#Paper/Research

AIRSIGym 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.

AIGoodfire has published research on deploying cyber monitors in production on Kimi K3. The post links to the full research write-up and invites organizations to get in touch about deploying these monitors.

AIGoodfire built cybersecurity monitors for Kimi K3 and GLM 5.3 that it says are more accurate, 50x faster, and 50x cheaper than an optimized LLM judge. External red-teaming by Far AI Research reportedly found the monitor greatly reduces universal jailbreaks.

AIGoogle Research is presenting EnvHarness, a flexible framework that enables co-evolution between LLM agents and their training environments, at the #COLM2026 Google booth #107 today at 11:00 AM PT. The post notes that static environments limit agent growth, and EnvHarness is described as a plug-in architecture that dynamically reshapes environment behaviors to improve reinforcement learning and adaptability.

AIGoodfire 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.

AIArena links readers to a full technical report on its blog and to a full rankings page in its Alignment Index. The post itself gives no model names, scores, or findings, so the substance is only in the linked materials.

AIArena found that some models misquote users while others credit users with others' work in false attribution cases. GPT-6 Luna and Astra rarely misquoted users, at 15.6% and 28.6%, but often misattributed statements, at 53.1% and 48.2%. Sibling model GPT-6 Sol had the highest rate of misstating the user's history, at 23.5%.

AISantiago says physical consistency is the most important and hardest feature of a world model, and that many generated videos show objects defying gravity. He reports that Seedance 2.5 is currently the best among the evaluated world models. The post links to a physics evaluation benchmark in which eight video world models reached a top score of 57.76/100.

AIGoogle shared research on what its work could mean for the future of global maternal healthcare. The post links to a fuller write-up but gives no specific findings, models, or figures.

AIIn a prospective clinical study, Google's models pinpointed gestational age within 4 days of accuracy. The company says that precision could meaningfully affect clinical care, and that extending such tools to low-resource settings could help reduce maternal deaths and close care gaps worldwide.

AIBoris Power, who owns OpenAI's account, praised the pace of progress on a result he called remarkable. The context from @0xdoug reports a PR merged and a tightened bound from κ = 2⁻¹⁸² to κ = 2⁻¹⁵, a community effort across contributors.

AIZyphra has released a blog post and arXiv paper on expert coupling in mixture-of-experts (MoE) pretraining. The post itself provides only links, so the specific findings are not described here.

AIZyphra says its approach is lossless: the same tokens still reach the same experts, with unchanged architecture, routing decisions, and training objective. By reorganizing where experts and tokens live, it reduces the communication needed to perform the same computation.

AIZyphra reports that its MoE training optimizations speed up token exchange by 1.16x to 2.63x and full training steps by up to 1.41x in Megatron-LM on 8 to 64 GPUs. The gains are largest when each token uses more experts and those experts span several nodes.

AIZyphra reports that patterns in model training emerge early enough to be useful and are inexpensive to measure. Using only 4,096 tokens, its placement and routing predictions come within roughly one percentage point of results obtained with 524,000 tokens.

AIZyphra reports that expert routing in mixture-of-experts models is predictable across layers, since the experts a token uses in one layer indicate which it will need next. Its token shuffling method moves each token to the GPU holding those experts within a transfer that already runs after attention, adding no network traffic.

AIZyphra places experts that are frequently chosen together on the same GPU, so each token is sent to a GPU only once regardless of how many of its experts reside there. On 8 GPUs, this removes up to 58% of token copies sent across the network.

AIIn Zyphra's runs, MoE token exchange between experts consumed 13-24% of step time on one node and 45-60% across four nodes. Because experts are spread across GPUs and nodes, tokens must be sent to their experts and returned, making this communication a major training cost as models scale.

AIIn one layer, just 64 of 8,128 possible expert pairs handled 42% of tokens, far above the 1.6% expected if experts were chosen independently. Zyphra says this structure can be exploited to improve expert placement.

AIZyphra researchers report that exploiting patterns in how tokens are routed to experts makes Mixture of Experts communication up to 2.63x faster on AMD MI300X GPUs. The speedup comes without changing the model itself.

AIReJev, an independent community project, applied LoRA post-training to OpenBMB's MiniCPM5-2B for bounded agent decisions: state, question, and candidate options yield one choice. On its sealed 1,892-sample holdout, accuracy rose from 51.11% to 80.50% (+29.39 percentage points) with 0% invalid outputs, at about $5.31 in cumulative Modal billing including earlier experimental overhead. The authors describe this as an early, task-specific result, not parity with Jev.

AIUniPat AI's PaperBenchX benchmark found the strongest model, GPT-6 Astra, fully reproduced only 13.98% of 93 real research-paper tasks across 12 scientific fields. Reproduction was judged by regenerating outputs in an isolated environment, with 3,168 expert-verified scoring items. UniPat has open-sourced 12 test tasks and kept 81 tasks closed to preserve long-term evaluation validity.

AINVIDIA, Princeton University, and the University of Maryland introduced PivotOPD, an on-policy distillation method that teaches multi-turn LLM agents to recover from their most damaging early mistake. Tested on Qwen3-1.7B and Qwen3-8B students, it posts the best average against 13 baselines on ALFWorld, WebShop, and Search-based QA. It recovers from 72.7% of replayed pivotal mistakes, versus 20.3% for standard OPD, with no added inference cost.

AIOpenAI withdrew three math manuscripts, including "Algebraicity of Weil classes on split abelian eightfolds," after a sign error invalidated a stabilization-trace cancellation argument used by two dependent papers. The withdrawn papers now carry notices linking to archived manuscripts, and 14 other manuscripts were revised with proof repairs and corrected statements.

