Skip to main content
Search

Microsoft Research

7 related articles

Subscribe to updates
  1. TokenEconomizer lets coding agents learn from past sessions: 18.4%–30.9% lower cost across 277 real bug-fixing tasks

    Developers use AI coding agents in the same codebases day after day, yet agents often start each session from scratch, rediscovering familiar facts, loading unused tools and repeating unsuccessful approaches. TokenEconomizer, an open-source plugin from UC Berkeley, Microsoft Research and Microsoft Security, turns completed session logs into guidance for later sessions without modifying the agent or its underlying model. Across 277 real bug-fixing tasks in six repositories, it cut average cost by 18.4%–30.9% for five agent and model combinations, saving in all 30 repository-combination pairs while task success rates stayed broadly stable.

  2. Cell foundation models stop chasing alignment: a new score shows fusion pays off only when modalities truly complement

    Multimodal cell foundation models usually freeze each modality's encoder and train only a fusion interface, yet whether fusion adds information beyond the best single modality has lacked a test. Researchers introduce the Synergistic Information Score (SIS), which measures accessible synergy as the gain of a fused representation over the strongest unimodal one under a linear probe. Across lung, thymus and breast spatial transcriptomics, unimodal baselines suffice in redundancy-dominated tasks, while non-spectral fusion reaches higher SIS in the resolution-mismatched thymus task.

  3. arXiv

    History Forcing teaches few-step video models to remember: a 1.3B student reaches 79.82 on 60-second VBench-Long

    Few-step autoregressive video diffusion models gradually lose subject and scene information over long rollouts, and existing distillation targets do not constrain distant history separately. History Forcing builds a context residual from the difference between one autoregressive teacher's predictions with and without extra history, then weights it into the DMD or OPSD distillation target. A 1.3B student reaches a VBench quality score of 85.07 for 15-second generation and a VBench-Long aggregate of 79.82 for 60-second generation, and raises PlayWorld Evolution Quality from 2.35 to 2.70 when the camera leaves and returns.

  4. Microsoft Research Asia open-sources Agent Lightning v1.0: Harnessed Agentic RL in about 3,500 lines lifts Qwen3.5-9B from 41.8% to 56.4% on SWE-bench Verified

    Microsoft Research Asia introduces the Harnessed Agentic RL paradigm and open-sources a rebuilt Agent Lightning v1.0, in which the same agent harness used in deployment participates directly in reinforcement learning through an LLM proxy; the framework is about 3,500 lines of code, runs agents as standard Kubernetes jobs, and on an end-to-end coding agent pipeline built on SWE-smith, mini-SWE-agent, and Qwen3.5-9B, roughly 6,000 training samples raise Pass@1 on SWE-bench Verified from 41.8% to 56.4%, an absolute gain of 14.6 percentage points.

  5. Microsoft Research introduces Quine: a multimodal biology world model that prioritized compounds driving tumor-state shifts in pancreatic cancer, narrowing candidates in a single weekend

    Microsoft Research introduces Quine, a research system combining a world model of biology trained jointly across modalities including sequence, structure, function, cellular state, and imaging with a harness connecting scientific tools, literature, the wet lab, and researchers; with the Broad Institute it used the system in pancreatic ductal adenocarcinoma (PDAC) to predict and prioritize thousands of compounds by their potential to shift tumor cells between therapeutically relevant states, wet-lab assays showed Quine's highest-ranked compounds produced the largest intended shifts, the whole process from narrowing the search space to prioritizing a handful of candidates took just one weekend, and the experiments also bore out the model's prediction of a distinct third phenotype.

  6. Microsoft Research Asia – Singapore at one year: nine new projects, a summer school reaching over 300 students, and the lab's first IPP student earning a CVPR 2026 oral

    Microsoft Research Asia – Singapore reviews its first year since opening on July 24, 2025: it pursues a "research-to-impact flywheel" across four pillars (next-generation AI models and agentic systems, domain-specific AI for real-world impact, AI-native research practices, and ecosystem and talent development), launched nine new projects with the National University of Singapore and Nanyang Technological University, signed a five-year Framework Research Agreement with NUS, reached more than 300 students through its summer school since 2025, and saw its first Industrial Postgraduate Programme student Qiming Huang have a RobotSeg paper selected for an oral presentation at CVPR 2026, with the second year focused on scaling what works.

  7. arXiv

    ProgramDistill: Turning Interactive Web Apps into Verifiable Reference-Guided SWE Tasks

    This work introduces the ProgramDistill benchmark and a fully automated mine–craft–patch pipeline that factorizes 26 interactive web applications into 1,975 replay-verified behaviors and constructs 4,063 tasks, letting coding agents infer and restore missing functionality by interacting with a reference application whose source is hidden; across nine frontier agents, the best full-application reconstruction success is 49.2%, and partial-application reconstruction success falls from 100% to 64.0% and from 96% to 32% as restoration depth increases from 1 to 8.

You’re all caught up