← All concepts

bayesian update

A Bayesian update is a way to improve a guess as new evidence comes in. You start with a prior belief, then weigh each new piece of information by how reliable it is, and adjust your belief accordingly. The more trustworthy the evidence, the more it shifts your view; unreliable evidence barely changes it. This lets you gradually home in on the truth without overreacting to noise.

Across the papers, Bayesian updates are used to combine information from multiple sources in a principled way. Whether fusing advisor opinions in multi‑agent systems, aggregating LLM answers, or guiding a robot that tracks objects from past events, the common thread is managing uncertainty. The approach outperforms simpler methods like majority voting or end‑to‑end learning by explicitly modeling reliability, reversing the direction of reasoning, or adjusting for overconfidence. This makes the systems more robust to misleading input and more transparent about how beliefs form.

Papers
16
Released code
1
First seen
Sept 2026
Latest
Nov 2026

15 papers in the last two months, against 1 in the two before.

Start here

Three papers to read first, in the order they came out
  1. 1Bayesian reliability memory helps agents decide when to trust advice

    BaRe-Mem uses Bayesian updates from past interactions to estimate advisor reliability, which then guides consultation decisions and response weighting.

    Sept 2026
  2. 2LLM aggregators partly count restated evidence as new readings, measure shows

    LLM aggregators treat repeated evidence as partly independent, inflating confidence and triggering decisions unsupported by the underlying sources.

    Oct 2026
  3. 3Giving harder inputs more attempts helps little on hard LLM workloads

    Giving harder inputs more repeated attempts by an LLM pays off only when the budget is large relative to difficulty; otherwise the optimal allocation is inverted-U.

    Nov 2026

Who is working on it

Peking University 2NVIDIA 2

The papers

Most central to this idea first, not most recent.

Concepts are extracted from each paper and reused across the corpus, so this page grows on its own as the desk reads.