paper-with-me

홈 › Papers

UC-Search: Risk-Aware Test-Time Search for Delayed Constrained Time-Series Control

2026-06-24 · Xibai Wang arxiv

Time-series deployments often need delayed feasible decisions, not only accurate forecasts. UC-Search is a trace-only retained-search layer for delayed constrained control: a frozen backbone emits forecasts or action scores, a hard-feasibility automaton rolls paths forward, and bounded search returns the first action of a feasible trajectory. The main claim is conditional: retained lookahead can improve delayed constrained decisions only when delayed feasible-set coupling, retained-prefix premises, and fail-closed release certificates hold. The promoted public endpoint is Phase128 certified M4 expanded40: validation selects Certificate-Constrained Retained Pareto Beam with $λ=0.25$, the held-out test has certificate/risk-active rates $1.0000/0.9642$, and the weakest family remains above the unchanged $0.95$ gate at $0.9516$ on M4Weekly. The author-defined public $9$-family suite remains an uncertified stress-test boundary. The paper reports a trace-only mechanism, one certified public endpoint, failed-route certificates, and deployment boundaries rather than a universal risk-control theorem.

📄 PDF Abstract BibTeX arXiv:2606.25274

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Risk-Aware Batch Testing for Performance Regression Detection

2026-03-31 · Ali Sayedsalehi, Peter C. Rigby, Gregory Mierzwinski arxiv

Performance regression testing is essential in large-scale continuous-integration (CI) systems, yet executing full performance suites for every commit is prohibitively expensive. Prior work on performance regression pred…

A Formal Metareasoning Model of Concurrent Planning and Execution

2023-03-05 · Amihay Elboher, Ava Bensoussan, Erez Karpas, Wheeler Ruml 외

Agents that plan and act in the real world must deal with the fact that time passes as they are planning. When timing is tight, there may be insufficient time to complete the search for a plan before it is time to act. B…

Evaluating whether AI models would sabotage AI safety research

2026-04-27 · Robert Kirk, Alexandra Souly, Kai Fronsdal, Abby D'Cruz 외 arxiv

We evaluate the propensity of frontier models to sabotage or refuse to assist with safety research when deployed as AI research agents within a frontier AI company. We apply two complementary evaluations to four Claude m…

Entropic Risk-Aware Monte Carlo Tree Search

2026-01-25 · Pedro P. Santos, Jacopo Silvestrin, Alberto Sardinha, Francisco S. Melo arxiv

We propose a provably correct Monte Carlo tree search (MCTS) algorithm for solving risk-aware Markov decision processes (MDPs) with entropic risk measure (ERM) objectives. We provide a non-asymptotic analysis of our prop…

Controlling the Risk of Conversational Search via Reinforcement Learning

2021-01-15 · Zhenduo Wang, Qingyao Ai

Users often formulate their search queries with immature language without well-developed keywords and complete structures. Such queries fail to express their true information needs and raise ambiguity as fragmental langu…

Conversational Searchreinforcement-learningReinforcement LearningReinforcement Learning (RL)+1