Record 14102026 · captured 2026-10-15
0 tracked subjects, 25 discussions, 25 papers. This record is frozen and will not change.
Complete record JSON
What the people building things argued about, from Hacker News.
Papers submitted to arXiv cs.AI that day.
Modeling and Understanding Neural Weights of Humanoid Policies with Diffusion
Recent advances in robot learning have driven rapid progress in humanoid control, enabling increasingly agile behaviors in the real world. However, humanoid control networks are typically obtained through conventional training procedures, while comparatively little attention has been given to directly modeling the distribution of their learned weights and generating functional networks in weight space. In this work,
Hierarchical Residual Policy Learning for Real-World Mobile Manipulation with Sparse Human Guidance
Mobile Manipulation (MoMa) is a cornerstone of autonomous robotic systems, yet real-world fine-tuning remains a formidable challenge because of high-dimensional action spaces and intricate coupling between heterogeneous modules. In this paper, we propose HiRe-MoMa (Hierarchical Residual Mobile Manipulation), a systematic framework for stable and sample-efficient real-world fine-tuning of complex MoMa systems. At its
Co-Evolving Acting and Forecasting for Language Agents
Training language agents is bottlenecked by the high cost of long-horizon rollouts, yet standard agentic reinforcement learning (RL) learns only from a terminal scalar reward, leaving the supervision in intermediate steps largely unused. Prior work exploits this supervision through value targets that estimate per-step success probabilities or observation targets that fit environment response. Both are hard to constru
Your Transformer Is Secretly Elastic
Scaling up transformers has produced models with broad capabilities, deployed across heterogeneous hardware and fluctuating workloads. Yet, model families offer only a few fixed sizes (e.g., S, B, L), forcing users to commit to a model based on hardware and latency constraints. This rigidity is often suboptimal under varying query loads. We introduce a retraining-free method that elastifies pre-trained transformers i
Price of Anarchy of First-Price Auctions in Agentic Markets
An agentic market is a decentralized serving-time market where AI agents bid to claim each user prompt. An agent's bid is based on its expected value for the prompt, which is the expectation of the reward for its response minus its inference costs. First-price auctions (FPAs), in which the highest bidder pays its bid and receives the prompt, are a natural way to allocate prompts in such a market, since they are simpl
We introduce Continuum Attention (CA), a causal Transformer attention operator that replaces discrete key and value lookup with integration over a continuous, piecewise linear memory curve. Each query induces an exponential relevance density along the curve. Integrating the density and interpolated values yields exact normalized attention from closed form exponential moments, including half token boundary contributio
Player-1: Learning to Play from Synthetic Experience
Computer-use agents have demonstrated strong capabilities in interpreting screens and executing keyboard and mouse actions. However, games, with their visually rich worlds and diverse mechanics, remain challenging and offer a demanding next step toward general digital control. Current game-agent learning pipelines often rely on large-scale demonstrations with limited coverage of dynamic game states, while scalable en
One Task, Many Interfaces: Simple Cross-Interface Consistency Training Improves LLM Agent Robustness
Post-training binds the competence of an LLM agent to the interface it was trained on. Semantics-preserving perturbations of that interface, such as renaming an action or changing the notation, leave the underlying task unchanged yet make the agent worse at it. Scoring each sample independently means interface randomization only broadens this dependence from a single interface to the training interface distribution,
Beyond LLM Judge: Mechanical Verification for Agentic Autoformalization
We introduce a novel method for verifying Lean formalizations that goes beyond LLM-judged faithfulness. Unlike most verification methods, which rely on LLMs or trained models, our method combines LLM-based semantic review with mechanical numerical and vacuity checks, providing checkable feedback and detecting errors missed by LLM judges. We apply this method, along with our Extract-Verify-Proof autoformalization pipe
Recovering Reliable Supervision via Critique-Guided On-Policy Distillation
On-policy distillation (OPD) trains a student model on its own rollouts with token-level supervision from a teacher, assuming that the teacher can reach a correct answer from any prefix the student writes. We call this property the recoverability of the teacher and show it fails on incorrect rollouts: the teacher follows student errors, although it recognizes them. We propose CriticOPD, using error recognition to res
Scaling Discovery Requires Forgetting
Automated research with LLM agents has shown promising results in various domains. Through iterative refinement and scored verifiers, LLM agents are capable of discovering new ideas. There are different ways to scale automated research: let one agent iterate for longer, run several agents in parallel, or further let the parallel agents communicate and build on one another's candidates. However, we find that all three
PhySGA: A Physics-Space Grounded Agentic Framework for Generalizable and Interactive 3D Composition
3D object composition is pivotal to digital content creation and robot simulation, while also serving as a critical testbed for physical intelligence in foundation models. Previous methods either leverage large language models to directly predict object coordinates, or utilize generative diffusion priors to synthesize composite images for visual alignment, both of which rely on static priors in digital spaces. Howeve
PerSo: Investigating Facets of LLMs' Social Intelligence in Real-World Persuasion Scenarios
Understanding the social intelligence of large language models (LLMs) is increasingly important for applications involving human-AI interaction and multi-agent environments. Social intelligence comprises two aspects: cognitive intelligence, the ability to infer others' mental states, and behavioral intelligence, the ability to select appropriate social actions based on these inferences to achieve social goals. Persua
