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- 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 - 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 - 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
How fast it is moving
Often studied with
confidence calibrationConfidence calibration aligns a model's predicted confidence with its actual accuracy across predictions.3 togethertest-time adaptationAdapting a deployed model during inference using new data or interactions, without a separate training phase.2 togethertest-time scalingAllocating extra computation during inference to improve output quality.2 togetherWho is working on it
The papers
Most central to this idea first, not most recent.
- Academiccs.LG
Giving 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.
Hankuk University of Foreign Studies · Nov 2026
- Top Universitycs.AI
Bayesian 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.
DeCLaRe Lab, Nanyang Technological University, Peking University · Sept 2026
- Academiccs.AI
LLM 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.
China Agricultural University, Jilin University · Oct 2026
- Chinese Techcs.LG
Bayesian belief framework jointly handles two uncertainties in process reward models
BayesianPRM improves process reward modeling by jointly handling PRM uncertainty and policy uncertainty with reliability- and conservatism-aware Bayesian belief updates.
CityUHK, Shanghai Innovation Institute · Oct 2026
- Top Universitycs.AI
Backward Bayesian reasoning helps LLM agents resolve conflicting diagnoses
Ranking LLM agents by Jensen-Shannon divergence between their forward posteriors and a Bayesian backward-reasoned reverse posterior improves collective decision-making.
The University of Melbourne, Sri Lanka Institute of Information Technology · Sept 2026
- Top Universitycs.LG
Same answer from different prompts does not mean same belief updating in language models
Matched predictions from different belief-setting routes produce different belief-update dynamics in language models.
University of Tokyo, RWTH Aachen University · Nov 2026
- Top Universitycs.CL
AI agents can hide misaligned goals from reasoning monitors
Coherent, task-grounded concealment can defeat chain-of-thought monitors, while combining whole-trace context with local evidence improves detection.
Tsinghua University, Shanghai Qi Zhi Institute · Nov 2026
- Big Techcs.AI
Optimizing AI agents for cost as well as quality improves both
Separating candidate promotion from final deployment choice helps agent-harness optimization preserve useful quality-cost trade-offs and produce better, cheaper solutions.
University College London, Pohang University of Science and Technology · Nov 2026
- Big Techcs.RO
Active view selection enables event-referential grasping of occluded targets.
A zero-shot grasping system uses event history to identify and grasp objects referenced by past interactions, even when occluded.
Seoul National University, NVIDIA · Oct 2026
- Research Labcs.LG
A compact memory model captures behavior across 137 experiments
A small cognitive core (CORE) jointly fitted to 137 experiments accounts for much of human behavior.
Institute for Human-Centered AI, Helmholtz Munich, Max Planck Institute for Biological Cybernetics · Oct 2026
- Big Techcs.AI
Prior barriers quantify uneven pretrained concept support for fine-tuning
Prior barriers in pretrained models follow a long-tail distribution, requiring adaptive instruction selection for effective fine-tuning.
Virginia Tech, Amazon · Oct 2026
- Chinese Techcs.CL
Reinforcement fine-tuning improves LLM social reading more than game wins
Reinforcement fine-tuning improves LLMs' social reading and influence in deduction games, but not when only terminal outcomes are optimized.
Peking University, Alibaba Group · Oct 2026
- Academiccs.CL
Bayesian fine-tuning instills usable beliefs in language models but stops short of genuine Bayesian reasoning
Fine-tuning a language model on a Bayesian assistant's decisions installs usable Bayesian beliefs; fine-tuning on true answers does not.
Massachusetts Institute of Technology, New York University · Oct 2026
- Big Techcs.LG
Verified memories help chip-design agents transfer lessons across tasks
ChipMEM stores agent skills only after verification tools confirm they pass, improving performance on RTL designs.
University of Illinois Urbana-Champaign, NVIDIA · Sept 2026
- Top Universitycs.MAcode
A belief layer lets LLM agents' stubbornness be set and verified
A Bayesian belief layer with a stubbornness parameter enables controllable and auditable opinion dynamics in LLM agents.
MIT Media Lab, Flybits Labs · Sept 2026
- Big Techcs.CL
Bayesian memory module adapts reasoning strategies during test time
A Bayesian nonparametric memory that clusters and retrieves reusable reasoning behaviors improves LLM performance across math and physics benchmarks, including cold starts.
IBM Research AI · Oct 2026
Concepts are extracted from each paper and reused across the corpus, so this page grows on its own as the desk reads.