Research library

Search papers on equipment connectivity, quality inspection, production analysis, and manufacturing work.

Search and filter

New paper summaries

Summaries are editorial notes, not statements by the original authors. Check the original paper. Updated 2026-11-20.

  1. 1155AI Agents

    Turbo Harness: Instance-Adaptive Harness Optimization

    • Built a tailored harness per task instance instead of one global harness, consistently improving performance.
    • Recycled trial-and-error artifacts discarded during prior optimization into a playbook used as training data.
    • Raised pass rate on SWE-smith-MR from 50.7% to 64.0% with Claude Haiku 4.5 and from 70.7% to 88.0% with Gemini 3.7 Flash.
    • A small 9B-class editor model (Qwen3.5-9B) sufficed, and it is invoked only once per task, keeping inference overhead low.
    • Recorded a higher pass rate on Terminal-Bench 2.1 than widely-used human-designed harnesses.
  2. 1154Robotics

    DuoMind: Enabling Distributed Multi-Robot Coordination with Semantic Communication

    • They proposed a hierarchical design in which each robot runs a VLM orchestrator (high-level reasoning) and a VLA action model (low-level control) in a distributed setup.
    • Robots exchange semantic messages containing intent and subgoals rather than raw data.
    • They built RoboPoly, a new benchmark for long-horizon multi-robot manipulation, filling an evaluation gap.
    • It consistently outperformed baselines on RoboPoly and RoboTwin, and ablations confirmed the separate contributions of the hierarchical design and semantic communication.
  3. 1153AI / Evaluation

    KaliBench: A Fine-Grained Benchmark for Cybersecurity Tool Use on Kali Linux with Runtime-Free Verifiable Rewards

    • They built a benchmark of 8,504 query-command pairs covering 1,642 Kali Linux tools across 23 capability dimensions.
    • In the unrestricted setting without tool hints, no open-weight model exceeded 42% exact-command accuracy.
    • They created runtime-free verifiable rewards that can be used directly for SFT and reinforcement learning training.
    • An 8B model trained with these rewards performed on par with a 685B MoE model.
    • They proposed a fine-grained evaluation scheme that decomposes command errors into tool selection, optional arguments, ordering, and syntax.
  4. 1151Robotics

    Reconstruct, Practice, Go Real: Guided Self-Improvement for Embodied Agents

    • They proposed the RPG framework, which automatically creates simulation practice tasks from offline data and revises the skill library and prompts through failure diagnosis.
    • Without changing model weights, improving only skills and prompts raised success on 22 tasks from 28.6% to 95.0%.
    • It outperformed the prior best baselines ASPIRE (75.5%) and a GPT-6-based agent (60.0%) by a wide margin.
    • Skill revisions are only retained after cross-task validation showing they also help other tasks sharing the library.
    • After calibration, the frozen system succeeded in all 30 physical robot trials across three tasks.
  5. 1149Machine Learning

    Decoding Looped Transformers Better for (Almost) Free

    • They proposed training-free contrastive decoding that uses the first recurrent pass of looped transformers as a weak model.
    • LoopCD-Logits raised Ouro-2.6B's AIME 2024 pass@1 from 61.88% to 73.33%, and LoopCD-Hidden lifted Huginn's HumanEval from 22.56% to 31.71%.
    • Halving the number of recurrent loops still matched or exceeded full-depth baselines, cutting compute by 22.5% to 48.2%.
    • They showed that multiple-choice tasks need strong guidance (omega=0.5) while long generation tasks need weak guidance (omega=0.2-0.3).
  6. 1148Machine Learning

