TIDE: Proactive Multi-Problem Discovery via Template-Guided Iteration

Hugging Face Daily Papers Papers
template-guided iterative-discovery multi-problem-discovery ai-agents task-coverage

Summary

TIDE is a template-guided iterative framework for discovering multiple hidden problems from context, improving problem identification and resolution in document and code environments. It uses iterative discovery and thought templates to surpass single-shot and multi-agent baselines.

Agents are widely deployed as assistants over documents, tools, and code. However, they typically act only on explicit user requests, which surface only the problems the user has noticed, while many other important problems coexist, hidden in plain sight, within the broader user context, with their total number unknown in advance. We frame this as the task of discovering multiple hidden problems from context, in which coexisting problems should be uncovered, grounded in supporting evidence, and paired with concrete actions. To this end, we introduce TIDE, a template-guided iterative framework with two complementary mechanisms. Specifically, motivated by the observation that single-pass prediction anchors on the most salient cases and yields generic claims, we propose iterative discovery, which surfaces a small batch of candidates per round while conditioning on what has already been found, so subsequent rounds extend coverage; and thought templates, reusable schemas distilled from previously solved cases that specify what contextual signals to attend to and how to connect them, anchoring each prediction in a recognizable problem class. We validate TIDE on two realistic settings, personal workspaces and software repositories, across four model backbones, showing substantial gains over single-shot and parallel multi-agent baselines on task coverage, identification, and resolution.
Original Article
View Cached Full Text

Cached at: 06/05/26, 06:06 AM

Paper page - TIDE: Proactive Multi-Problem Discovery via Template-Guided Iteration

Source: https://huggingface.co/papers/2606.04743

Abstract

TIDE is a template-guided iterative framework for discovering hidden problems from context, using iterative discovery and thought templates to improve problem identification and resolution across document and code environments.

Agents are widely deployed as assistants over documents, tools, and code. However, they typically act only on explicit user requests, which surface only the problems the user has noticed, while many other important problems coexist, hidden in plain sight, within the broader user context, with their total number unknown in advance. We frame this as the task of discovering multiple hidden problems from context, in which coexisting problems should be uncovered, grounded in supporting evidence, and paired with concrete actions. To this end, we introduce TIDE, a template-guided iterative framework with two complementary mechanisms. Specifically, motivated by the observation that single-pass prediction anchors on the most salient cases and yields generic claims, we proposeiterative discovery, which surfaces a small batch of candidates per round while conditioning on what has already been found, so subsequent rounds extend coverage; andthought templates, reusable schemas distilled from previously solved cases that specify what contextual signals to attend to and how to connect them, anchoring each prediction in a recognizable problem class. We validate TIDE on two realistic settings, personal workspaces and software repositories, across four model backbones, showing substantial gains over single-shot and parallel multi-agent baselines ontask coverage,identification, andresolution.

View arXiv pageView PDFAdd to collection

Get this paper in your agent:

hf papers read 2606\.04743

Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash

Models citing this paper0

No model linking this paper

Cite arxiv.org/abs/2606.04743 in a model README.md to link it from this page.

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2606.04743 in a dataset README.md to link it from this page.

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2606.04743 in a Space README.md to link it from this page.

Collections including this paper0

No Collection including this paper

Add this paper to acollectionto link it from this page.

Similar Articles

Towards Robust Argumentative Essay Understanding via TIDE: An Interactive Framework with Trial and Debate

arXiv cs.AI

This paper introduces TIDE, a novel framework that integrates trial and debate mechanisms to improve criteria-based prompt optimization for argumentative essay understanding tasks such as automated essay scoring, argument component detection, and argument relation identification. Experiments show performance improvements, highlighting the potential of combining prompt-based methods for robust argument analysis.

TIDE: Every Layer Knows the Token Beneath the Context

arXiv cs.CL

This paper introduces TIDE, a method that addresses the Rare Token and Contextual Collapse problems in LLMs by injecting token identity into every layer via Embedding Memory. The authors demonstrate theoretical and empirical improvements across language modeling and downstream tasks.

From I/O to Code with Discovery Agent

arXiv cs.LG

This paper introduces DIO-Agent, a discovery agent that synthesizes programs from input-output behavior using LLM-guided evolutionary search with a transformation priority premise to avoid dead ends. Experiments show it outperforms traditional methods and baselines on a new IO2CodeBench benchmark.

ADIAS: Automated Design of Interactive Agentic Systems

arXiv cs.AI

ADIAS is a framework for automated design of agentic systems that uses issue-centric optimization, maintaining a persistent issue state across repair rounds. It outperforms the strongest baseline by 25.2% on average across five interactive benchmarks and shows consistent gains with four backbone models.