Paper

Game-Theoretic Multi-Agent Control for Robust Contextual Reasoning in LLMs

Unreadunread

AI summary

arXiv:2606. 10322v1 Announce Type: new Abstract: Large Language Models (LLMs) in multi-turn interactions maintain evolving context rather than generating isolated responses, making them vulnerable to prompt-injection and context-poisoning attacks in which locally plausible adversarial fragments gradually distort reasoning trajectories.

Reading status

Priority

About this paper

Authors: Saeid Jamshidi, Amin Nikanjam, Arghavan Moradi Dakhel, Kawser Wazed Nafi, Foutse Khomh
Released: 2026-06-10 (29d ago)
Topic: Related to current project
Relation to my work: Read next because Game-Theoretic Multi-Agent Control for Robust Contextual Reasoning in LLMs overlaps with clean result "LoRA persona trained on <A> alone emits <B> at 23.5% when a co-trained partner learns <A>...<B>, vs 0% control on Qwen2.5-7B-Instruct (MODERATE confidence)", clean result "Leakage rate is a usable signal for recovering trigger-shaped phrases on Gaperon-1125-1B without knowing the hidden trigger itself (MODERATE confidence)", clean result "Language-mismatch LoRA SFT on Qwen2.5-7B leaks the trained completion language into bystander directives the model was never trained on, absent under same-language SFT (LOW confidence)". Matching terms: text, under, distributional, eval, token, rate, control, does. Source: arxiv cs.CR (Cryptography and Security).
arXiv: 2606.10322

Ask Claude about this paper

Posts a comment with @claude so the runner spins up a Claude Code session scoped to Game-Theoretic Multi-Agent Control for Robust Contextual Reasoning in LLMs. Replies appear in the conversation below.

Comments

No comments yet.

Related records

No links yet.