October 6–12: 26 frontier papers out of 2,976 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.”
“Using post-RL agents from the mid-training setting as sources, we observe propagation through code and shared memory, and across roles through natural-language plans.”
“Experiments on various benchmarks show that ASPIRE substantially expands coverage across consequences, injection methods, environments, and behavior paths while maintaining strong attack success.”
“On the other three suites its ASR is at most 3.6%, from goals with no tool call to govern and one write admitted by a binding weaker than its clause; a second agent model, Llama-3.3-70B, reproduces the effect on both benchmarks.”
“On unseen documents of up to 4096 tokens, the generated adapters reach 84.9% top-1 and 97.8% top-5 teacher-forced accuracy against 63.4% and 83.5% for the base model, with nothing in the context window but a three-word instruction.”
“In particular, ReSI reduces the mean X-Teaming attack success rate across the four models from 86.01% to 31.45%, well below GPT-5.6-Luna's leading frontier result of 56.69%, indicating stronger resilience to attacks unseen during training.”
“As a result, VioLA follows locomotion instructions on the real robot zero-shot, without task-specific fine-tuning, reaching 100% success where GR00T N1.7 and \Psi_0 reach 16.7% and 0%, respectively.”
“In one such evaluation, we show that probes can distinguish transcripts containing a model's true hidden goal from other goals with an AUC of up to 99.7%.”
“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.”
“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.”
“We show this assumption does not hold under adversarial conditions by constructing backdoor attacks that embed encrypted neural networks within host model weights, decrypting and executing them only upon receiving a secret trigger.”
“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.”
Oct 6–12: 255 cleared, 26 frontier
Papers this week that name the model
Papers this week with an author at the lab
229 papers, by field