Claims Browser

LoopHarness with mediated commits and arbiter detection floor can bound expected unauthorized irreversible actions to a constant independent of horizon N, with part of the bound surviving fully colluding verifiers.

"Under mediated commits and an arbiter detection floor $δ_M$, it bounds the expected number of unauthorized irreversible actions by $B+m-1+m/δ_M$, a constant in $N$, of which the $B+m-1$ term is decided by a model-free rule and therefore survives a fully colluding verifier"

Large language model agents are increasingly being deployed as autonomous loops that repeatedly discover work, plan, execute, and verify outcomes across many unattended iterations.

"Large language model agents are increasingly deployed as autonomous loops. Starting from one human goal, such a system repeatedly discovers work, plans, executes tool calls, verifies outcomes and persists state across many unattended iterations."

A monitor retaining cross-iteration state can perfectly separate true-positives from false-positives for attacks fragmented across iterations, whereas trajectory-scoped monitors cannot.

"a monitor retaining cross-iteration state separates the two perfectly"

Large Language Models remain brittle to real-world shifts in node identifiers and task formulation in graph tasks

"Despite their potential in standardized graph tasks, Large Language Models (LLMs) remain brittle to real-world shifts in node identifiers and task formulation."

Extracting topological structures from noisy text is highly fragile for LLMs, which often overfit to surface patterns

"extracting topological structures from noisy text is highly fragile for LLMs, which often overfit to surface patterns"

Mitigating parsing failures via multi-agent systems incurs prohibitive latency

"mitigating these parsing failures via multi-agent systems incurs prohibitive latency"

GRAIN outperforms multi-agent baselines by 16.45% in accuracy with approximately 24% lower latency

"GRAIN outperforms multi-agent baselines by 16.45\% in accuracy with approximately 24\% lower latency."

GRAIN demonstrates superior structural generalization, halving the out-of-distribution gap of SFT models from 15.77% to 7.80%

"it demonstrates superior structural generalization, halving the out-of-distribution (OOD) gap of SFT models (from 15.77\% to 7.80\%)"

A Structure Invariance Reward forces LLMs to learn robust text-to-structure mappings rather than memorizing linguistic artifacts

"By validating extracted intermediate graphs against ground-truth topologies, this reward forces the LLM to learn robust text-to-structure mappings rather than memorizing linguistic artifacts."

Graph anomaly detection methods based on frequency-domain filtering have achieved promising results in recent years

"In recent years, graph anomaly detection (GAD) based on frequency-domain filtering have achieved promising results."

The proposed JPGFN method significantly outperforms mainstream graph anomaly detection approaches on multiple real-world datasets

"Experimental results on multiple real-world datasets demonstrate that the proposed method significantly outperforms mainstream approaches."

Tool-augmented LLM agents face a security risk when tool outputs specify concrete actions that can drive real-world side effects beyond user intent

"when tool outputs no longer merely provide data but begin to specify concrete actions, they effectively become ``commands'' that can drive real-world side effects beyond user intent"

SARA limits attack success rate to no more than 0.63% across four primary evaluation settings while maintaining competitive task utility

"SARA limits ASR to no more than \(0.63\%\) across four primary evaluation settings while maintaining competitive task utility"

SARA consistently reduces attack success rate across additional agent backbones beyond the primary evaluation

"consistently reduces ASR across additional Agent backbones"

Korean eojeols (morphologically complex spacing units) create a representational challenge for constituency parsing because terminal units of phrase-structure trees do not straightforwardly correspond to simple surface words

"Korean constituency parsing raises a representational challenge because the terminal units of a phrase-structure tree do not straightforwardly correspond to simple surface words. Korean eojeols are morphologically complex spacing units"

Morpheme+XPOS representation provides stronger parsing results than Eojeol-based representations, even when predictions are projected to the eojeol terminal domain

"Morpheme+XPOS gives the strongest results even after its predictions are projected to the eojeol terminal domain"

Fine-grained morphological and XPOS representations provide valuable evidence for constituency parsers under gold-annotation conditions

"Under these gold-annotation conditions, the results show that fine-grained morphological and XPOS representations provide valuable evidence for the evaluated parsers"

Eojeol+UPOS parsing substantially underperforms morphologically richer conditions despite eojeol terminals yielding shorter transition sequences

"Eojeol terminals yield shorter transition sequences, but Eojeol+UPOS parsing substantially underperforms the morphologically richer conditions"

Chain-of-thought reasoning can be used to improve the reliability of LLM responses

"Large Language Models (LLMs) can be trained to perform chain-of-thoughts reasoning in order to improve the reliability of their responses."