing Continuum
May 11, 2026Suvi De Silva, Alfreds Lapkovskis, Alaa Saleh +2Tool Failures Causal Reasoning
Uncovering Hidden Systematics in Neural Network Models for High Energy Physics
May 8, 2026Lucie Flek, Philipp Alexander Jungs, Akbar Karimi +6High Energy Physics Partial Observability
From Pixels to Primitives: Scene Change Detection in 3D Gaussian Splatting
May 8, 2026Chamuditha Jayanga Galappaththige, Jason Lai, Timothy Patten +3Change Detection Gaussian Splatting
Beyond the Black Box: Interpretability of Agentic AI Tool Use
May 7, 2026Hariom Tatsat, Ariye ShaterMechanistic Interpretability Model Interpretability
Monitoring autonomous persistent surveillance missions using invariance
May 7, 2026Vladislav Nenchev, Prodromos SotiriadisPartial Observability Runtime Enforcement
Neural Co-state Policies: Structuring Hidden States in Recurrent Reinforcement Learning
May 6, 2026David Leeftink, Max Hinne, Marcel van GervenLatent States Hidden States
Recurrent Deep Reinforcement Learning for Chemotherapy Control under Partial Observability
May 4, 2026Firas Mohamed Elamine Kiram, Imane Youkana, Rachida Saouli +2Deep Reinforcement Learning Soft Actor-Critic
Spatial-Temporal Learning-Based Distributed Routing for Dynamic LEO Satellite Networks
May 4, 2026Po-Heng Chou, Chiapin Wang, Shou-Yu Chen +1Satellite Adaptive Routing
Observability Conditions and Filter Design for Visual Pose Estimation via Dual Quaternions
May 3, 2026Nicholas B. Andrews, Kristi A. MorgansenQuaternion Visual-Inertial Systems
Forager: a lightweight testbed for continual learning with partial observability in RL
May 1, 2026Steven Tang, Xinze Xiong, Anna Hakhverdyan +7Efficient Continual Learning Partial Observability
Algebraic Semantics of Governed Execution: Monoidal Categories, Effect Algebras, and Coterminous Boundaries
May 1, 2026Alan L. McCannAlgebraic Structures Formal Semantics
Observable Performance Does Not Fully Reflect Adaptive System Organization: A Multi-Level Analysis of Gait Dynamics Under Occlusal Constraint
May 1, 2026Jacques Raynal, Pierre Slangen, Elsa Raynal +1Single-Subject Gait Dataset Partial Observability
Learning Tactile-Aware Quadrupedal Loco-Manipulation Policies
Apr 29, 2026Pokuang Zhou, Yuhao Zhou, Quan Khanh Luu +7Humanoid Loco-Manipulation Tactile Perception
Observable Neural ODEs for Identifiable Causal Forecasting in Continuous Time
Apr 28, 2026Jennifer Wendland, Nicolas Freitag, Maik KschischoNeural Ordinary Differential Equations Partial Observability
Agentic Harness Engineering: Observability-Driven Automatic Evolution of Coding-Agent Harnesses
Apr 28, 2026Jiahang Lin, Shichun Liu, Chengjun Pan +8Agent Harness Coding Agents
VISION-SLS: Safe Perception-Based Control from Learned Visual Representations via System Level Synthesis
Apr 27, 2026Antoine P. Leeman, Shuyu Zhan, Melanie N. Zeilinger +1Visual Servoing Feedback Linearization
Efficient learning by implicit exploration in bandit problems with side observations
Apr 27, 2026Tomas Kocak, Gergely Neu, Michal Valko +1Near-Optimal Regret Guarantees Bandits
Architecture Determines Observability of Transformers
Apr 27, 2026Thomas CarmichaelAutoregressive Transformers Transformer Architectures
Reconstructive Authority Model: Runtime Execution Validity Under Partial Observability
Apr 24, 2026Marcelo Fernandez - TraslaIACanonical Action Verification And Attestation Authority
Information-Theoretic Geometry Optimization and Physics-Aware Learning for Calibration-Free Magnetic Localization
Apr 24, 2026Wenxuan Xie, Yuelin Zhang, Qingpeng Ding +4Optimal Sensor Placement Robust Localization
Time, Causality, and Observability Failures in Distributed AI Inference Systems
Apr 23, 2026Ankur Sharma, Deep Shah, David Lariviere +1Online Inference Clocks
From Admission to Invariants: Measuring Deviation in Delegated Agent Systems
Apr 19, 2026Marcelo FernandezStructural Enforcement Admissibility
Active World-Model with 4D-informed Retrieval for Exploration and Awareness
Apr 17, 2026Elaheh Vaezpour, Amirhosein Javadi, Tara JavidiWorld Models Autonomous Exploration Strategies
Quantifying Motion Excitation for Metric Scale Observability in Monocular Visual-Inertial Odometry
Mar 22, 2026Hadush Hailu, Bruk Gebregziabher, Siddhartha Gudipudi +1Visual Odometry Inertial
Stability and Concentration in Nonlinear Inverse Problems with Block-Structured Parameters: Lipschitz Geometry, Identifiability, and an Application to Gaussian Splatting
Feb 10, 2026Joe-Mei Feng, Hsin-Hsiung KaoIll-Posed Inverse Problem Gaussian Splatting
Graph-Loc: Robust Graph-Based LiDAR Pose Tracking with Compact Structural Map Priors under Low Observability and Occlusion
Feb 9, 2026Wentao Zhao, Yihe Niu, Zikun Chen +4Robust Lidar-Inertial Odometry Light Detection And Ranging
Geometric Observability Index: An Operator-Theoretic Framework for Per-Feature Sensitivity, Weak Observability, and Dynamic Effects in SE(3) Pose Estimation
Feb 5, 2026Joe-Mei Feng, Sheng-Wei Yu, Hsin-Hsiung KaoPartial Observability Feed-Forward Visual Geometry Estimation
Toward Learning POMDPs Beyond Full-Rank Actions and State Observability
Jan 26, 2026Seiji Shaw, Travis Manderson, Chad Kessens +1Partially Observable Markov Decision Process Markov Decision Processes
MACRO-LLM: LLM-Empowered Multi-Agent Collaborative Reasoning under Spatiotemporal Partial Observability
Jan 14, 2026Handi Chen, Running Zhao, Xiuzhe Wu +2Multi-Agent Reasoning Partial Observability
When is a System Discoverable from Data? Discovery Requires Chaos
Nov 12, 2025Zakhar Shumaylov, Peter Zaika, Philipp Scholl +3Chaos Data-Driven
Learning Robust Penetration Testing Policies under Partial Observability: A systematic evaluation
Sep 24, 2025Raphael Simon, Pieter Libin, Wim MeesPartially Observable Markov Decision Process Penetration Testing
The observational partial order of causal structures with latent variables
Feb 11, 2025Marina Maciel Ansanelli, Elie Wolfe, Robert W. SpekkensCausal Foundation Models Causal Reasoning
Observability-Aware Control for Quadrotor Formation Flight with Range-only Measurement
Nov 6, 2024H S Helson Go, Ching Lok Chong, Longhao Qian +1Flight Performance Partial Observability

