Related papers: Dear Algo: A Precision-First Agentic Intent Layer for Unified Search and Recommendation

Dear Algo: A Precision-First Agentic Intent Layer for Unified Search and Recommendation

URL: http://arxiv.org/abs/2608.15877v1
Date: Sun, 16 Aug 2026 17:59:12 GMT
Title: Dear Algo: A Precision-First Agentic Intent Layer for Unified Search and Recommendation
Abstract summary: Open-ended requests such as emphmore NBA news or emphless politics steer subsequent feed recommendations rather than a one-shot result list.<n>Dear Algo on Threads compiles explicit, inferred, negative, and compound intent into a grounded executable plan.<n>We show how explicit natural-language intent can be carried into feed recommendation under a precision-first evaluation framework.
Score: 14.580988352516457
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Abstract: Search and recommendation serve a shared discovery objective but encode intent differently. We study this boundary through Dear Algo on Threads, a deployed product where open-ended requests such as \emph{more NBA news} or \emph{less politics} steer subsequent feed recommendations rather than return a one-shot result list. Its agentic intent layer compiles explicit, inferred, negative, and compound intent into a grounded executable plan, then invokes conventional retrieval and optional semantic or multimodal reranking. The layer shares an intent-to-retrieval contract without requiring one model or serving path across search-like and recommendation-like modes. We evaluate Dear Algo under a precision-first objective. In a blinded audit of 300 public request-item pairs (296 evaluable), a strict categorical LLM-as-a-judge gate achieved 94.4\% exact-Relevant precision [88.8\%, 98.9\%]. Across 72 normalized request clusters, the full configuration produced 7.73 judge-qualified candidates per 20 slots versus 6.61 for an LLM-derived-query baseline, a gain of 1.11 [0.12, 2.12]. In a candidate-randomized serving-path study restricted to the reranker path's first 72 eligible hours, the user-weighted judge-Irrelevant share among judged admissions was 2.80\% versus 4.78\% off (-1.97 points [-3.02, -0.94]), while Exact-Relevant share was 2.24 points higher [0.08, 4.41]. Together, these studies show how explicit natural-language intent can be carried into feed recommendation under a precision-first evaluation framework

