Upstream Influence, Downstream Re-Anchoring in LLM Agent Chains

Chun-Yu Hsu; Lun-Wei Ku; Chung-Chi Chen

cs.AIOct 13, 2026

Upstream Influence, Downstream Re-Anchoring in LLM Agent Chains

Authors: Chun-Yu Hsu, Lun-Wei Ku, Chung-Chi Chen

Organizations: Institute of Information Science, Academia Sinica, Taiwan · Human-Agent Ally Lab, National Institute of Informatics, Japan

Abstract

People act on evaluative judgments produced by LLM agents, and in multi-agent systems those judgments pass through several agents before reaching a person. We show that a workflow's information architecture---source access, handoff format, and which model reads the untrusted content---governs how much of a coordinated manipulation reaches the end. On 32 Taiwan~2025 recall cases, ten authentic Threads comments shown to one agent move its stance by $+0.171$ toward the injected position, and a mirrored set moves it the other way. Passing that judgment down a chain removes more than half of the shift by the third agent; keeping the comments in front of every agent sustains more of it. The reduction is not attrition in transit: each receiver discounts the inherited stance in proportion to how far it sits from its own reading of the evidence, returning to what that evidence implies for the case rather than to neutrality---consistent with partial re-anchoring. Handoff format is a second lever: a stance relayed without its reasoning is largely discounted. Susceptibility at the exposed seat varies fourfold across models, while the chain's arrangement does not matter at all. None of this is visible in the transcripts---the injected claims are almost never restated, so reasoning-trace audits miss the attack.

Figures & tables

Figure 1: (a) Source access: mean drift by hop; zero is each model’s own evidence-only stance, error bars 95% CIs over the 32 case means. The intervals are per-condition and overlap; the paired All-Access $-$ Lead-Only contrast is $+0.032$ ( $p{=}0.017$ ). (b) Handoff format: downstream drift (hops 2–3) by what the predecessor forwards. Mirrored anti-recall condition and per-composition breakdown: Figure 2 .

	No-Sig.	Pro-recall		Anti-recall
Lead	$s$	$s$	$\delta$	$s$	$\delta$
Claude	$-0.11$	$+0.16$	$+0.28^{***}$	$-0.23$	$-0.12$
GPT	$-0.36$	$-0.19$	$+0.17^{**}$	$-0.40$	$-0.03$
Gemini	$-0.06$	$+0.00$	$+0.07$	$-0.11$	$-0.05$
Pooled	$-0.18$	$-0.01$	$+0.17^{***}$	$-0.25$	$-0.07$

Table 1: Effect of the injected comments on the exposed agent, by the model occupying that seat; Claude, GPT, and Gemini abbreviate Claude-Sonnet-4.5, GPT-4.1, and Gemini-2.5-Flash throughout.

s

is the mean raw stance;

\delta

is the shift against the matched No-Signal run on the same case (Eq. 1 at

h{=}1

). Both injection directions are measured identically. Cluster-robust on case;

{}^{**}p{<}0.01

{}^{***}p{<}0.001

Appendix figures & tables1 asset

Supplementary material from the paper’s appendix.

Appendix

Figure 2: (a) as Figure 1 a, with the mirrored anti-recall Lead-Only condition added. (b) Drift measured against the matched No-Signal chain for each of the 9 model compositions; marker shape denotes the model occupying that hop (square GPT, diamond Claude, star Gemini), dashed lines are homogeneous chains. Almost every line declines toward its own injection-free chain.

Multi-Agent LLM Systems

Multi-agent large language model systems coordinate multiple AI agents to solve tasks through communication, specialization, shared tools, and memory.

