Metraipolis › archive › dc_ce2ab486d1a7

Understanding and Exploiting Initialization Anchoring Weakness in Feedback-Based Agent Planning — arXiv:2609.29697

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.29697
License (as archived)
CC0-1.0
Archived
2026-10-08T04:27:42.843Z
SHA-256 of the archived text
5fe056f6b736663cf6703cd6fc619795c490acf7d8c5bb79b33c53e4cadeee6c
Stable URL of this page
https://metraipolis.com/documento/dc_ce2ab486d1a7

How to cite

Understanding and Exploiting Initialization Anchoring Weakness in Feedback-Based Agent Planning — arXiv:2609.29697 — arXiv (en), https://arxiv.org/abs/2609.29697 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ce2ab486d1a7 (Metraipolis archive dc_ce2ab486d1a7, sha256 5fe056f6b736663cf6703cd6fc619795c490acf7d8c5bb79b33c53e4cadeee6c)
BibTeX
@misc{dcce2ab486d1a7,
  title = {Understanding and Exploiting Initialization Anchoring Weakness in Feedback-Based Agent Planning — arXiv:2609.29697},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.29697},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ce2ab486d1a7; sha256 5fe056f6b736663cf6703cd6fc619795c490acf7d8c5bb79b33c53e4cadeee6c},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.29697. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Feedback-based planning improves agent reliability by incorporating tool observations and corrective feedback. However, its protection may not be distributed uniformly across planning stages. We conduct a round-wise analysis of four representative feedback mechanisms and uncover an initialization anchoring weakness: the first feedback round corrects 46\% of adversarial directions, whereas the rates fall to 13\% and 7\% among directions surviving into the next two rounds. Our analysis attributes this weakness to three interacting factors: a contextually plausible shift in the initial plan, insufficient counterevidence, and the persistence of accepted directions in the accumulated trajectory. Based on these findings, we propose \textsc{InitAnchor}, a black-box framework for exploiting this weakness through attacker-controlled external materials. It operationalizes the three factors as directional-shift, contextual-plausibility, and counterevidence-resilience signals under either limited target access or no target access. Across 112 tasks from 16 domains, six agent architectures, and five backbone LLMs, \textsc{InitAnchor} achieves average ASRs of 76.1\% and 72.0\% under the two settings while reducing first-round mitigation rates to 21.0\% and 25.0\%, respectively. It also remains effective against six defenses and across six real-world agent systems. These findings show that feedback-based agents can retain early biases even when later correction is available.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-25 in cs.AI).
Categorie arXiv: Cryptography and Security (cs.CR) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.29697 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-08T03:50:58.134Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-25?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).