Skip to content
#Paper/Research

#Paper/Research

Oct 8

TodayOct 8Thu61 items
  1. PandailyAI score46

    ByteDance Seed Finds Periodic Weak Spots in Chunked KV-Cache Compression

    ByteDance Seed researchers found that language models compressing their KV cache in fixed-size chunks retrieve the same information unevenly depending on token position. In a 128K-token needle-in-a-haystack test, base DeepSeek-V4 checkpoints differed by up to 40.2 percentage points by phase, and post-training narrowed but did not eliminate the gaps. The authors urge evaluating such models across positional phases, since high average accuracy can hide systematic failures.

  2. PandailyAI score41

    Simplexity Robotics Trains One Robot to Tend Two CNC Lathes With 600 Trajectories

    Simplexity Robotics says it trained a single robot to load and unload two CNC lathes on its own, using 600 real-robot trajectories and reporting a 100% success rate on the precision CNC insertion task. The work, presented at IROS 2026 on September 29, combines the SimpleWAM world action model, a DRAM memory module and DPE action scoring, with force and torque feedback for insertion recovery. The company did not say how many trials the 100% figure covers, and it does not describe the yield of the whole cell.

  3. QbitAI (量子位)AI score58

    AgentGarten lets agents evolve through code-built worlds and neural rendering

    MirroS released AgentGarten, which pairs executable code environments with a real-time neural renderer running above 30 fps so agents can act, observe, and learn. In a one-on-one hide-and-seek setup, the hider learned to block passages by round 4 and the seeker learned to climb ramps by round 10, guided by notes the agents wrote after each round. The authors report applying the same loop to four other tasks, including a dog-companion game, a narrow-bridge car passing task, herding, and quarry loading.

  4. Tencent HunyuanAI score63

    Tencent Hunyuan releases ExplorationBench to test AI rule discovery

    Tencent Hunyuan, with Fudan and Tsinghua researchers, released ExplorationBench, a benchmark that tests whether AI systems can discover rules through experiments in verifiable alien worlds. Across 10 frontier systems, feedback from experiments raised the best AlienCode score to 89.0% after four rounds, while closed-book runs without feedback stayed at 0.5–11.0%.

  5. PandailyAI score44

    Donghua University Spins Transistors Into Fibers That Act as Soft Robot Circuits

    Donghua University researchers spun transistors, resistors and capacitors into a continuous fiber that functions as a circuit, using microfluidic encoded spinning, according to a Nature Electronics paper. The fibers integrated multicolor electroluminescence, analog and digital logic, and non-contact spatial sensing, and in demonstrations guided a robotic gripper and let a finger control a robotic arm and drone without touch.

  6. PandailyAI score55

    Chinese Team Publishes 3D Cell Atlas of Rice's Full Life Cycle in Cell

    A Chinese-led team published in Cell a three-dimensional spatiotemporal cell atlas covering rice from germinating seed to grain fill, along with a public portal and the RICE scGPT single-cell foundation model. The atlas combines single-nucleus RNA sequencing with BGI's Stereo-seq spatial transcriptomics across 10 organ and tissue types and 61 stages, defining 119 cell types and 133 subtypes.

  7. Leiphone (雷峰网)AI score46

    IROS 2026 papers show AI reintegrating with classical robotics rather than replacing it

    Of 1,933 IROS 2026 papers, Robot Learning/Embodied AI appears in about 809, while Navigation/Planning covers 564 and Perception/Vision 556. The article argues large models are being embedded into traditional planning, geometry, and control rather than replacing them. Vision-language-action models are shifting toward efficiency, 3D understanding, memory, and system integration.

  8. Leiphone (雷峰网)AI score46

    IROS 2026 Best Paper goes to LT-Mem robot long-term memory study

    At IROS 2026 in Pittsburgh, the Best Paper Award went to Yumin Lee, Hyoseok Ju and Giseop Kim for LT-Mem, a volatility-aware spatio-temporal memory system for lifelong robot scene understanding. The Best Student Paper Award went to Pei-An Hsieh and colleagues for flatness-preserving residual learning enabling real-time tight quadrotor formation flight. Other honors included a humanoid tennis-skills paper and SteadyTray, a humanoid tray-transport study.

  10. Elvis SaraviaAI score55

    HERMES harness lifts GPT-5.6 Sol repository migration from 6.5% to 31.0%

    A paper introduces HERMES, a harness that pairs each repository component with a resident LLM and uses dependency-aware activation and failure diagnosis. With the same model and effort setting, GPT-5.6 Sol's whole-repository migration score rose from 6.5% to 31.0% when Codex was replaced by HERMES. Across four software engineering benchmarks, HERMES beats matched baseline harnesses by 12.4 points on average, and Qwen3-8B components come within 4.5 points of an all-GPT-5.6 Sol setup while cutting Terminal-Bench 4.0 inference cost by 26.2%.

