Oct 2026· Electronics· Vol 15, pp. 4688· 0 citations
TL;DR
SCAR–Pair improves selected-tool memory evidence ranking within the evaluated setting, and separates schema-expanded candidate generation from parameter-level scoring and integrates request, tool, field, and cross-encoder evidence through query-balanced pairwise learning.
Abstract
Large language model (LLM) agents often need historical conversations to recover argument values omitted from current tool requests. This study introduces SCAR–Pair, a two-stage ranker for memory retrieval after tool selection. It separates schema-expanded candidate generation from parameter-level scoring and integrates request, tool, field, and cross-encoder evidence through query-balanced pairwise learning. On a reconstructed Mem2ActBench bank containing 19,661 conversations and 391 evidence-bearing tasks, SCAR–Pair achieved 0.450 Recall@5 and 0.365 nDCG@5 under stratified five-fold evaluation, compared with 0.396 and 0.325 for a matched request-only pairwise ranker. Component-aware intervals and adjusted tests support these task-weighted gains in the ToolACE-dominated mixture. Controlled comparisons support the complete schema-view scoring configuration over request-only scoring on the same candidate pool but do not isolate correct-schema semantics or individual field components as independent contributors. The pairwise advantage over pointwise training is also not significant. Across the tested readers, higher retrieval quality does not yield a significant tool-call accuracy advantage over the strict request-only control. SCAR–Pair therefore improves selected-tool memory evidence ranking within the evaluated setting.
CoRA-Bench, a benchmark for evaluating evidence preservation under shared token budgets, is introduced and results show that method rankings vary across evidence types and between evidence recall and downstream accuracy.
Huzaifa Pardawala, Siddhant Sukhani, Sudheer Chava et al.· 0 citations
Schema matching increasingly uses generative language models to rerank retrieved column candidates, although the underlying task is a bounded correspondence decision. We present JevNexus, which combines typed pairwise decisions with schema/instance evidence and invokes listwise refinement only when the evidence disagre...
Run-Ze Li, Han-Chen Wang, Ying Zhang et al.· 1 citation
We study bounded Agentic retrieval-augmented generation (RAG) for knowledge-intensive question answering. The task is to answer multi-hop or domain questions from auditable external evidence under a fixed inference budget. Existing Agentic RAG evaluations often vary the model, retriever, corpus interface, controller, t...
Chuan-Heng Ma, Yi-Zhao Wang, Sheng-Yang Li· Proceedings of the 35th ACM...· 0 citations
Retrieval-grounded machine-learning pipeline synthesis must reconcile code templates with package versions and resource budgets. We study a two-stage pre-validator adapted from concrete dependency-satisfiability and resource-prediction mechanisms: an inexpensive retrieval-profile margin ranks candidate manifests; a bud...
Maya Jenkins, Thomas Baker, Theo Hernandez· Academic Journal of Applied...· 0 citations
This work introduces \textsc{ArchOR], an archetype-centric skill agent that builds on \textsc{OptSkills} by adding two retrieval-focused modules, and refines the ordering of cached skill representations through a low-rank prototype residual.
An-Ran Liu, Benjamin Hou, Zong-Sheng Cao et al.· 0 citations
EviGraphRAG is proposed, a ranker-agnostic reliability layer that separates candidate ranking from exact verification and explicit abstention, and exact conjunction over represented event constraints and linked source-record connectivity can improve selective reliability, while parser quality and candidate retrieval re...
Yu-Teng Sun, Yang Su, Xu-An Wang· Computers, Materials & C...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.