cs.AINov 17, 2026

Proceedings of the 2026 XCSP3 Competition

Authors: Gilles Audemard, Christophe Lecoutre, Emmanuel Lonca

Organizations: CRIL University of Artois & CNRS France

Abstract

This document constitutes the proceedings of the 2026 XCSP3 Competition. The results of this competition of constraint solvers were presented at FLOC (Federated Logic Conference) 2026 Olympic Games, held in Lisbon, Portugal from 20th to 29th July, 2026.

Figures & tables

Explore similar work

Sep 1, 2020

PyCSP3: Modeling Combinatorial Constrained Problems in Python

In this document, we introduce PyCSP33, a Python library that allows us to write models of combinatorial constrained problems in a declarative manner. Currently, with PyCSP33, you can write models of constraint satisfaction and optimization problems. More specifically, you can build CSP (Constraint Satisfaction Problem) and COP (Constraint Optimization Problem) models. Importantly, there is a complete separation between the modeling and solving phases: you write a model, you compile it (while providing some data) in order to generate an XCSP33 instance (file), and you solve that problem instance by means of a constraint solver. You can also directly pilot the solving procedure in PyCSP33, possibly conducting an incremental solving strategy. In this document, you will find all that you need to know about PyCSP33, with more than 50 illustrative models.
Mar 20, 2026

Putnam 2025 Problems in Rocq using Opus 4.6 and Rocq-MCP

We report on an experiment in which Claude Opus~4.6, equipped with a suite of Model Context Protocol (MCP) tools for the Rocq proof assistant, autonomously proved 10 of 12 problems from the 2025 Putnam Mathematical Competition. The MCP tools, designed with Claude by analyzing logs from a prior experiment on miniF2F-Rocq, encode a "compile-first, interactive-fallback" strategy. Running on an isolated VM with no internet access, the agent deployed 141 subagents over 17.7 hours of active compute (51.6h wall-clock), consuming approximately 1.9 billion tokens. All proofs are publicly available.
May 23, 2026

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

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.