    Finetuning with Sampling: SFT Learns Better Than You Think

    • They proposed projection sampling, which rewrites expert answers via MCMC sampling to be closer to the model's own expressions before SFT.
    • On chemistry tasks, plain SFT lost substantial MMLU-level capability, while this method forgot the least with an average loss of only -1.10%.
    • Increasing MCMC steps moved the training data closer to the model distribution while accuracy rose in tandem, showing sampling itself is a scalable compute axis.
    • The trained model acquired genuinely new abilities, solving problems the base model could never solve with up to 67.2% pass rate.
    • Initializing RL on top of sampling SFT achieved the best overall results with +40.7% on MATH500 and +25.1% on GSM8K.
  7. 1147AI / Agents

    VISTA: A Visual Harness for Reasoning in an Interactive World

    • The system was designed to preserve past screens in their original form and let the model enlarge and revisit relevant views.
    • The authors reported solving all 25 public ARC-AGI-3 games while using 57.4% fewer actions than first-time human participants.
    • The authors reported improving accuracy from 41.0% to 63.2% on 39 BabyVision visual tracking questions.
    • The authors stated that they could not rule out the possibility that the public games were included in model training.
  8. 1146AI / General

    Sharpening Tax in Post-Training

    • The study analyzed 42 conditions by comparing 14 pairs of models before and after post-training across three benchmarks.
    • The study found that base models equipped with a simple tool-execution harness could solve more tasks than post-trained models when given enough retries.
    • The training procedure was designed to encourage more diverse actions on difficult tasks based on each task’s success history.
    • The method improved both single-attempt success rates and the range of tasks solved through repeated attempts in two game environments.
    • The authors stated that the observational results alone could not establish causality because the training data of the existing public models were unknown.
  9. 1145AI / General

    ScholarCatalyst: A Benchmark for Retrieving Papers That Inspire New Research

    • The authors constructed 894 early-stage research questions based on judgments from 184 researchers.
    • The study reported that search agents retrieved 42% of the needed papers in the top 20 results, compared with 48% for semantic similarity retrieval.
    • The study found that 43.6% of the papers judged useful for subfield-specific questions were absent from the source studies’ reference lists.
    • The analysis indicated that getting useful candidates into the search results mattered more than reading the candidate papers at greater length.
  10. 1144AI / Agents

    Turbo Harness: Instance-Adaptive Harness Optimization

    • The work starts from the observation that a globally optimized harness tuned to the average may not be optimal for every task instance.
    • It recycles byproducts from a finished optimization run into a structured playbook, avoiding the cost of re-running expensive search.
    • A harness editor referencing the playbook generates instance-specific patches, so the execution model runs in a tailored environment.
    • It consistently outperformed existing harness optimization methods across 7 benchmarks covering interactive agents, software engineering, and long-horizon terminal tasks.
  11. 1143AI / Agents

    Learning from Research: Toward Lifelong Agent Harness Evolution

    • The approach keeps model weights fixed and lets the agent evolve its harness (the software wrapping it) by learning from research papers.
    • Motivated by the passivity of execution-feedback-only methods, it proactively extracts improvement strategies from the research literature.
    • It builds a pipeline that uses topic modeling to find strategies in papers and experiments with their combinations to select the best.
    • Task goal completion improved from 49.6% to 63.6% on AppWorld and from 72.7% to 81.9% on Tau2-Bench Telecom.
  12. 1142AI / Agents

    PivotOPD: Learning to Recover from Pivotal Mistakes in Multi-Turn Agents

    • Across three Qwen3 models (8B to 235B), more than half of failed rollouts contained a pivotal mistake, usually occurring in early turns.
    • Those mistakes were critical yet recoverable: guiding the model for just a few turns after the pivotal turn restored task success.
    • The proposed PivotOPD has a teacher provide a gold action for prevention and recovery actions for restoration, trained with two distillation losses.
    • Compared against 13 baselines, it improved ALFWorld by +5.5% and transferred to SWE-Bench Verified with +3.2% resolve rate on another model family.
  13. 1141Computer Vision

