Debate-to-Skill: Capability-Bound Process Supervision for Industrial Query-to-Agent Annotation

arXiv:2609.11176v1 Announce Type: new Abstract: Industrial query-to-agent matching fails when topical relevance is mistaken for executable capability, especially on long-tail and boundary-sensitive requests. We formulate annotation as capability-bound process supervision and instantiate it with Debate-to-Skill, which uses reusable decision principles, structured deliberation, verifier-based verdict extraction, and disagreement-driven refinement. On an industrial Query2Agent benchmark, we compare Debate-to-Skill with direct-label supervision, reasoning-SFT, and structural ablations. The results test whether gains come from supervising the capability-critical decision process itself, especially on grey-zone cases where semantic relatedness and executable capability diverge.

SkillShapley: Boundary-Adaptive Shapley Valuation for Skill Step Attribution in LLM Agents
When Self-Evolution Backfires: Pre-Commit Gating against Skill Contamination in LLM Agents
SkillResolve-Bench: Measuring and Resolving Same-Capability Ambiguity in Agent Skill Retrieval
NiyamAI - An Intent-Bound AI Agent with Cryptographically Verifiable Guardrails using Zero-Knowledge Proofs
Autonomous Topology Mutation: Safe Runtime Restructuring for Multi-Agent LLM Systems with Capability, State, and Shadow Invariants

Source: arXiv cs.AI | 2026-09-12

Related