May 25, 2026 · cs.LGJ/K move · Enter open · S save

The Behavioral Credibility Trilemma: When Calibrated Autonomy Becomes Impossible

Lauri Lovén, Nam Do, Hassan Mehmood, Dinesh Kumar Sah+1

We prove that no reinforcement learning policy with confidence-gated autonomy can simultaneously achieve maximum helpfulness, optimal calibration, and full autonomy under rational oversight, whenever some tasks exceed the agent's reliable competence: the Behavioral Credibility Trilemma. The impossibility is geometric -- adding any non-affine autonomy incentive to a strictly proper scoring rule destroys strict properness, so an agent rewarded for both calibrated confidence and autonomous action systematically inflates its reported confidence on tasks below the principal's approval threshold. The Behavioral Perturbation Lemma quantifies the inflation (scaling as

w_A/(2 w_C)

for the Brier score) and shows detection requires

Ω(1/Δ^2)

observations. We prove the principal's optimal oversight rule is necessarily non-affine, making the impossibility unconditional and optimizer-independent across log-concave-density policy families. We formalize the Confidence-Gated Decision Problem, map existing methods onto the trilemma, and identify two constructive resolution pathways (commitment, domain separation). A 540-configuration Best-of-N experiment tests five pre-registered hypotheses, all strongly confirmed (effect sizes

d = 1.10

5.32

), and adds a descriptive analysis of the achievable-

(H, C, A)

surface geometry showing a plateau-truncated frontier consistent with the predicted inflation saturation.

Scalable Oversight Autonomy Incentives Partial Observability

Open paper Ask about it PDF