Tag
The Agent Instruction Protocol (AIP) proposes modeling AI agent skills as directed execution graphs with schema-validated YAML specifications, replacing free-form prose instructions. Experiments show AIP compilation raised Claude Sonnet's task reward from 0.60 to 0.71 and pass rate from 53% to 67% across 27 real agent tasks.
This paper proposes MONIR, a Modalized-Output Normative Intermediate Representation that bridges LLM-assisted norm extraction and ASP-based compliance reasoning for technical standards. The framework is instantiated on Chinese ADAS regulations, combining symbolic reasoning with LLM pipelines for explainable compliance checking.
This paper argues that consensus-seeking in multi-agent LLM systems is insufficient for value-laden tasks, proposing a knowledge-representation layer that classifies agent reasoning-trace disagreements into four symbolic states to enable strategic routing in systems like content moderation.
This paper presents a prototype framework for managing uncertainty in LLM-generated procedural knowledge for virtual laboratory planning, using structured domain representations to repair uncertain procedural steps.
This paper investigates the phenomenon where large language models hallucinate despite having the correct answer available in their generation-time distribution. By introducing a semantic notion of answer availability, the authors show that 16-47% of instruction-tuned model hallucinations occur when the correct concept is already represented, and that this rate increases with scale. They identify that instruction tuning sharpens answer commitment, making helpfulness and confident hallucination two sides of the same coin.
This paper introduces a quantitative notion of diversity of extensions in abstract argumentation based on symmetric difference, and provides a systematic complexity classification for related reasoning tasks.
DALM proposes a domain-algebraic language model that generates text under exact structural constraints derived from a domain lattice, addressing hallucination by organizing knowledge into separate domain fibers with algebraic guarantees. The model uses three-phase structured denoising (domain → relation → concept) with domain-annotated training data to prevent cross-domain contamination.