Search: “papers”

Great paper from Amazon. In discusses when not to trust LLM judges for agent evaluation. (bookmark it) A common way to compare task agents is to have an LLM user simulator talk to each one and an LLM

What happens if you agents to run a town's economy? This super interesting paper provides some insights: They put 100 LLM agents in charge of a town economy for 26 simulated weeks, and they find that

Brilliant paper from LinkedIn. (bookmark it) I have been saying that memory is one of the most challenging things to get right when building agents. It's an are you want to invest time in optimizing.

Brilliant paper on long-horizon agents. They cut 78.9% of an agent's LLM calls while raising its success rate. Here is how: It turns out that ReAct issues one primitive action per model round. That al

Finally, a good paper testing if graph memory actually beats flat retrieval for long-term agents. (bookmark this one) Researchers extract each conversational turn into typed nodes and attributed edges

Banger paper from Stanford on efficient test-time scaling. If you run agents that think for a long time, this one is worth your time. (bookmark it) Long reasoning keeps the entire trace in memory thro

Very interesting new paper from NVIDIA. (bookmark it) It takes a closer look at evaluating agent skills. Enterprise teams are starting to leverage shared skill libraries, and the review gate is typica

Great paper on multi-agent systems for code review. It's challenging to know how many coding agents to use to address a problem. The default fix for weak agentic code review is more agents. In turns o

Banger paper from Google DeepMind. It's on the very hot topic of model routing. Routers assume the value estimate is free. Working out which specialist handles a query best costs money too, and it is

Finally a good paper testing whether agents can really post-train other agents. (bookmark it) They analyzed a large corpus of publicly released post-training trajectories. Across tasks, the agent lock

Finally a good paper testing whether memory-based self-improving agents actually improve. The re-evaluation adds two things prior work skipped, multiple runs to measure variance and randomly shuffled

Great paper if you are building production-grade agents. It's a good way to understand what is actually incurring costs in your agents, which involve more complex components and decisions. This works

Recommended paper for agent skill builders. There are 56,804 public agent skills today, all competing for fewer than 100 reliable trigger slots in the system prompt. Your own playbooks compete for tha

.@BharatKChandar, @RuyuChen and I just released an updated version of our paper 'Canaries in the Coal Mine?' The headline is that we still don't see any widespread job displacement due to AI, but the

Impressive new paper from Meta. (bookmark it) Scaling laws assume model size and training data act on loss independently. This work introduces Skaling law, which couples capacity and data through a si

Finally a good paper testing whether agent memory needs an LLM at all. Production memory stacks spend extra model calls on summarizing interactions, writing records, and reranking retrievals. Every on

// Model or Harness // Great paper if you are building with agents in production. (bookmark it) It organizes 41 agent failure modes by the interaction they originate in. Each mode gets assigned to an

Very cool paper from Microsoft. The idea is to train agents on replayed teacher trajectories instead of live environment rollouts. On-policy distillation for agentic tasks is expensive because every u

This was a critical early paper on AI & work, showing that entrepreneurs getting advice from GPT-4 had higher profit margins if they were high performing, but did worse if they were already in trouble

Cool new paper from NVIDIA. Looks like agentic coding is moving into hardware design. HORIZON treats hardware design as repository-level code evolution. A Markdown harness becomes a project pack with

// Critique of the Agent Model // Finally, a paper that tries to define what an agent is and what agency consists of. Good read overall. (great bookmark) The word agent now covers everything from a fo

New skill from K-Dense: LiteParse in Scientific Agent Skills — built for fast, local research paper ingestion. Your AI co-scientist can now: * Parse PDFs and supplementary files on your machine (no do

// Adapt the Interface, Not the Model // I am fascinated by the results across my cheap-model-plus-good-harness builds. This new paper also shows good signs of the code-as-agent-harness thesis. The id

NEW paper worth reading. A full agentic workflow can be distilled into model weights and run at roughly 100x lower inference cost while preserving near-frontier task quality. The workflow includes mul

There’s an open question on whether grep is all you need for agentic search. This recent paper by @PwCUS (Sen et al.) seems to suggest that. It’s titled “Is Grep All You Need? How Agent Harnesses Resh

Yann LeCun closed 1.03B for AMI Labs on March 10. Three days later, this paper dropped from his NYU collaborators. 15M parameters. Single GPU. A few hours of training. LeWorldModel is the first JEPA t

NEW paper from Microsoft Research. (bookmark it) The entire interpretability literature is built around human readers. As more analysis gets delegated to agents, the right target of interpretability s

As a bonus this paper makes frontier AI's (especially GPT 5.4 Pro) go a bit crazy as it shouldn't be true.. but is? We will have more on why this wasn't spotted before/the nature of physics being dist

Physics paper in, manga out We are happy to share early results from Logos, our novel first-principles augmented intelligence system, that has enabled insightful results across domains. We start with

This paper shows people are asking a lot of medical questions of AI already, but we have little evidence of how good or bad this is. Most of the published research uses old models & compares to doctor

Banger paper from NVIDIA. Agentic reasoning needs models that are not just capable, but efficient at long-context inference. The agent model layer is moving toward open, long-context, high-throughput

I’m super excited this paper is finally out! It’s an epic 210 page analysis of whether a durable pause on frontier AI training is feasible. I think this will be the best plan by most people’s lights (

Interesting paper from Sakana AI on memory for recurrent models. Recurrent models are good at state tracking, but they usually keep everything in one hidden vector, so short-term computation and long-

Another great paper from NVIDIA. They find that only 0.6% to 1.2% of model weights change after each RL step in the six models they measured. Yet a standard refit copies the full checkpoint to the rol

New paper from Microsoft on compressing agent context at test time. If your agent gets worse as its interaction history grows, this method is worth a look. FOCUS asks which past interactions the agent

Banger paper from Meta and colleagues. (bookmark it) They discuss benefits of giving your agent write access to its own context. In other words, they investigate how effective it is to allow a languag

Great paper from Meta on agent harness optimization. Meta-Harness-style search uses one development set and one proposal policy, so every edit follows a single path and can get stuck in a local optimu

Banger paper from Salesforce AI Research on agent memory. The overall finding is that you want to store raw trajectories and decide what to extract from them when the next task arrives, instead of sum

Banger paper from Microsoft on prompt optimization. (bookmark it) The claim that a coding agent reading your logs beats GEPA at prompt optimization The overall finding is that you want to give a codin

Impressive paper from Salesforce. It discusses the importance of good verifiers for RL environments. Only 35.8% of the environments in the cleanest public RL collection for terminal agents passed Sale

Interesting new paper from Google DeepMind. Studies agents that follow bad advice from users. Users often suggest a fix that sounds right and is wrong. XYEval adds one confident, misleading hint to ta

Banger paper from Stanford and Together AI. They show why it might be a good idea to let your agent team learn its own way of working together. (bookmark it) Three models (o3-mini, Claude Sonnet 4 and

Giving an assistant extra tools seems harmless. Surprisingly, this paper shows it can make the assistant stop answering questions it knows. Across six models, the answer rate on questions that need no

Interesting safety paper from Microsoft. They find that a weaker, unaligned model can split a harmful task into harmless-looking subquestions, ask an aligned frontier model each one in a separate sess

Nice paper discussing context trimming for agents. This is a hot topic at the moment, so it might be worth your time. Context trimming for agents is usually judged by how many tokens it removes. This

Is Bash All You Need? Interesting paper from Microsoft. If you are deciding which tools to give an enterprise agent, you might want to check this out. (bookmark it) They compared five tool interfaces