R.I.P.
๐ป
Ghosted
TASR: Training-Free Adaptive Stopping for Iterative Retrieval
June 11, 2026 ยท Grace Period ยท ๐ KDD 2026
Authors
Adrian Kieback, Uyiosa Philip Amadasun, Aman Chadha, Aaron Elkins
arXiv ID
2606.13814
Category
cs.IR: Information Retrieval
Citations
0
Venue
KDD 2026
Abstract
Iterative retrieval-augmented generation agents commonly overspend by continuing to retrieve after the model has converged on an answer, incurring calls that change neither the prediction nor the supporting evidence. Existing remedies learn a stopping policy from labeled trajectories, tying the decision to a trained component that requires retraining for each new model or task. We propose TASR (Training-Free Adaptive Stopping Rule), a one-line predicate that fires when the model repeats its previous-round normalized answer and the isotonically calibrated logit margin exceeds 0.25. No classifier or value head is learned; the threshold is fixed across all twenty-four (model, retriever, corpus) configurations we evaluate. On a 3-model x 2-dataset distractor grid, TASR retains 94.8% of fixed-k=5's macro F1 at 62.6% of its calls and exceeds fixed-k=3 by +3.42 F1. The pattern holds on nine open-domain BM25 cells (55.01 F1 at 2.98 calls vs. 54.33 at 3.00 for fixed-k=3) and, with calibration locked from the distractor split, on nine dense-retrieval cells across two retriever families, with zero significant regressions in either extension. The rule was selected from an exhaustive enumeration of 381 candidate stopping rules; no alternative Pareto-dominates it on any evaluated configuration. A signal-quality analysis shows that verbalized 1-5 confidence collapses on RLHF-tuned models (96.5% of values equal 5, entropy 0.182 nats), while the logit margin achieves 44x better class-conditional separation, grounding the design in a measurable model pathology. TASR is an auditable, training-free Pareto baseline against which learned stopping controllers can be compared. Code is publicly available.
Community Contributions
Found the code? Know the venue? Think something is wrong? Let us know!
๐ Similar Papers
In the same crypt โ Information Retrieval
๐
๐
Old Age
Neural Graph Collaborative Filtering
R.I.P.
๐ป
Ghosted
DeepFM: A Factorization-Machine based Neural Network for CTR Prediction
R.I.P.
๐ป
Ghosted
BERT4Rec: Sequential Recommendation with Bidirectional Encoder Representations from Transformer
R.I.P.
๐
404 Not Found
Graph Neural Networks for Social Recommendation
R.I.P.
๐ป
Ghosted