AI Research Radar

Directional Alignment Mitigates Reward Hacking in Reinforcement Learning for Language Models

SEC-bench Pro

“Our evaluation shows that coding agents with frontier models remain below 40% success on both evaluated engines.”

Blind PRNG Hijacking

“Across three watermarking schemes and three open-source LLMs, the attack triggers 0/6 state-of-the-art content-side statistical detectors while inflating the watermark z-score up to 2.42x (system-level defenses such as entropy-source attestation remain orthogonal and complementary).”

JT-SAFE-V2

“Extensive evaluations demonstrate that JT-Safe-V2 achieves state-of-the-art performance across both general intelligence and safety benchmarks.”

Hallucination as Exploit

“A HACR audit on 500 stratified task keys shows that unsupported action-critical claims reach unsafe execution for naive agents (100.0%) and prompt-only defenses (49.6%), but not for ECA.”

DiscoverPhysics

“Across eleven frontier models, we find that the strongest agents pass only half of the worlds and consistently fail on those where latent structure must be uncovered.”

Plant, Persist, Trigger

“Experiments on seven strong open-source and closed-source LLMs show that state-of-the-art LLM agents remain vulnerable to Sleeper Attack, even when they achieve low attack success rates under a single-interaction baseline.”

Transformers Provably Learn to Internalize Chain-of-Thought

“Experiments on multi-layer transformers confirm the theory and visualize how reasoning is progressively absorbed into deeper layers.”

Alignment Tampering

“Our experiments demonstrate amplification across diverse biases: from keyword bias to propaganda (e.g., sexism), brand promotion, and instrumental goal-seeking.”