• GraphEcho's controlled experiments vary the number of graph paths and where evidence originates while holding the evidence's actual content fixed, isolating whether agents treat repeated encounters as independent corroboration.
• Redundant supporting paths increased the share of repeated walks across every frozen agent tested, though the effect on agents' actual judgments was model-dependent rather than uniform.
• Provenance-aware post-training (PAPT) cuts both repeated revisits and the number of distinct sources an agent reaches — on synthetic claims it also raises accuracy, but on real scientific claims it keeps reducing repetition while accuracy actually declines.

• LLM — A large language model — the neural network behind tools like Claude and ChatGPT, trained on huge amounts of text to predict what comes next.
• AI agent — An AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.
• RAG — Retrieval-augmented generation — fetching relevant documents first and pasting them into the model's context so it answers from your data instead of memory.

Reveals a concrete failure mode in graph-based agent reasoning: agents can learn to stop repeating paths while still missing distinct evidence they need, relevant to anyone building RAG or multi-hop agent pipelines.

• articleWhy Better Models Can Create Riskier Systems: Evidence from LLM Agents in Financial MarketsJillian Ross, Eric So, Zoe De Simone, Charles Pozniak, Andrew W. Lo
• articleEpistemic Sybil Resistance: Multiplying AI Agents Without Multiplying EvidenceMarc Bara
• articleWhen May an Agent Stop? Evidence-Carrying Termination for Tool-Using LLMsJason Liu

Checking sign-in…

Loading comments…