When Evidence is Sparse: Weakly Supervised Early Failure Alerting in Dialogs and LLM-Agent Trajectories
cs.CL, cs.AI, cs.HC, cs.LG
Submitted: 2026-06-03
Updated: 2026-10-30
Code: https://github.com/stonybrooknlp/appworld
Terminology
Sources
- TimeMIL: Advancing Multivariate Time Series Classification via a Time-aware Multiple Instance Learning
- Learning the Optimal Stopping for Early Classification within Finite Horizons via Sequential Probability Ratio Test
- Provable Benefit of Orthogonal Initialization in Optimizing Deep Linear Networks
- Reward-Conditioned Policies
- Multi-Step Dialogue Workflow Action Prediction
- Early Classification of Time Series: A Survey and Benchmark
- Alert: Learning Trigger Functions for Early Classification of Time Series using Deep-RL
- Proximal Policy Optimization Algorithms
- Judging the Judges: A Systematic Study of Position Bias in LLM-as-a-Judge
- ALFWorld: Aligning Text and Embodied Environments for Interactive Learning
- AppWorld: A Controllable World of Apps and People for Benchmarking Interactive Coding Agents
- Math-Shepherd: Verify and Reinforce LLMs Step-by-step without Human Annotations
- Persuasion for Good: Towards a Personalized Persuasive Dialogue System for Social Good
- Watch Every Step! LLM Agent Learning via Iterative Step-Level Process Refinement
- ReAct: Synergizing Reasoning and Acting in Language Models
- Justice or Prejudice? Quantifying Biases in LLM-as-a-Judge
- Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Models
Related papers
- ALARM: Audio-Language Alignment for Reasoning Models
- ThinkSum: Probabilistic reasoning over sets using large language models
- Coherence boosting: When your pretrained language model is not paying enough attention
- From Facts to Insights: A Persona-Driven Dual Memory Framework and Dataset for Role-Playing Agents
- Improving General Role-Playing Agents via Psychology-Grounded Reasoning and Role-Aware Policy Optimization
- The Art of Asking: Multilingual Prompt Optimization for Synthetic Data