    Looped Diffusion Transformer

    • Instead of scaling up model size, the paper gains capacity by looping shared transformer blocks multiple times within a single denoising step.
    • It identifies weak supervision across intermediate loops and unstable attention updates as the reason naive looping degrades quality.
    • Looped-DiT, combining intermediate-loop deep supervision with self-modulating attention, lets a 260M-parameter model surpass a model 6.5x larger.
    • Under a fixed inference budget, increasing loop depth yielded larger gains than adding more denoising steps.
    • Deeper loops progressively corrected mistakes made in earlier loops, showing behavior suggestive of latent reasoning.
  14. 1140Robotics

    T$^2$Mem: Learning Test-Time Memory for Robotics

    • T²Mem adds internal memory to a pretrained vision-language-action model so that actions can use information no longer visible in the current observation.
    • An observation-grounded interface stores history in fast weights, while the memory module and action policy are trained in alternating stages.
    • Across 16 RoboMME tasks, average success increases from 17.93% for the memory-free baseline to 56.83%.
    • The method uses memory without an external reasoning model, and controlled RTX A5000 profiling shows approximately three times faster foreground computation than FrameSamp+Modul.
    • Reasoning about swapped object locations and precise insertion remain limitations, and the timing measurements exclude communication and environment execution.
  15. 1139AI / General

    Context Language Models

    • Context Language Models expose the live context as a file that the model can directly edit through general code tools.
    • Edits are reflected in the next model call, and the approach extends to multi-agent systems that manage multiple context files.
    • On BrowseComp-Plus with Qwen3.6-27B, accuracy is 11.4% higher in relative terms than the strongest baseline, with 21.5% fewer prefix-reuse FLOPs.
    • Natural-language guidance and reinforcement learning can improve context-management strategies, while a separate suffix-cache reuse method reduces compute by 35% relative to standard SGLang in the reported evaluation.
    • Editable context can become a new channel for persistent malicious instructions, requiring context-integrity protections alongside flexible management.
  16. 1138AI / General

    MatToolBench: Benchmarking Multimodal Agents in Real-World Materials Science Workflows

    • MatToolBench provides 204 tasks using ten materials-science tools inside a Windows 11 virtual machine.
    • It evaluates GUI operation, OriginPro scripting, and code-based queries, distinguishing partial-credit scores from success that satisfies every criterion.
    • The highest average success rates among the evaluated models are 25% on GUI tasks and 45% on code tasks.
    • Performance drops when domain-specific workflow guidance is removed, highlighting the importance of tool knowledge and procedural support.
    • Evaluation is limited to English prompts and single sessions of at most 50 steps, excluding some specialist tools and longer workflows.
  17. 1137Robotics

    AD-E2E-JEPA: A Joint-Embedding Predictive Architecture For End-to-End Autonomous Driving

    • AD-E2E-JEPA is an autonomous-driving world model that predicts future latent visual representations and selects trajectories close to a target image.
    • A learnable projector with SIGReg regularization reduces the number of planning patches to one-sixteenth and the feature dimension to one-quarter.
    • In an A100 experiment evaluating 256 candidate trajectories, planning takes 0.8 seconds per scene, compared with 91.8 seconds for DINO-WM and 101.0 seconds for JEPA-WM.
    • Using the pretrained projector in a separate imitation-learning setup raises EPDMS from 80.2 with random initialization to 85.4, demonstrating the value of reusing its representations.
    • Zero-shot evaluation supplies ground-truth future images as goals and does not directly optimize safety, so the results do not establish safety on real roads.
  18. 1136LLMs / NLP

    Improving Test-Time Scaling with Adaptive Looped Transformers

    • Co-post-trained an iteration decider with the backbone using online labels of whether one more loop iteration improves the prediction.
    • Improved the accuracy-per-compute-doubling slope of test-time scaling by 53% over the non-looped baseline (2.74 vs 1.79).
    • Exceeded the baseline's peak AIME accuracy by about 3.4 points at matched compute, with gains growing from +2.8 at depth 2 to +3.9 at depth 8.
    • Focused extra computation only on tokens that benefit from looping, unlike fixed-depth looping which iterates on every token.
    • Achieved these results purely through post-training of a 1.7B model.
  19. 1135Computer Vision

