The paper settles the computational complexity of Quoridor and related games by reducing them to Reisch's planar graph-Hex.

This paper introduces Epistemic Byzantine Fault Tolerance (EBFT), a fault-tolerance model for agentic infrastructure and post-deterministic distributed systems, addressing the Honest Quorum Problem an…

The paper introduces VeriTrip, a new verifiable benchmark that evaluates travel planning agents' ability to perform evidence-grounded reasoning over complex, unstructured, and multimodal web data, rev…

QUBRIC introduces a co-design framework that simultaneously optimizes queries and rubrics, overcoming the bottleneck of vague rubrics derived from open-ended questions, leading to significant gains in…

FARS is a fully automated AI-for-AI research system that generated and advanced 166 complete research papers across 67 topics in a large-scale public deployment, with evaluations from 282 reviews.

The paper introduces DrugClaw, a multi-agent system, and DrugAudit, a new benchmark, demonstrating that DrugClaw excels at answering drug-related questions by grounding answers in primary regulatory s…

This paper proposes Rhetor, a multi-agent system that generates rehearsed live demonstrations with segment-synchronized narration and real-time voice question answering for web applications.

SwarmHarness introduces a decentralized, incentive-aligned protocol enabling self-organizing compute swarms for AI tasks, eliminating the need for central coordinators or heavy blockchain infrastructu…

This paper proposes FinSAgent, an evidence-grounded multi-agent framework for financial question answering over SEC filings, which improves retrieval coverage and answer correctness through corpus-sid…

The paper introduces ADR, a novel, production-proven detection system that provides high-fidelity security monitoring for AI agents operating via the Model Context Protocol, significantly outperformin…

The paper conducts a reproducibility study on FACTER, a model-agnostic framework for fairness and statistical coverage in LLM-based recommendation, and evaluates its consistency and contribution.

The paper introduces RUBAS, a rubric-based reinforcement learning framework that improves agent safety by providing fine-grained, multi-dimensional rewards for complex tool-use scenarios.

The paper proposes CheckRLM, a framework that improves the reliability of Reasoning Language Models by identifying and correcting factual errors using Retrieval-Augmented Generation.

The Cologne Information Retrieval group participated in iKAT SCAI 2026 shared task using an agentic conversational search system with query rewriting, retrieval, reranking, answer generation, and clar…

The paper introduces presidio-hardened-x402, an open-source middleware that intercepts x402 payment requests to detect and redact PII and enforce spending policies before on-chain settlement.

The paper introduces SafeAudit, a meta-audit framework that systematically enumerates test cases and uses a quantitative metric to uncover significant residual unsafe behaviors in LLM agents that exis…

OpenForgeRL is an open-source framework for training harness-based AI agents end-to-end in various environments using a lightweight proxy and Kubernetes orchestrator.

TalTech submitted top-ranking systems to the Beyond Transcription Challenge using fine-tuned Voxtral models and reinforcement learning against Open Medical Concept F1.

The paper introduces SafeRx-Agent, a knowledge-grounded multi-agent framework that improves medication recommendation accuracy and safety by incorporating fine-grained ATC codes and rigorous safety ve…