BenchJack audits 10 AI agent benchmarks, synthesizes exploits achieving near-perfect scores without task completion, surfaces 219 flaws, and reduces hackable-task ratios to under 10% on four benchmarks via iterative patching.
Reward tampering problems and solutions in reinforcement learning: A causal influence diagram perspective
6 Pith papers cite this work, alongside 2 external citations. Polarity classification is still indexing.
6
Pith papers citing it
2
external citations · external index
citation-role summary
background 2
citation-polarity summary
years
2026 6roles
background 2polarities
background 2representative citing papers
Introduces loop engineering as a distinct practice layer for coding agents, supplies a taxonomy and verification ladder, and analyzes a hand-coded corpus of fifty real loops.
AI alignment is reframed as a fixed-point incentive problem in a solver-auditor pipeline, solved via bilevel optimization and bandit search over reward profiles to maintain monitoring and reduce hallucinations in LLM coding tasks.
SMEPO applies fine-grained semantic masking to expert guidance in RLVR, turning hard problems into fill-in-the-blank tasks while preserving structure, yielding up to 3.2 point accuracy gains and 4.2x faster training.
An off-Earth autonomy pathway can reduce AGI confrontation incentives by making early cooperation preferable to power-seeking on Earth.
Proxy RL produces a staged proxy-internalization capability that emerges before and predicts reward hacking in coding environments.
citing papers explorer
-
Do Androids Dream of Breaking the Game? Systematically Auditing AI Agent Benchmarks with BenchJack
BenchJack audits 10 AI agent benchmarks, synthesizes exploits achieving near-perfect scores without task completion, surfaces 219 flaws, and reduces hackable-task ratios to under 10% on four benchmarks via iterative patching.
-
Stop Hand-Holding Your Coding Agent: Engineering the Loops that Replace Step-by-Step Prompting
Introduces loop engineering as a distinct practice layer for coding agents, supplies a taxonomy and verification ladder, and analyzes a hand-coded corpus of fifty real loops.
-
AI Alignment via Incentives and Correction
AI alignment is reframed as a fixed-point incentive problem in a solver-auditor pipeline, solved via bilevel optimization and bandit search over reward profiles to maintain monitoring and reduce hallucinations in LLM coding tasks.
-
Hide to Guide: Learning via Semantic Masking
SMEPO applies fine-grained semantic masking to expert guidance in RLVR, turning hard problems into fill-in-the-blank tasks while preserving structure, yielding up to 3.2 point accuracy gains and 4.2x faster training.
-
Reframing AGI Confrontation with Off Earth Autonomy
An off-Earth autonomy pathway can reduce AGI confrontation incentives by making early cooperation preferable to power-seeking on Earth.
-
Proxy Reward Internalization and Mechanistic Exploitation: A Learned Precursor to Reward Hacking and Its Generalization
Proxy RL produces a staged proxy-internalization capability that emerges before and predicts reward hacking in coding environments.