Amir Saeidi

activity

20222026

most citedA Novel Neuromorphic Processors Realization of Spiking Deep Reinforcement Learning for Portfolio Management

4 citations · 6 across the 10 of their papers we have counts for

collaborators

Showing cs.AIShow all

2 papers · 1 filter

cs.AI2026

$τ$ -Emotion-Bench: Exposing the Interaction Fragility of LLM Agents through Real-World User Emotions

Rishitosh Kumar Singh, Amir Saeidi, Shamanthak Hegde +2

In long-horizon tool-calling tasks, LLM agents can fail not only because of tool-use errors, but also because of ineffective interaction with users. Yet existing benchmarks largely…

cs.AI2026

LedgerAgent: Structured State for Policy-Adherent Tool-Calling Agents

Md Nayem Uddin, Amir Saeidi, Eduardo Blanco +1

Policy-adherent tool-calling agents in customer-service domains must maintain task states across turns while calling tools and obeying domain policies. Task states consist of relev…

τ-Emotion-Bench: Exposing the Interaction Fragility of LLM Agents through Real-World User Emotions

LedgerAgent: Structured State for Policy-Adherent Tool-Calling Agents

$τ$ -Emotion-Bench: Exposing the Interaction Fragility of LLM Agents through Real-World User Emotions