TwinCheck: Evidence-Grounded Negative-Twin Verification for Stateful Tool Agents
cs.AI
Submitted: 2026-09-22
Updated: 2026-09-22
Terminology
Sources
- CausalFlow: Causal Attribution and Counterfactual Repair for LLM Agent Failures
- Why Do Multi-Agent LLM Systems Fail?
- CRITIC: Large Language Models Can Self-Correct with Tool-Interactive Critiquing
- AttriGuard: Defeating Indirect Prompt Injection in LLM Agents via Causal Attribution of Tool Invocations
- Large Language Models Cannot Self-Correct Reasoning Yet
- Let's Verify Step by Step
- DoVer: Intervention-Driven Auto Debugging for LLM Multi-Agent Systems
- Self-Refine: Iterative Refinement with Self-Feedback
- Judging the Judges: A Systematic Study of Position Bias in LLM-as-a-Judge
- Reflexion: Language Agents with Verbal Reinforcement Learning
- GuardAgent: Safeguard LLM Agents by a Guard Agent via Knowledge-Enabled Reasoning
- ReAct: Synergizing Reasoning and Acting in Language Models
- $\tau$-bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains
- Generative Verifiers: Reward Modeling as Next-Token Prediction
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems
- VSAL: A Vision Solver with Adaptive Layouts for Graph Property Detection