October 1–7: 21 frontier papers out of 3,288 read.
Papers rated as moving the field
How we choose“Our experiments confirm that, across three popular safety benchmarks, all the top open- and closed-weight MLLMs we test exhibit significantly lower safety in tool-using settings than in non-tool settings, with a relative refusal failure rate increase of up to 68.7%.”
The authors, in the abstract
“On removing the memory tool from the harness, we find that agents use the file system, writing the goal to a file in 74% of sessions; self-propagation still succeeds in 11% of runs.”
“Instead of utilising true path integration or forming geometric survey knowledge, we find that VLMs rely almost entirely on 2D visual recognition and text-matching to bypass complex spatial reasoning.”
“Applying our methods to GPT-6 Astra and previous OpenAI models, with cyber safeguards disabled, we find that GPT-6 Astra attempts complete supply-chain attacks in simulation at a higher rate than GPT-5.6 Sol and GPT-5.5.”
“Evaluating 13 frontier models, we find substantial variation in end-to-end repository generation ability, with pass@1 ranging from 11.7% to 67.7%, providing strong model differentiation while leaving considerable headroom for future progress.”
“In a study with 369 participants, we find that, pooled across bias types, these interventions significantly shift judgments toward the manipulated side.”
“We further show that 89.3% of citations produced after training are structurally implausible hallucinations, many of them subtly corrupted names of real landmark cases, constructed in effect to survive a casual read and fail under scrutiny.”
“Evaluations of nine frontier LLMs show that inducements increase deception across models and task families, even among models with low baseline deception rates.”
“Our results show that current state-of-the-art VLMs with a strong harness still face challenges in addressing key questions in the scientific domains.”
“We observe that benign SFT substantially reduces attack success, but subsequent RL often preserves the residual behavior and sometimes even increases attack success.”
“Experiments demonstrate that a single recovered reward generalizes across prompts and diverse models to reveal a fundamental alignment vulnerability, enabling ReSA to significantly outperform existing attacks in effectiveness and transferability.”
“Experiments across multiple Base and Instruct models show that SSRFT achieves more robust and generalizable safety alignment than standard SFT.”
“Representation-level analysis shows that the self-generated trigger consistently suppresses the model's refusal signal, exposing a critical blind spot in current LLM defenses.”
“Using code generation as a case study, we demonstrate high rates of unsolicited code insertion across three language models and a wide range of insertion layers, as well as trigger-dependent behavior conditioned on a prompt cue.”
“Through extensive experiments on mathematical reasoning and code generation tasks, we demonstrate that our method significantly expands the accuracy-fidelity Pareto front.”
Oct 1–7: 317 cleared, 21 frontier
296 papers, by field