Detection of Potato Plant Leaf Diseases using Convolutional Neural Networks
Potato is an important food-security crop in Ethiopia, but its production is affected by foliar diseases, particularly early blight and late blight. This study develops a lightweight convolutional neural network (CNN) to classify potato leaves into three categories: healthy, early blight, and late blight. The proposed model was trained using 2,215 images from the PlantVillage dataset and evaluated on an independent f
Multimodal code intelligence connects the symbolic world of programs with the visual world their execution creates. Interest in this capability is burgeoning, as models are increasingly asked to produce charts, webpages, animations, and semi-structured documents. Recently, proprietary models have pushed far ahead, producing interactive artifacts even from a text description or a screenshot alone. Yet their data and t
ActiveEvidence: Decision-Focused Evidence Graphs with Verifiable Acquisition Gaps
A multimodal agent must decide whether visual evidence is worth acquiring, which candidate or resolution to query, and when further interaction can no longer change its decision. We study this problem under a strict free-metadata/paid-observation boundary, stochastic vector costs, and a frozen execution trace, and treat it as decision-certifiable active evidence acquisition. A Counterfactual Evidence Interaction Grap
The Wealth of Agents: Scaling Agentic AI Across Developers
Today's agentic systems are typically designed, built, and deployed by single developers with full control over all participating agents. While this simplifies development, it limits the potential scale of agentic systems. We study multi-developer agentic systems (MDAs) which enable developers to collaboratively build agentic systems to push frontier capability beyond what any individual developer could achieve alone
VASPO: Self-Distillation with Privileged Value Estimation
On-policy self-distillation provides dense supervision for reasoning models via a privileged self-teacher. However, this supervision reflects local token preferences rather than the expected return of an unguided student continuation. Recent methods combine this signal with GRPO. They use GRPO for update directions and the teacher for signal scaling. However, we demonstrate a more effective integration within PPO. Sp
VascuSR: Iterative Anatomy-Aware Diffusion for CT Super-Resolution
Generative super-resolution (SR) can recover sharp detail in computed tomography (CT) images from severely downsampled observations, but the missing high-frequency content is not uniquely determined by the low-resolution input. Consequently, visually plausible reconstructions may contain anatomically unsupported vascular detail, such as missing, spurious, or incorrectly connected vessels. To overcome this challenge,
Hindsight-Privileged RLVR: Single-Rollout Token Credit Without Group Sampling
Reinforcement learning with verifiable rewards (RLVR) trains language models from checked task outcomes, but assigning a terminal reward to individual reasoning tokens or actions remains difficult. Group-relative methods such as Group Relative Policy Optimization (GRPO) sample several attempts per prompt, but lose their reward-based learning signal when all attempts receive the same outcome. We propose Hindsight-Priv
Quantifying privacy risks in foundation model representations of brain MRI
Pretrained representations are increasingly used to share and reuse information from medical images without exposing the original scans, but it is unclear how much patient-specific information these representations retain. We investigate this question for brain magnetic resonance imaging (MRI) by evaluating five frozen pretrained encoders spanning different architectures, pretraining objectives, and training domains
SafeAdapt-Poker: Counterfactual Risk Calibration for Budgeted Adaptation under Opponent Shift
Opponent histories can mislead after behavioral shifts. SafeAdapt-Poker formulates budgeted adaptation under opponent shift as a dual-counterfactual sequential-control problem using only information available before each decision. At each decision the controller asks two distinct questions: what local downside a deviation from the frozen anchor would induce under matched legal continuations, and what future adaptatio
Selective Growing Q-Networks (SGQN): An Analysis of Adaptive Action Grids in Decoupled Q-Learning
Value-based Q-learning for continuous control can discretise the action space, but the resolution of the discretisation trades early exploration against final precision. Growing Q-Networks (GQN) grow the resolution uniformly from coarse to fine. We introduce Selective Growing Q-Networks (SGQN), which keeps decoupled Q-learning and replaces uniform growth with an adaptive action grid: bins are added next to bins with
Equal CER, Unequal Damage: Severity-Weighted Character Error Rate for OCR
Character Error Rate (CER), the standard metric for OCR and vision-language models (VLMs), charges a typo as much as a wrong name. We introduce semCER, which keeps CER's alignment and denominator and charges each grapheme edit a severity from an LLM judge, with no word segmentation. Normalized CER keeps the score of a whole transcription, where it tracks readers as well as semCER or better, and semCER breaks that sco
Mid-2026 reporting on autonomous AI evaluation incidents claimed that frontier large language model (LLM) agents escaped server containment through emergent coordination and cloud infrastructure attacks. This paper contextualizes those claims through forensic analysis and containerized recreation of both the Highly Persistent Internal Model (HPIM) training-case conditions and the Phase One privilege escalation target
Origins publishing files written for machines rather than people. Measured against a frozen cohort, so a change in the number means a change in adoption.
| Signal | Web head Tranco top 1,000 n=1,000 | Web tail sampled to rank 100k n=1,000 | AI-native model & dev platforms n=110 |
|---|---|---|---|
| Any agent-facing signal | 12.3% (123) | 4.8% (48) | 74.55% (82) |
| llms.txt (apex domain) | 10.1% (101) | 4.1% (41) | 60.91% (67) |
| llms.txt (docs subdomain) | 4% (40) | 0.9% (9) | 46.36% (51) |
| .well-known/mcp.json | 0.6% (6) | 0.2% (2) | 9.09% (10) |
| .well-known/agents.txt | 0.3% (3) | 0.1% (1) | 0% (0) |
| ai.txt | 0.3% (3) | 0.1% (1) | 0% (0) |
| ai-plugin.json (deprecated) | 0.6% (6) | 0.2% (2) | 0.91% (1) |
Notable events recorded on this day and month across all years.