  11. SiliconANGLE · AIAI score60

    OpenAI publishes 722 AI-generated math papers, including Riemann hypothesis progress

    OpenAI has published 722 math papers generated by an unreleased AI model, posted to GitHub, spanning about 20 mathematical subfields. The model did not fully prove the Riemann hypothesis but proved the quasi-Riemann hypothesis, and it also produced theoretical computer science and partial differential equation results. Many papers include Lean files for computer verification, and OpenAI plans to release more of them.

  12. Sundar PichaiAI score65

    Google's AMIE Chat System Is Tested With Real Urgent Care Patients in The Lancet

    Google published a prospective study of AMIE, a research conversational system that patients chat with before doctor appointments, in The Lancet with Beth Israel Deaconess Medical Center. Clinicians reported the summaries helped them prepare for visits in 75% of cases and influenced their approach to care in more than half. AMIE's differential diagnoses matched the doctors' final diagnoses 90% of the time.

    AIWhy it matters: The study tests a patient-facing diagnostic chat system in a real urgent care clinic, a setting that goes beyond lab evaluation and is useful for judging clinical readiness.

  16. GoogleAI score62

    Google's AMIE Diagnostic Chatbot Studied Prospectively in Real Clinical Setting

    Google reports that its medical research system AMIE, described as the first patient-facing conversational diagnostic tool of its kind studied prospectively in a real-world clinical setting, was evaluated in a study published in The Lancet. Patients who chatted with AMIE before in-person appointments reported stronger confidence and better organized thoughts. Physicians reviewing the pre-visit conversation information gained more time for collaborative care and shared decision-making instead of digging through data.

  17. MIT News · AIAI score34

    MIT's Sasha Rakhlin outlines how universities should respond to AI in research and training

    MIT Statistics and Data Science Center director Sasha Rakhlin argues that AI progress is fastest where results can be verified quickly, citing a model reaching gold-medal level at the International Mathematical Olympiad a year before models produced new research results. He says departments should reconsider how they reward work, emphasizing question-asking, replication, and disclosure of AI's role in a researcher's contributions. He also urges universities to build shared lab infrastructure that captures failed experiments and tacit expertise.

  18. Epoch AIAI score31

    This isn’t conclusive evidence of a new architecture, but it suggests something has changed in how GPT-6.1 Sol handles long contexts. This is a follow-up to our earlier report on latency scaling in frontier models: https://epoch.ai/publications/long-context-latency-scaling-gpt-vs-claude#appendix-h-gpt-6-sol-and-gpt-61-sol

    This isn’t conclusive evidence of a new architecture, but it suggests something has changed in how GPT-6.1 Sol handles long contexts. This is a follow-up to our earlier report on latency scaling in frontier models: https://epoch.ai/publications/long-context-latency-scaling-gpt-vs-claude#appendix-h-gpt-6-sol-and-gpt-61-sol

  20. AnthropicAI score57

    Astrophysicist uses Claude to build first complete ultraviolet sky map

    An astrophysicist worked with Claude Science to create the first complete ultraviolet map of the sky, covering regions never observed in UV. Claude located existing datasets, combined them, and filled gaps with statistical inference, taking a few days rather than weeks of human work. The map is presented as a teaching tool and an example of low-priority scientific work that AI now makes feasible.

  21. Epoch AI · The Epoch BriefAI score49

    Epoch AI's October 2026 Brief Covers AI Agents, Falling Costs, and China's Chip Exposure

    Epoch AI estimates the AI chips shipped through 2027 could support about 30 to 170 million concurrent frontier-model agents, or nearly 2 billion with cheaper models. Its researchers find the cost of a fixed level of AI performance has fallen about 47% per quarter over the past three years. The newsletter also reports China's semiconductor supply-chain exposure is 2.7 times that of the US.

  23. Google ResearchAI score20

    Interested in privacy-preserving synthetic data? Catch Alex Bie at the @COLM_conf Google booth (#107) today, at 2:00 PM PT for an encore presentation of ContinuousBench, evaluating knowledge transfer and data contamination in DP synthesis.@GoogleDeepMind Join the conversation at #COLM2026!

    Interested in privacy-preserving synthetic data? Catch Alex Bie at the @COLM_conf Google booth (#107) today, at 2:00 PM PT for an encore presentation of ContinuousBench, evaluating knowledge transfer and data contamination in DP synthesis.@GoogleDeepMind Join the conversation at #COLM2026!

