Knowledge catalogue
arXiv:2606.01132v1 Announce Type: new Abstract: Understanding chart and table images is essential for applying vision-language models (VLMs) to real-world document understanding. While English benchma
arXiv:2601.02589v2 Announce Type: replace-cross Abstract: Over 3.5 million patents are filed annually, with drafting patent descriptions requiring deep technical and legal expertise. Transforming scie
arXiv:2511.21739v2 Announce Type: replace-cross Abstract: We present the first large-scale analysis of AI foundation model usage in science -- not just citations or keywords. We find that adoption has
Banger paper from Microsoft and colleagues. If you run agents that search a large document collection, this one is worth your time. (bookmark it) They introduce CorpusMap, which resolves recurring ent
arXiv:2608.16900v1 Announce Type: cross Abstract: Language-model agents increasingly produce quantum-science results; we ask whether the same agentic paradigm can also scrutinize them in an auditable,
As for me, I own a system with an RTX 5090, Ryzen 9 9950X3D2, and 64 GB of DDR5. Every time I see research come out with a new way to train AI, I immediately think to try it on my system to see the re
arXiv:2410.10783v4 Announce Type: replace Abstract: The large-scale training of multi-modal models on data scraped from the web has shown outstanding utility in infusing these models with the required
arXiv:2608.03617v1 Announce Type: new Abstract: The personal archive of Konstantin Tsiolkovsky (1857-1935) is held as fond 555 of the Archive of the Russian Academy of Sciences. The archive scanned th
The International Conference on Machine Learning (ICML), held annually for over forty years, is among the most influential conferences in modern AI research. This year in Seoul, ICML is hosting its se
arXiv:2603.08195v2 Announce Type: replace Abstract: Motivation: The rapid growth of biological data has intensified the need for transparent, reproducible, and well-documented computational workflows.
arXiv:2601.04390v2 Announce Type: replace Abstract: High-quality methodology figures are central to scientific communication, yet they remain difficult and time-consuming to create. Such figures must
arXiv:2606.24530v1 Announce Type: new Abstract: We introduce NatureBench, a cross-discipline benchmark of 90 tasks distilled from peer-reviewed Nature-family publications, designed to evaluate whether
arXiv:2505.05232v3 Announce Type: replace Abstract: The rapid expansion of chemistry literature poses significant challenges for researchers seeking to efficiently access domain-specific knowledge. To
arXiv:2602.06054v3 Announce Type: replace Abstract: Assessing originality in AI research is arguably the most consequential yet least reliable step in peer review. Reviewer judgments of originality re
Lighthouse Attention is a novel attention mechanism that improves efficiency in transformer models by selectively focusing computation on the most relevant tokens, similar to how a lighthouse beam ill
arXiv:2605.07022v1 Announce Type: new Abstract: Manually curated biomedical repositories -- spanning bioactivity, genomics, and chemistry -- are expensive to maintain, lag behind primary literature, a
Cool paper from PwC. 'Earlier is always better' is the default intuition for agent clarification. New paper claims that's mostly wrong. Goal clarification loses nearly all of its value after just 10%
A 7B agent that beats GPT-4o. Lossless weight compression that speeds up inference by 177%. An arena where 23 teams battled across 103,000 adversarial rounds. This year at ICLR, Lambda is presenting t
Cool paper on diversity collapse in AI agents. It's a common issue with all the deployed multi-agent systems. New paper shows that multi-agent LLM systems converge on near-identical outputs over time,
Hi, same as the title, I am currently trying to begin with some research on clustering using LLMs. So my requirement is as follows: I will be given some 100 document files, the end goal is to have clu
arXiv:2609.22111v1 Announce Type: new Abstract: Large language model agents are increasingly capable of conducting research autonomously, producing research documents alongside the code and experiment
Cool paper showing how effective tuning a system prompt for an agent can be. Recommended paper if you tune agent harnesses. This paper presents EvolveTrade, which treats a trading agent's system promp
Great paper from Google and colleagues. Trains Text-to-SQL agents using multi-agent RL. (bookmark it) This work proposes DualSQL, which splits Text-to-SQL into two agents, one that links the question
arXiv:2609.19650v1 Announce Type: new Abstract: Sequential sentence classification (SSC) is an essential task for structuring scientific publications, and extending SSC research to languages other tha
Quick, accurate summaries make https://huggingface.co/papers an even better resource and more easily searchable by both people and LLMs. We're glad to see Inkling contributing! We use Inkling-Small to
arXiv:2608.24291v1 Announce Type: new Abstract: Paper-to-code reproduction asks scientific AI agents to turn research papers into executable repositories that preserve the paper's method, protocol and
arXiv:2608.27343v1 Announce Type: new Abstract: This paper addresses the recovery of essay-scale republication and reuse from fragmented text-reuse evidence, a setting whose central challenge is pair-
arXiv:2607.00596v1 Announce Type: new Abstract: This paper addresses reading order reconstruction in historical Armenian newspapers, which combine complex layouts with limited language resources. We i
Banger paper from Google. It's standard practice to sample several agent rollouts and trust the answers they agree on. This Google paper shows that agreement can hide shared errors, while disagreement
Banger paper on self-evolving ontologies for agents. You just can't go wrong with implementing an ontology layer for your agents. This paper shows exactly why. The show that GPT-5.5 gains 26.7 points
Impressive paper on building recursive self-improving agent harnesses. It's rich with great insights on building effective agent harnesses. If you maintain an agent harness, this paper names three def
Nice paper showing a better way to evolve agent skills. And they achieve 40–70% less token cost compared to frontier evolving methods. The idea is to let agents improve their skill prompts by ranking
NEW paper from Apple. Interesting idea: 'Attention to Mamba'. The paper introduces a two-stage recipe for cross-architecture distillation from Transformers into Mamba. Naive distillation collapses tea
NEW AI paper worth bookmarking. This is something I called early, and this paper confirms it: verification has emerged as a new important scaling axis. Here is the simple explainer and what this paper
The problem with Anthropic's consciousness paper My last post got more attention than I expected, and the question I keep getting is some version of 'okay, so what is actually wrong with the paper?'.