    Learning Native Reflection in Unified Models with Interleaved Reinforcement Learning

    • Trained the entire self-reflection loop (diagnose then revise) inside one unified multimodal model with reinforcement learning.
    • Used group-relative advantages over sibling trajectories sharing one initial image so the model compares reflection strategies rather than lucky first draws.
    • Applied a single trajectory-level advantage to update both reflection tokens and image revisions, avoiding the combinatorial blow-up of per-round credit assignment.
    • Gains transferred to benchmarks never used in training: +12.05 on GenEval, +10.97 on WISE, and +3.48 on OneIG-Bench.
    • Found that SFT rollouts already contained correct repairs for 78% of failing images, yet a single trajectory fixed only 20.59%, rising to 64.94% after RL.
  20. 1134Robotics

    DexAgent: An Agentic Human2Sim2Robot Framework for Dexterous Manipulation with Self-Evolving Tool Library

    • Generated physically grounded robot trajectory data from a single egocentric human video and a task prompt.
    • At each of four pipeline stages, selected or newly developed tools and required property-specific verifiers to pass before advancing, preventing error propagation.
    • Stored newly developed skills and verifiers in a self-evolving library, reducing processing time as more videos are handled.
    • Achieved a 3.5x higher success rate than competing baselines across eleven real-world tasks spanning rigid, articulated, and deformable objects.
    • Varied object and robot states in simulation and retextured rendered observations to facilitate sim-to-real transfer.
  21. 1133Robotics

    Agent Priors-guided Policy Learning

    • Used each skill's structural prior both as an inductive bias during training and as a descriptive document for the runtime agent.
    • Proposed several priors per skill and trained and verified a separate diffusion policy for each prior.
    • Let the runtime agent read priors, handoff conditions, and verification evidence to choose policies and invoke them in chunks of up to 300 steps.
    • Showed stronger out-of-distribution skill generalization on MetaWorld and ManiSkill and succeeded at previously unseen skill compositions.
    • Confirmed the interface is essential: removing the prior information in ablations sharply degraded performance.
  22. 1132Machine Learning

    PoEM: Predicting RL Outcomes from Existing Policies

    • They proved that if a new reward is a linear combination of existing rewards, the new log-policy can also be written as a linear combination of the existing log-policies.
    • Even in non-linear cases, the empirical finding that log-policies lie in an approximately low-rank subspace became the backbone of the algorithm.
    • The combination coefficients are estimated using only rewards or basis-policy outputs on samples, without running any actual reinforcement learning.
    • They validated the approach on synthetic and real rewards across both text and image modalities.
    • In environments like LabChin, where reward models change frequently during experiments, this can save substantial training cost.
  23. 1131Machine Learning

    Minimally Invasive Steering of Language Models

    • It adjusts model dispositions using only vectors added to the final hidden states without retraining, while suppressing distribution shift with a Fisher quadratic penalty.
    • It exactly decomposes the sequence-level KL gradient into an analytic term and a score-function term, and proves the validity of the approximation to first order.
    • The computation reduces to matrix-vector products with the frozen model head, so position-specific steering vectors can be optimized without any training.
    • It achieved the highest mean reward in six of seven settings on preference and code-generation tasks across 1B-14B models, while keeping diversity and coherence at Best-of-N levels.
  24. 1130Robotics

    AD-WM: Action-Discriminative World Models for Counterfactual Model Predictive Control

    • It precisely identifies the structural problem of world models: low factual prediction error does not mean good action selection.
    • It attaches an action-recovery (inverse dynamics) auxiliary task during training only, so predictions retain action information, and removes it at test time to keep planning unchanged.
    • It improved hard-start success from 3.7% to 52.0% on OGBench-Cube, and real Franka robot pick-and-place from 42.2% to 71.1%.
    • It also showed that diagnostic metrics such as elite regret align with actual success better than plain prediction error.
  25. 1129Reasoning