  24. Elvis SaraviaAI score48

    Google's FlowAgent auto-repairs failing tests inside code review

    Google proposed FlowAgent, a ReAct-style agent that generates and validates fixes for pre-submit test failures and shows them in its code review tools. Two abstention filters, before and after execution, suppress weak suggestions; in a manual review of 195 real failures, 67.18% of fixes were correct. After the Google-wide launch, it suggested fixes on 295,508 changes, with developers previewing 65,069 and applying 28,554.

  25. GoodfireAI score44

    The Alzheimer’s Translation Challenge is built on a new 150M-cell atlas of neurons, astrocytes, and microglia across different genetic backgrounds under combinatorial perturbations, with multi-modal readouts. The data will be made available through the AD workbench and Prima Mente's modeling platform.

    The Alzheimer’s Translation Challenge is built on a new 150M-cell atlas of neurons, astrocytes, and microglia across different genetic backgrounds under combinatorial perturbations, with multi-modal readouts. The data will be made available through the AD workbench and Prima Mente's modeling platform.

  26. TechCrunch · AIAI score65

    OpenAI's math solutions fall short of the field's standards, mathematicians say

    OpenAI released hundreds of claimed solutions to hard math problems but did not fully meet guidelines from the Advisory Group on Mathematics and Artificial Intelligence. Only 10 of 719 manuscripts included chain-of-thought releases, and just 42% of proofs were formalized. A Cambridge and King's College paper found discrepancies between a natural language proof and its Lean code for a Navier-Stokes-derived problem.

  28. Lewis TunstallAI score62

    Lewis Tunstall Shares a Physics Paper Proof Developed with OpenAI's Astra Model

    Lewis Tunstall quotes Kyle Cranmer's post about a paper by Nate Gunnarsson on a non-perturbative approach to chiral fermions in the Standard Model, extending Lüscher's abelian result. The paper's acknowledgments state that OpenAI's GPT-6 Astra model was essential, proposing refinement strategies, writing rewrites of the proof, and carrying out Lean verification.

  30. Epoch AIAI score14

    For example, GPT-6 Astra ran an experiment exploring why AI agents fail to learn with practice. It set AI agents’ token budgets too low. Instead of treating this as a mistake, it reported “sensitivity to the acquisition budget” as a key finding.

    For example, GPT-6 Astra ran an experiment exploring why AI agents fail to learn with practice. It set AI agents’ token budgets too low. Instead of treating this as a mistake, it reported “sensitivity to the acquisition budget” as a key finding.

  35. Elvis SaraviaAI score46

    RSIGym gives research agents services, lifting SWE-bench Verified to 50.33%

    RSIGym provides a research agent with training, inference, evals, and sandboxes as callable services, so it spends its budget on experiments rather than rebuilding infrastructure. With Opus 5 as the researcher, the improved system rose from 17.67% to 50.33% on SWE-bench Verified. The post also highlights a way to measure co-evolution between harnesses and models.

  37. GoodfireAI score28

    We built cybersecurity monitors for Kimi K3 and GLM 5.3 — more accurate, 50x faster, & 50x cheaper than an optimized LLM judge. External red-teaming from @farairesearch found that our monitor greatly reduces universal jailbreaks. 🧵

    We built cybersecurity monitors for Kimi K3 and GLM 5.3 — more accurate, 50x faster, & 50x cheaper than an optimized LLM judge. External red-teaming from @farairesearch found that our monitor greatly reduces universal jailbreaks. 🧵

  38. Google ResearchAI score14

    Missed yesterday's demo on adaptive agent environments? Stop by the #COLM2026 Google booth #107 today at 11:00 AM PT to catch Zifeng Wang presenting EnvHarness — a flexible framework enabling co-evolution between LLM agents and their training environments.

    Missed yesterday's demo on adaptive agent environments? Stop by the #COLM2026 Google booth #107 today at 11:00 AM PT to catch Zifeng Wang presenting EnvHarness — a flexible framework enabling co-evolution between LLM agents and their training environments.

  39. Goodfire ResearchAI score57

    Goodfire deploys probe-based cyber monitors on Kimi K3 with a judge cascade

    Goodfire Research describes probe-based cyber monitors for Kimi K3 and GLM 5.3 deployed on a production inference stack. The probe filters suspicious exchanges before an LLM judge reviews them, reaching about 93% recall at a 5.5% benign-session interruption rate at roughly 50x lower judge cost. In FAR.AI's red-teaming, the monitor reduced universal jailbreaks to zero across 140 tested strategies.