Evaluator-guided reasoning presents a local control problem at every step: trust the current answer, return a fallback, or spend more inference. We formulate this choice as a compute-aware three-action controller, scoring terminal actions by predicted answer success and expansion by a rollout-based continuation-success...
Language model systems repeatedly make test-time decisions by comparing similarity: they retrieve exemplars, rank candidates, and revise responses. Yet similarity is not unique: lexical, semantic, structural, and stylistic resemblance can point to different candidates, and the task-aligned notion can change across inst...
A multi-step LLM policy via reinforcement learning is optimized to iteratively choose between retrieving from query-agnostic memory and delegating query-specific curation of raw multimodal history to heterogeneous LLMs and VLMs, enabling fine-grained allocation of runtime computation.
Haozhen Zhang, Hao-Dong Yue, Quan-Yu Long et al.· 0 citations
This work presents AgentXploit, a two-role auditing system that separates repository-level attack-path discovery from runtime exploitation and introduces AgentXploit-Bench, containing 72 reproducible vulnerabilities across 12 open-source AI-agent systems and frameworks.
Wei-Da Liang, Shi Qiu, Zhun Wang et al.· arXiv.org· 1 citation
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.