# Agent-Guided Evidence Acquisition for Emotion-Cause Pair Extraction

arXiv: https://arxiv.org/abs/2610.14886 · HTML: https://mlsanity.com/paper/2610.14886/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 12 of its 37 references that are in the map.
- First posted on arXiv 10 Oct 2026.

## Builds on (most cited first, 12 of 12)

- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [GraphRouter: A Graph-based Router for LLM Selections](https://mlsanity.com/paper/2410.03834/) (2024)
- [A Unified Approach to Routing and Cascading for LLMs](https://mlsanity.com/paper/2410.10347/) (2024)
- [Emotion-Cause Pair Extraction: A New Task to Emotion Analysis in Texts](https://mlsanity.com/paper/1906.01267/) (2019)
- [Router-R1: Teaching LLMs Multi-Round Routing and Aggregation via Reinforcement Learning](https://mlsanity.com/paper/2506.09033/) (2025)
- [Multimodal Emotion-Cause Pair Extraction in Conversations](https://mlsanity.com/paper/2110.08020/) (2021)
- [SemEval-2024 Task 3: Multimodal Emotion Cause Analysis in Conversations](https://mlsanity.com/paper/2405.13049/) (2024)
- [Conformal Arbitrage: Risk-Controlled Balancing of Competing Objectives in Language Models](https://mlsanity.com/paper/2506.00911/) (2025)
- [Tools in the Loop: Quantifying Uncertainty of LLM Question Answering Systems That Use Tools](https://mlsanity.com/paper/2505.16113/) (2025)
- [M3HG: Multimodal, Multi-scale, and Multi-type Node Heterogeneous Graph for Emotion Cause Triplet Extraction in Conversations](https://mlsanity.com/paper/2508.18740/) (2025)
- [Single-Pass, Depth-Selective Reading for Multi-Aspect Sentiment Analysis](https://mlsanity.com/paper/2605.20998/) (2026)
- [Generation or Judgement? A Paradigm Perspective on LLM-Based Emotion-Cause Pair Extraction in Conversation](https://mlsanity.com/paper/2607.26967/) (2026)

## Abstract (arXiv)

Emotion-Cause Pair Extraction (ECPE) requires identifying the causes associated with emotions expressed in a conversation. Accurate extraction can depend on evidence that is not initially available, making it important to decide when further information is worth acquiring. We study agent-guided evidence acquisition for ECPE, where a student agent selectively accesses expert judgments for borderline relations on both sides of its validation-selected F1 decision boundary and revises only queried predictions. Through controlled comparisons under different information-access conditions, we examine how delegation granularity, query selection, and response integration affect prediction quality. At a nominal 10% query rate, selective fusion improves mean pair F1 by 2.64-3.88 points over the student in our main experiments, reaching 65.14 on ECF and 49.74 on MEC4 across model families. Our analysis suggests that greater access does not always translate into better cause identification. These findings motivate acquisition strategies that consider both the relevance of newly available evidence and its effect on prediction revision, providing an empirical basis for more effective and efficient evidence acquisition in ECPE.