Newest papers

NIOCIS: Typed-Decision Next-Hop Routing with Node-Conditioned Option Spaces for Tool-Use Agents

Jin Han, Mingfeng Xin, Feng Liang, Jingtao Yu · 2026 · arXiv (Cornell University)

DOI: 10.48550/arxiv.2610.25985 · cited by 0 works (OpenAlex) · open-access PDF

Korean

도구 사용을 잃은 에이전트는 결정에 대 한 상당히 평평한 간격을 지불합니다 (+ 각 호프에 언어 모델은 상태를 다시 읽고 몇 초 동안 생각하지만, 그 조건은 제한적이고 결정을 격리한다. 우리는 NIOCIS를 제시합니다, 로딩 레이어는 실행 로그를 루프 충돌 한 특정 액션 그래프 (앞으로 전환과 복구 back-edges)에 접합하여 상태에서 선언 한 옵션을 다시 읽고, 그 옵션을 몇 초 동안 생각합니다. 우리는 하나의 패스에 실행 로그를 접합하는 로딩 레이어를 제시합니다. 1,615 생산 보안 작동 열쇠 에피소드에서 우리는 레이어가 대체, 복구 back-edges에 대 한 무엇을 측정하고 반환합니다. 대체 : 표

Machine translation (Meta M2M100); the English original follows.

Abstract

Tool-use agents pay per decision: at each hop a language model re-reads the state and thinks for seconds, though its actions are finite and decisions recur. We present NIOCIS, a routing layer that folds execution logs into a loop-collapsed action graph (forward transitions plus recovery back-edges) answering one typed question: which declared option at a state, plus stop, does the fleet take next? A small model reads a calibrated distribution over them in one pass, emitting no text. On 1,615 production security-operations episodes we measure what the layer replaces, returns and is bounded by. Replaces: the typed encoder matches the logged next hop on 32.2% of the 3,875 held-out decisions (34.9% within the declared options) in 10 ms of encoder time (19.5 ms for the typed-choice form), against 2.2 s per LLM hop; two feature readouts reach 32.8% and 32.3%, an ordering the paired test does not resolve, so the typed layer is chosen for cost, not a separated lead. Tuning: jpt-4b reaches 9.9% zero-shot and 31.9% fine-tuned, a gap an exact paired test does not resolve (p=0.68), at 244 ms. Returns little: the realised hop falls outside the declared options for 7.9% of decisions and outside the model's top twenty for 9.3%; the most confident 15% holds 91.9% accuracy. Bounded: a cross-trace leave-one-out test puts the released state's ceiling at 25.6--44.9% as the state key grows more specific, i.e. repeated states disagree more often than they agree; the option-space ablation attributes the gain to per-node candidate restriction (+3.5 points over a flat catalog) rather than graph traversal (zero within its interval); a gated self-evolution loop lifts every arm above its anchor yet ends below full supervision; a confidence-gated cascade loses agreement when the escalation arm is the zero-shot stand-in; and agreement past a third of the fleet needs a state carrying the plan and the observation.

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Topics: Computer science, Encoder, Bounded function, Layer (electronics), Measure (data warehouse), State (computer science)

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange