paper-with-me

홈 › Papers

CP-Agent: A Calibrated Risk-Controlled Agent for Feedback-Driven Competitive Programming

2026-05-23 · Peisong Wang, Bowen Liu, Zehua Li, Yuyao Wang, Zhiwei Ma, Yuhan Li, Jia Li arxiv

Large language models still struggle with contest-level programming, while many agentic remedies rely on massive inference-time sampling or expensive multi-stage post-training. We study when execution feedback reliably helps an LLM CP solver and which mechanisms govern the gains. We model feedback-driven solving as a calibrated stopped process and identify three quantities: false-admission risk, program-level evidence against bad programs, and the active-state success hazard. Under held-out trace calibration and selection from a pre-declared finite controller manifest, the resulting structural certificate lower-bounds the clean success probability before false admission. We instantiate mechanisms targeting these quantities as Dual-Granularity Verification, Test Augmentation, and Experience-Driven Self-Evolving, yielding CP-Agent. Without updating any parameters, CP-Agent raises Pass@1 from 25.8\% to 48.5\% on LiveCodeBench Pro and improves Refine@5 by 11.0\% on ICPC-Eval. Across three LLM backbones, CP-Agent lies on the cost--accuracy efficiency frontier, and ablations show that each component primarily affects its corresponding certificate quantity.

📄 PDF Abstract BibTeX arXiv:2605.24693

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Interactive multi-modal motion planning with Branch Model Predictive Control

2021-09-10 · Yuxiao Chen, Ugo Rosolia, Wyatt Ubellacker, Noel Csomay-Shanklin 외

Motion planning for autonomous robots and vehicles in presence of uncontrolled agents remains a challenging problem as the reactive behaviors of the uncontrolled agents must be considered. Since the uncontrolled agents u…

Autonomous VehiclesModel Predictive ControlMotion Planning

Calibrating the Evaluator: Does Probability Calibration Mitigate Preference Coupling in LLM Agent Feedback Loops?

2026-06-30 · Zewen Liu arxiv

When large language model (LLM) agents adapt their behavior through evaluator feedback, systematic evaluator biases propagate into the agent's learned strategy distribution - a phenomenon termed evaluator preference coup…

Human-Centric Reflective Architecture for Human-AI Collaborative Decision-Making

2026-07-03 · Andreas Kouridakis, Dimitrios Patiniotis Spyropoulos, George Vouros arxiv

The use of Large Language Models (LLMs) across diverse areas of human activity-ranging from everyday tasks to safety-critical applications-aims to enhance decision-making effectiveness with minimal human feedback. Concur…

Reinforcement Learning

Beyond Forecasting: The Belief-to-Trade Layer in Prediction-Market Agents

2026-07-03 · Yishu Wang, Yuxuan Wang, Jiaqi Deng, Hanyang Tang arxiv

Forecasting future events has attracted growing attention as a testbed for general-purpose AI. A natural way to ground this evaluation is let the models trade in the prediction markets. Trading, however, requires more th…

Risk Alignment in Agentic AI Systems

2024-10-02 · Hayley Clatterbuck, Clinton Castro, Arvo Muñoz Morán

Agentic AIs $-$ AIs that are capable and permitted to undertake complex actions with little supervision $-$ mark a new frontier in AI capabilities and raise new questions about how to safely create and align such systems…