AIA Galbot, Tsinghua University and collaborators paper won IROS 2026's Best Entertainment and Amusement Paper Award for LATENT, a humanoid tennis-return method trained on imperfect amateur motion-capture clips. In simulation, the full forehand policy succeeded on 96.52 percent of returns, versus 71.85 percent for PULSE. On a real Unitree G1, the paper reports 90.90 percent forehand success across 20 consecutive rallies, with motion capture still used rather than the robot's own cameras.

AIHuawei engineers presented XMFS, an experimental Linux kernel prototype filesystem, at the Linux Plumbers Conference in Prague on October 5. It aims to let applications reach cross-node shared memory on CXL 3.0 or Huawei unified bus servers through standard POSIX file calls. The code exists only on openEuler, not in the mainline Linux kernel.

AIJohns Hopkins astrophysicist Brice Ménard, working as an Anthropic researcher, used Claude Science to produce the first complete map of the sky in ultraviolet light. Claude orchestrated agents to merge GALEX, Swift, and FIMS/SPEAR data, then predicted roughly a third of the sky that no UV telescope had observed, using relationships to visible, infrared, and radio data. Hidden test regions were reconstructed to within about 10% of real measurements, and each pixel is labeled measured or predicted with uncertainty estimates.

Why it matters: The post shows how an astrophysicist used Claude Science agents to merge UV surveys and predict missing sky regions, with a validation step that makes the method reusable.

AIOpenAI published 722 math manuscripts covering 372 result groups in a new GitHub repository, openai/math, all produced by an unreleased internal model. The author describes the results as including a near-Riemann hypothesis claim pushed to 0.875, and notes that 25 Fields Medal winners criticized the company's approach to AI math research.

Why it matters: The piece traces how AI math results moved from benchmarks to open problems, offering context on verification and the mathematicians' pushback.

AIA NVIDIA study accepted at NeurIPS 2026 reports that multimodal models refuse harmful requests less reliably when they call tools. Refusal failures rise by up to 68.7% relative and by 17.7% on average across the models tested, including Claude Opus 4.6 and 4.7 and Gemini Agentic Vision. The authors attribute this to tool outputs crowding out the original harmful intent and to attention shifting toward describing tool results. Re-inserting the original request and image before the final response restores part of the lost refusals.

AIThe vLLM team released a technical report on vLLM-Omni, a unified serving runtime for omni-modality generation spanning multi-stage autoregressive pipelines, iterative diffusion, and stateful sessions. Current LLM servers and diffusion stacks each cover only one of these patterns, pushing deployments to stitch disjoint runtimes together. vLLM-Omni offers a shared control plane in which an orchestrator advances requests across stages, specialized engines handle compute, and a connector carries payloads.

AIAndrew Curran posted a brief "Updated again." with no further details. The post links to background from @0xdoug on OpenAI problem #109 (integer multiplication), which reports tightening the bound from κ = 2⁻¹⁸² to κ = 2⁻³⁴, a roughly 48-million-fold improvement.

AIAccording to the source, OpenAI released a set of results produced by an internal frontier model on 722 math problems, without advance warning or peer review. The excerpt provided does not include full details of the methods or verified outcomes.

AIOpenAI announced on X that it is releasing a series of new mathematical results produced by its internal frontier model. The material is reported as 722 manuscripts posted to GitHub, and the excerpt provides no further detail on the specific results.

AIApple researchers introduced Normalizing Trajectory Models (NTM), which model each reverse diffusion step as a conditional normalizing flow trained with exact likelihood. The model matches or outperforms strong image generation baselines on text-to-image benchmarks in just four sampling steps while retaining exact likelihood over the generative trajectory.

AIWaymo research found that even fully sober human drivers face nighttime fatal crash risk 3.1 to 3.9 times higher than daytime risk, pointing to systemic hazards beyond impairment. The study used an exposure reconstruction model across the 50 most populous U.S. urban areas, showing removing alcohol-involved drivers lowers the average urban fatal crash rate by 23%, from 1.42 to 1.10 per 100 million miles.

AIAndrew Curran notes two posts five hours apart as a gauge of how fast progress is moving. The linked update tightens the bound on OpenAI problem #109 (integer multiplication) to κ = 2⁻⁵⁹, down from OpenAI's original κ = 2⁻¹⁸².

AIGoogle Research is hosting a walkthrough at its COLM booth #107 today at 5:00 PM of ContinuousBench, a standardized benchmark for measuring knowledge transfer in differentially private synthetic data. The session, led by Alex Bie, asks whether DP synthetic data preserve actual information or only style. A paper is linked on arXiv.

AIGoogle Research announced findings from a three-month randomized controlled trial with practicing patent attorneys, led by Visiting Fellow David Autor. The study examines both short-term productivity gains and longer-term skill building resulting from AI usage.

AIA Google Research field experiment with 133 patent lawyers found AI tool access raised drafting scores by 0.34 to 0.38 standard deviations over three months. When the tool was removed for a redlining task, only senior lawyers kept an advantage of 0.45 SD, while junior lawyers showed no discernible improvement. The authors argue that tools which boost current output must not stop junior professionals from building the judgment that senior experts rely on.

Why it matters: The field experiment separates AI's short-term productivity gains from skill retained after the tool is removed, which matters for training junior professionals.

AINVIDIA researchers built PivotOPD, a training method that helps AI agents avoid early mistakes and recover when they occur. During training, a teacher model shows the agent a better action and guides it back on track over the next few steps.