3

Agentic Systems

Spurious Tool Use: When RL Agents Learn the Wrong Reason to Act

Understanding and mitigating shortcut tool selection in RL-trained agents through rewards for tool necessity.

Sep 14, 2026 • 1 min read

Agentic Abstention: Do Agents Know When to Stop Instead of Act? featured image

Agentic Systems

Agentic Abstention: Do Agents Know When to Stop Instead of Act?

A benchmark and analysis of when tool-using LLM agents should stop and abstain rather than continue acting.

May 1, 2026 • 1 min read

Tensorized Clustered LoRA Merging for Multi-Task Interference

Tensorized clustered LoRA merging to reduce multi-task interference in adapter-based LLM fine-tuning.

Aug 15, 2025 • 1 min read

InfoVisDial: An Informative Visual Dialogue Dataset by Bridging Large Multimodal and Language Models featured image

Visual Dialogue

InfoVisDial: An Informative Visual Dialogue Dataset by Bridging Large Multimodal and Language Models

An informative visual dialogue dataset created by bridging large multimodal and language models.

Dec 1, 2023 • 1 min read

Recommender Systems

Towards Generating Robust, Fair, and Emotion-Aware Explanations for Recommender Systems

Improving robustness, fairness, and emotion-awareness of explanations in recommender systems.

Aug 20, 2022 • 1 min read

Recommender Systems

EGCR: Explanation Generation for Conversational Recommendation

Generating explanations in multi-turn conversational recommendation with EGCR.

Aug 20, 2022 • 1 min read