REVEAL: Reverse Engineering Agentic Latents from Frontier-Model Traces
cs.AI, cs.CL
Submitted: 2026-10-12
Updated: 2026-10-14
Code: https://github.com/harbor-framework/terminal-bench-2-1
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Representation Engineering for Large-Language Models: Survey and Research Challenges
- Eliciting Latent Predictions from Transformers with the Tuned Lens
- Verbalizable Representations Form a Global Workspace in Language Models
- In-Context Learning Creates Task Vectors
- Distilling Step-by-Step! Outperforming Larger Language Models with Less Training Data and Smaller Model Sizes
- TRACES: Proactive Safety Auditing for Multi-Turn LLM Agents via Trajectory-State Modeling
- WebThinker: Empowering Large Reasoning Models with Deep Research Capability
- Terminal-Bench: Benchmarking Agents on Hard, Realistic Tasks in Command Line Interfaces
- WebGPT: Browser-assisted question-answering with human feedback
- gpt-oss-120b & gpt-oss-20b Model Card
- From Actions to Understanding: Conformal Interpretability of Temporal Concepts in LLM Agents
- Humanity's Last Exam
- Doomed from the Start: Early Abort of LLM Agent Episodes via a Recall-Controlled Probe Cascade
- TACT: Mitigating Overthinking and Overacting in Coding Agents via Activation Steering
- Tool-Call Dependency Structure is Linearly Decodable in LLM Agent Residual Streams
- Steering Language Models With Activation Engineering
- Taxonomy, Opportunities, and Challenges of Representation Engineering for Large Language Models
- Tool Calling is Linearly Readable and Steerable in Language Models
- Representation Engineering: A Top-Down Approach to AI Transparency
- Latent Collaboration in Multi-Agent Systems
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
- Agents' Last Exam
- 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