4 papers
From Confident Closing to Silent Failure: Characterizing False Success in LLM Agents
Laksh Advani
LLM agents can fail silently by asserting task completion when the environment state shows otherwise. We study this failure mode, false success, across two agent benchmarks: 9,876…
Trajectory Guard -- A Lightweight, Sequence-Aware Model for Real-Time Anomaly Detection in Agentic AI
Laksh Advani
Autonomous LLM agents generate multi-step action plans that can fail due to contextual misalignment or structural incoherence. Existing anomaly detection methods are ill-suited for…
When Small Models Are Right for Wrong Reasons: Process Verification for Trustworthy Agents
Laksh Advani
Deploying small language models (7-9B parameters) as autonomous agents requires trust in their reasoning, not just their outputs. We reveal a critical reliability crisis: 50-69\% o…
Effective Proxy for Human Labeling: Ensemble Disagreement Scores in Large Language Models for Industrial NLP
Wei Du, Laksh Advani, Yashmeet Gambhir +4
Large language models (LLMs) have demonstrated significant capability to generalize across a large number of NLP tasks. For industry applications, it is imperative to assess the pe…