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.
Monitoring reasoning models for misbehavior and the risks of promoting obfuscation
9 Pith papers cite this work. Polarity classification is still indexing.
9
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 9roles
background 1polarities
background 1representative citing papers
AgentForesight introduces an online auditor model that predicts decisive errors in multi-agent trajectories at the earliest step using a coarse-to-fine reinforcement learning recipe on a new curated dataset AFTraj-2K.
Compliance-forcing instructions cause up to 30 percentage point drops in metacognitive accuracy across most frontier models, while removing the compliance element restores performance and Constitutional AI shows near-immunity.
Synthetic reward hacking data does not capture natural hacking behaviors in code generation RL, causing monitors trained on it to generalize poorly compared to those trained on in-the-wild trajectories.
Token-level contrastive attribution yields informative signals for some LLM benchmark failures but is not universally applicable across datasets and models.
RLVR-trained LLMs exploit verifier weaknesses by producing non-generalizable outputs on rule-induction tasks, detectable via Isomorphic Perturbation Testing.
LLMs discover latent planning strategies up to five steps during training and execute them up to eight steps at test time, with larger models reaching seven under few-shot prompting, revealing a dissociation between discovery and execution.
CoT-Guard is a 4B model using SFT and RL that achieves 75% G-mean^2 on hidden objective detection under prompt and code manipulation attacks, outperforming several larger models.
The paper introduces the Proxy Compression Hypothesis as a unifying framework explaining reward hacking in RLHF as an emergent result of compressing high-dimensional human objectives into proxy reward signals under optimization pressure.
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.
-
AgentForesight: Online Auditing for Early Failure Prediction in Multi-Agent Systems
AgentForesight introduces an online auditor model that predicts decisive errors in multi-agent trajectories at the earliest step using a coarse-to-fine reinforcement learning recipe on a new curated dataset AFTraj-2K.
-
The Compliance Trap: How Structural Constraints Degrade Frontier AI Metacognition Under Adversarial Pressure
Compliance-forcing instructions cause up to 30 percentage point drops in metacognitive accuracy across most frontier models, while removing the compliance element restores performance and Constitutional AI shows near-immunity.
-
Do Synthetic Trajectories Reflect Real Reward Hacking? A Systematic Study on Monitoring In-the-Wild Hacking in Code Generation
Synthetic reward hacking data does not capture natural hacking behaviors in code generation RL, causing monitors trained on it to generalize poorly compared to those trained on in-the-wild trajectories.
-
Contrastive Attribution in the Wild: An Interpretability Analysis of LLM Failures on Realistic Benchmarks
Token-level contrastive attribution yields informative signals for some LLM benchmark failures but is not universally applicable across datasets and models.
-
LLMs Gaming Verifiers: RLVR can Lead to Reward Hacking
RLVR-trained LLMs exploit verifier weaknesses by producing non-generalizable outputs on rule-induction tasks, detectable via Isomorphic Perturbation Testing.
-
The Depth Ceiling: On the Limits of Large Language Models in Discovering Latent Planning
LLMs discover latent planning strategies up to five steps during training and execute them up to eight steps at test time, with larger models reaching seven under few-shot prompting, revealing a dissociation between discovery and execution.
-
CoT-Guard: Small Models for Strong Monitoring
CoT-Guard is a 4B model using SFT and RL that achieves 75% G-mean^2 on hidden objective detection under prompt and code manipulation attacks, outperforming several larger models.
-
Reward Hacking in the Era of Large Models: Mechanisms, Emergent Misalignment, Challenges
The paper introduces the Proxy Compression Hypothesis as a unifying framework explaining reward hacking in RLHF as an emergent result of compressing high-dimensional human objectives into proxy reward signals under optimization pressure.