Related papers

Codebook Agent: Amortized Topology Design for LLM Multi-Agent Systems [67.04448659688579]
We develop a query-independent 16-entry codebook that ranks the top decoded candidates in a single batched forward pass.<n>With no iterative search and no message passing at test time, Codebook Agent is the most accurate method on all six benchmarks.
arXiv Detail & Related papers (2026-09-02T08:10:22Z)
Small Language Models as Judges for Rubric-Based Reinforcement Learning [57.707881387886516]
We study whether smaller language models can serve as efficient and reliable rubric-based judges.<n>We compare three ways of extracting criterion-level judgments from small models: Generative verdicts, Yes/No Logprob margins, and Probe judges.<n>Across both datasets, the Qwen3-1.7B Probe judge achieves the strongest criterion-level agreement among these methods.
arXiv Detail & Related papers (2026-08-30T20:00:17Z)
Efficient GPU Retrieval for Semantic Search [11.631441668563802]
We present a policy-aligned retrieval framework for LinkedIn.<n>A lightweight single-slot Stage-1 scorer generates high-recall candidates.<n>On 21K held-out queries, this representation improves offline relevance over a matched-capacity baseline.
arXiv Detail & Related papers (2026-08-29T00:38:27Z)
Harness-IF: Evaluating Instruction Following Across Instruction Surfaces in Coding Agents [29.96375986740068]
Harness-IF scores operational rules one at a time from execution evidence.<n>AP-Acc scores only rules labeled as opposing unprompted defaults.
arXiv Detail & Related papers (2026-08-12T07:07:57Z)
Modality-Driven Search with Holistic Trace Judging for ARC-AGI-2 [0.0]
I present a solver for ARC-AGI-2, a few-shot visual reasoning benchmark.<n>It generates diverse candidates independently across text, image, and code channels.<n>Unlike self-consistency or majority voting, it reliably recovers correct minority hypotheses on tasks where the modal answer is wrong.
arXiv Detail & Related papers (2026-06-30T11:55:33Z)
Efficient Visual Pointing for Embodied AI:Agent-Driven Data Synthesis, Cross-Block Attention, and Iterative Correction [55.11480729304395]
We describe our PointArena 2026 solution, which achieves 77.2% overall accuracy and ranks second on the benchmark.<n>The ap proach targets three failure modes. First, agent-driven syn thesis builds large semantic and anchor-relative candidate pools.<n>Second, a determinis tic steerable-data pipeline creates a verified 10,000-sample main set, plus reserve samples, using masks, templates, and path verification.
arXiv Detail & Related papers (2026-06-29T06:39:03Z)
When Is an LLM Worth It for Hyperparameter Optimization? A Budget-Matched Study on Tabular Data Finds the Warm-Start Is a Default Configuration, Not the Model [0.0]
Large language models (LLMs) have been proposed as hyperparameter-optimization (HPO) advisors that "warm-start" search from prior knowledge.<n>We test that claim under a budget-matched, multi-seed protocol on eight PMLB benchmarks.
arXiv Detail & Related papers (2026-06-19T17:52:36Z)
AbstRAG: Learning to Abstract for Retrieval Problems [23.379898867224355]
AbstRAG decomposes the query--evidence gap into expression, conceptual, intent--evidence, and event-type components.<n>It outperforms on nDCG@10 in 18 of 21 paired-bootstrap contrasts and improves generation accuracy by 1.9%, 5.2%, and 4.0%.
arXiv Detail & Related papers (2026-06-08T13:14:01Z)
Step-wise Rubric Rewards for LLM Reasoning [72.17879367869503]
Reinforcement Learning with Verifiable Rewards (RLVR) is widely used to improve reasoning in large language models.<n>We find 18.2% of steps in correct responses are wrong yet positively rewarded.<n>Across six mathematical reasoning benchmarks, SRaR improves average accuracy over RaR by 3.57 points.
arXiv Detail & Related papers (2026-05-17T07:08:14Z)
Iterative Nash Policy Optimization: Aligning LLMs with General Preferences via No-Regret Learning [55.65738319966385]
We propose a novel online algorithm, iterative Nash policy optimization (INPO)<n>Unlike previous methods, INPO bypasses the need for estimating the expected win rate for individual responses.<n>With an LLaMA-3-8B-based SFT model, INPO achieves a 42.6% length-controlled win rate on AlpacaEval 2.0 and a 37.8% win rate on Arena-Hard.
arXiv Detail & Related papers (2024-06-30T08:00:34Z)
Query Performance Prediction using Relevance Judgments Generated by Large Language Models [53.97064615557883]
We propose a new Query performance prediction (QPP) framework using automatically generated relevance judgments (QPP-GenRE)<n>QPP-GenRE decomposes QPP into independent subtasks of predicting relevance of each item in a ranked list to a given query.<n>We predict an item's relevance by using open-source large language models (LLMs) to ensure scientific relevance.
arXiv Detail & Related papers (2024-04-01T09:33:05Z)
Progressive End-to-End Object Detection in Crowded Scenes [96.92416613336096]
Previous query-based detectors suffer from two drawbacks: first, multiple predictions will be inferred for a single object, typically in crowded scenes; second, the performance saturates as the depth of the decoding stage increases. We propose a progressive predicting method to address the above issues. Specifically, we first select accepted queries to generate true positive predictions, then refine the rest noisy queries according to the previously accepted predictions. Experiments show that our method can significantly boost the performance of query-based detectors in crowded scenes.
arXiv Detail & Related papers (2022-03-15T06:12:00Z)

This list is automatically generated from the titles and abstracts of the papers in this site.