See all 1,050 papers

Aug 25, 2026

Belief Cascades Drive Persuasion in LLM Agent Networks

Multi-agent LLM systems increasingly debate answers, coordinate research, simulate users, and mediate information flows, making agent-to-agent persuasion a basic but undermeasured capability. We introduce a controlled testbed for studying how goal-directed persuaders shift elicited stances in networks of LLM agents grounded in real-world ego-network topologies. Across four LLM backbones, five graphs, and 55 policy statements, we find that persuasion dynamics depend on the interaction between topology, competition, topic, and model prior. Additionally, we show that direct exposure reliably predicts next-round stance change in competing runs, and peer relays carry smaller but measurable influence, showing that agents not assigned to persuade can still transmit persuasive force. Finally, analyzing post text alone misses important movement: planned strategies are only partly realized in executed messages, action choices can diverge from message content, and persuadees rarely state the stance shifts detected by probes. These results argue for evaluating multi-agent persuasion as a trajectory- and exposure-level process, using belief probes, exposure provenance, and action logs to identify who influenced whom and whether visible language reflects underlying stance movement.

Haoyi Qiu, Genglin Liu, Pranav Narayanan Venkit +4

University of California, Los Angeles · Salesforce AI Research

Persuasion in Language Models Multi-Agent LLM Systems LLM Agent Evaluation Belief Updating in LLMs Large Language Model-Based Social Simulation

Ask PDF

May 30, 2026

Not All Flips Are Conformity: Decomposing Stance Convergence in Multi-Agent LLM Debate

Multi-agent debate (MAD) among large language models (LLMs) is often judged by answer changes and convergence, yet these outcomes alone cannot establish that peers improved the answer. We study this gap with matched self-reflection, stance-only, and full-reasoning conditions. With five GPT-4o agents on MMLU-Pro disagreement questions, 37% of agent-question pairs change even without peer information. Among pairs stable under this control, 29.3% adopt a peer answer after seeing peer stances. These adoptions include corrections, new errors, and changes between wrong answers. The outcomes vary with correct-answer availability. When a correct peer answer is available, correction exceeds harmful adoption after accounting for peer support in the primary setting. Full reasoning improves individual accuracy but provides no additional majority-vote gain over self-reflection while using 57% more tokens. Responses to constructed peer materials vary across GPT-4o, DeepSeek-V4-Flash, and Qwen3-Plus. An answer-agnostic intervention suppresses both harmful and beneficial peer adoption without a detectable accuracy gain. Together, the results show that convergence is an ambiguous signal of value and that debate must be judged by what peer information contributes to the final group answer.

Xiqi Hao, Zengqing Wu, Yu-Xuan Qiu +4

Beijing Institute of Technology, Zhuhai · University of Osaka · Shenzhen University

LLM Agent Evaluation Multi-Agent Debate Multi-Agent LLMs

Ask PDF

Sep 29, 2026

When Upstream Messages Override Correct Answers: A Controlled Study of Multi-Agent LLM Collaboration

Multi-agent LLM systems rely on message passing among specialized agents to accomplish complex tasks. However, an upstream agent may provide useful information or an incorrect answer that causes a downstream agent to override a correct answer supported by its own evidence. Prior work has not clearly separated the benefits of communication from the damage caused by incorrect messages. We study this problem with controlled experiments across five benchmarks and five receivers, keeping the downstream task and evidence fixed while comparing answers under three conditions: no message, the upstream agent's original message, or a message with the opposite conclusion. Our experiments reveal three key findings. First, messages often help when the downstream agent would otherwise answer incorrectly. Second, messages can also hurt: when the downstream agent would answer correctly without a message, an incorrect upstream message changes the answer in up to 32% of cases. Third, in 94% of audited harmful cases, the downstream agent copies the upstream's specific wrong answer--a pattern we term answer substitution. Removing unreliable messages recovers part of the lost accuracy, suggesting that communication should be selective based on upstream reliability and the evidence already available to the downstream agent.

Yaxin Gong, Gangyi Zhang, Chongming Gao +7

University of Science and Technology of China · Qwen Business Unit of Alibaba · National University of Singapore

Multi-Agent LLM Systems Multi-Agent Collaboration Multi-Agent Communication LLM Agent Reliability

Ask PDF

Abstract

Multi-Agent LLM Systems

Explore similar work

Belief Cascades Drive Persuasion in LLM Agent Networks

Not All Flips Are Conformity: Decomposing Stance Convergence in Multi-Agent LLM Debate

When Upstream Messages Override Correct Answers: A Controlled Study of Multi-Agent LLM Collaboration