    SAGE: Mitigating Long-Horizon Reasoning Biases via Topological Guidance

    • It defines long-horizon reasoning failures along two axes, exploration bias and compounding bias, and presents a theoretical analysis (Symbolic Closure Analysis).
    • Algebraic sparsification reduces spurious branches, while hyperbolic embedding provides dense depth-wise signals, each addressing one of the two biases.
    • It consistently outperformed existing methods across 12 benchmarks and 7 model families.
    • It achieved up to an 8-fold improvement on the real-world open Andrews-Curtis problem.
  26. 1128Agents

    GRASP: Generating, Revising, and Assessing for Strategic Planning with Agentic AI

    • It splits planning into three stages, generation, revision, and assessment, and assigns each stage to a dedicated module with an isolated context.
    • It gained about 12.4% higher accuracy on calendar scheduling and 30.8% on ZebraLogic puzzle reasoning compared to direct LLM planning.
    • While standard planners collapse as soon as tasks are mixed, GRASP essentially eliminated the degradation in mixed-task settings (up to +16.7%).
    • Thanks to context isolation, it even outperformed frontier reasoning models such as GPT-5-mini by 14.5% in some settings.
  27. 1127Computer Vision

    FuseReg: Regularizing Layer Fusion Mitigates the Reconstruction-Generation Gap in Representation Autoencoders

    • Instead of hand-picking encoder layers, it solves the problem with a single rule (FuseReg): train on random subsets of encoder layers each time.
    • It also showed theoretically that this rule acts as a penalty against sensitivity to disagreements between layers.
    • A single decoder handles full, sparse, and single-layer inputs without retraining, achieving higher reconstruction quality (PSNR) than decoders specialized to fixed fusions.
    • Replacing the decoder alone improved image generation quality (gFID) by 27%, and applying the same rule to the generation stage as well improved it by 29%.
    • The pretrained encoder is left completely untouched, so existing model assets can be reused as-is.
  28. 1126Agents

    HEXIS: Compiling Skills into Extended Finite State Machines

    • Proposed HEXIS, which compiles skill documents into FSMs by separating knowledge from control flow
    • Built an incremental compilation algorithm that aligns execution traces to find and add missing states
    • Updates are committed only after static checks and replay of all previously accepted traces pass
    • Improved success rate by an average of 16.1 percentage points over Skill+ReAct across four benchmarks and four executor models
    • Reduced Qwen3.8-27B execution tokens by 38.4-88.9% and achieved 84.2% success on SpreadsheetBench
  29. 1123Robotics

    Representation World Model: Learning States, Transition and Executable Plans in Representation

    • Proposed a world model that learns states, transitions, and plans together within a single representation space
    • Trained the representation so latent paths become actually executable plans, using inverse-dynamics supervision along the path
    • Completed planning at inference time purely by path construction, without recursive rollouts or action-space search
    • Achieved an average success rate of 93% on the LIBERO-Goal robot manipulation benchmark, far ahead of LeWM (71.2%)
    • Outperformed the strongest search-based baseline (which evaluates 384 candidate trajectories) with no search at all
  30. 1122AI Agents

    JEV-as-a-Judge: Accept When Confident, Escalate When Unsure

    • Compared a cheap verdict-plus-probability judge (JEV) fairly against sixteen generative LLM judges
    • Stayed within three percentage points of the strongest judge on ordinary preference and evidence-grounded factuality tasks
    • Measured cost was only 0.36% of the strongest comparator ($0.042 per million input tokens)
    • A cascade that accepts confident verdicts and escalates uncertain ones retained 99% of the comparator's accuracy
    • Showed clear limits on hard judgments such as checking derivations or resisting well-written wrong answers

From research to product use

Operating capabilities, pilots, and technologies in development are identified separately.

View technology