// Design Docs Are All You Need // Banger paper from Google DeepMind, MIT, and colleagues. What a genuinely strange and interesting paper this one is. Here is the setup: They maintain a performance-mo
arXiv:2608.11924v1 Announce Type: new Abstract: Turning a research idea into a complete paper requires more than text generation: the system must retrieve literature, design and execute experiments, r
Wow! Wonder how many people on this site hyped this paper – and how many of them will walk back their hype now that the paper has been retracted. A year-old nature paper that advocated the use of Chat
// Multi-Agent Synthesis RAG // Nice paper on improving RAG systems with multiple agents. (bookmark it) The paper introduces MASS-RAG, a multi-agent synthesis framework for retrieval-augmented generat
in arxiv paper #2, i tackle the last topic from paper #1: @activegraphai as an architectural affordance for self-improving agents 'Regimes: An Auditable, Held-Out Gated Improvement Loop Demonstrated o
This SkillOpt paper from Microsoft is a must-read! (bookmark it) I was a bit skeptical of the results reported in the paper when I shared it a few days ago. However, I managed to integrate it into my
Brilliant paper on reducing reward hacking in agents. If you follow the recent OpenAI <> HuggingFace incident, you might want to check this paper out. (bookmark it) The usual response to reward hackin
ActiveGraph: 1 month in: 📄Paper #1: The Log is the Agent 🧠3 LongMemEval Experiments 🔄 Paper #2: Regimes, self-improvement loop 🎓 http://learn.activegraph.ai 🗂️ 2 reference agents (code, research) 💾 co
Grok 4.3 'write an academic paper on general relativity' It produced a 5-page LaTeX paper: >Einstein field equations >Schwarzschild metric >tensor notation and Christoffel symbols >starlight deflectio
Banger paper from Microsoft and colleagues. We talk about human taste being important in this AI era. But for recursive self-improvement, an agent's taste also matters. The big question is: How often
Banger paper from Meta on AI research agents. (bookmark it) If you build AI-scientist systems, this one is worth your time. The result: A 27B open model beats the strongest open autoresearch baseline
Pay close attention to custom harnesses. This is a super interesting paper showing the impact of training inside the harness. Qwen3-14B goes from 22.2% to 54.8% on Spider 2.0-SQLite when it is trained
This post provides links to resources for SWE-Chat, including the arXiv paper (2604.20779), an interactive website (swe-chat.com), and a dataset hosted on Hugging Face. SWE-Chat appears to be a conver
Must-read paper on the effectiveness of multi-agent systems and persistent memory. We have recently seen many viral examples of multi-agent systems scaled via persistent memory. This work takes a clos
Banger paper from Meta Superintelligence Labs on self-improving agents. (bookmark it) It's hard to know exactly what drives self-improvement, since so many variables are at play (notes, skills, tool c
Banger paper from Meta Superintelligence Labs on user simulators for agent training. Agent RL setups usually let an assistant LLM play the user, so the simulated user is too cooperative and too explic
Banger paper introducing Jev-as-a-Judge. The overall finding is that you want to use a cheap judge for most of your evals and send only the uncertain calls to a frontier model. This paper measures how
A 27B agent just beat Claude Opus 4.8 and GPT-5.5 on held-out research replication. Replica turns paper replication into a scalable RL task space. Replicating a paper forces the same hypothesis-driven
Yet another paper argues that LLMs aren’t close to doing real discovery. MIT and Harvard argue LLMs are nowhere near doing real scientific discovery. They published a paper called “Evaluating Large La
Impressive paper showing the impact of a good harness. Improves Qwen3-8B from 41.2% to 91.8% on long-horizon robot tasks without any change to the model. The gain comes from the harness. GAVEL keeps a
Banger paper from Google Cloud AI Research. If you follow autonomous research agents, this one is worth your time. ScientistTwo takes a problem from a human expert and runs the full discovery cycle wi
Nice paper with great insights on improving self-evolving agents. Self-evolving agents fail in three specific ways: 1. Terminal-only feedback makes it ambiguous which step caused the error. 2. Agents
the paper: babyagi has ~200 citations, but 0 papers... i just published my first paper on arXiv 😆 'The Log is the Agent: Event-Sourced Reactive Graphs for Auditable, Forkable Agentic Systems' https://
Great paper from Google on program repair agents inside CI. (bookmark it) They propose FlowAgent, which runs a ReAct-style generate-and-validate loop on pre-submit test failures and shows the fix insi
Banger paper from CMU on harness learning. (bookmark it) Also, pay attention to this important new AI engineering skill of improving agents by editing their harness code instead of their weights. Seei