Behavioral Privacy Leakage in Agentic Negotiation: Formalizing and Mitigating Inference Attacks via Randomized Policies
This paper was accepted at the AI4TCI (Workshop on AI for Secure and Trustworthy Critical Infrastructure Systems) Workshop at the International Conference on Availability, Reliability and Security (ARES) 2026.
Autonomous negotiation agents are increasingly deployed in high-stakes settings such as in...
Aurora 1.5: Extending open foundation models for weather and Earth-system applications
Aurora 1.5 adds 22 more variables, hourly temporal resolution, and probabilistic ensemble forecasting to the Aurora foundation model, making it more useful for real-world weather, climate, and energy applications.
The post Aurora 1.5: Extending open foundation models for weather and Earth-system app...
arXiv:2607.06757v1 Announce Type: new
Abstract: Agent-based modeling (ABM) has the capability to model millions of individuals and their interactions, which is useful for policy making. However, ABMs have traditionally relied on static prior, which prevents the models from adapting to real-time cha...
TriRoute: Unified Learned Routing for Joint Adaptive Attention, Experts, and KV-Cache Allocation
arXiv:2607.06601v1 Announce Type: new
Abstract: Conditional computation can decouple language model quality from per-token inference cost, yet leading techniques act on a single axis in isolation: Mixture-of-Experts (MoE) sparsifies the FFN, Mixture-of-Depths (MoD) skips whole transformer blocks, a...
A Quiet Failure in Calibrated Virtual Screening: Marginal Conformal Prediction Under-Covers the Minority Class, and a Class-Conditional Fix Recovers It
arXiv:2607.06605v1 Announce Type: new
Abstract: Conformal prediction is being adopted in drug discovery to put an honest number on model reliability: pick an error rate alpha, and the method returns prediction sets containing the true label with probability at least 1 - alpha. We show this guarante...
D2PO: Optimizing Diffusion Samplers via Dynamic Preference
arXiv:2607.06609v1 Announce Type: new
Abstract: We propose D2PO (Dynamic Direct Preference Optimization), a principled framework for optimizing diffusion sampling policies with respect to timestep schedules and classifier-free guidance (CFG) weights. Our work is motivated by a fundamental limitatio...
When Does In-Context Search Help? A Sampling-Complexity Theory of Reflection-Driven Reasoning
arXiv:2607.06720v1 Announce Type: new
Abstract: Training large language models (LLMs) with extended reasoning has enabled in-context search, in which models iteratively generate, critique, and revise solution attempts. We provide a theoretical analysis of in-context search by modeling it as approxi...
QANTIS: Hardware-Calibrated Sequential POMDP Belief Updates on IBM Heron
arXiv:2607.06760v1 Announce Type: new
Abstract: Autonomous systems under partial observability act on beliefs, not raw sensor events. QANTIS treats the quantum processor as a calibrated belief-update service in that loop: it receives a prior and an observation model, estimates the rare-event eviden...
Cost-Effective Agent Harnesses for Abstract Reasoning and Generalization on ARC-AGI-1
arXiv:2607.06764v1 Announce Type: new
Abstract: Recent progress on ARC-AGI-1 from disclosed architectures has come broadly from two regimes: heavy test-time compute over frontier models (evolutionary search, exhaustive sampling, extended chain-of-thought), or benchmark-specific training in which sm...
Incentivizing Temporal-Awareness in Egocentric Video Understanding Models
Multimodal large language models (MLLMs) have recently shown strong performance in visual understanding, yet they often lack temporal awareness, particularly in egocentric settings where reasoning depends on the correct ordering and evolution of events. This deficiency stems in part from training ob...
Biomni can analyze mountains of medical data, spot patterns humans might miss, and even design experiments—helping researchers make discoveries faster in the race to cure disease.
Recursive Language Models Meet Uncertainty: The Surprising Effectiveness of Self-Reflective Program Search for Long Context
Long-context handling remains a core challenge for language models: even with extended context windows, models often fail to reliably extract, reason over, and use the information across long contexts. Recent works like Recursive Language Models (RLMs) have approached this challenge by agentic way o...
Short chart specifications are easy to write, but often produce uninspiring results. Flint is an open-source visualization language that offers a middle path, letting AI agents create expressive charts from compact, human-editable specifications.
The post Flint: A visualization language for the AI e...
arXiv:2607.05573v1 Announce Type: new
Abstract: Recent advances in Large Language Models (LLMs) and Vision-Language Models (VLMs) enable the automatic generation of parametric 3D designs from natural-language specifications. This chapter presents an empirical study of foundation models for automati...
Statistically Meaningful Geometry and Gauge Symmetry Breaking: A Geometric Foundation for Scientific Discovery and Intelligence Emergence
arXiv:2607.05436v1 Announce Type: new
Abstract: The rapid scaling of over-parameterized machine learning architectures, particularly LLMs, raises a profound crisis: do these systems exhibit genuine intelligence, or are they merely sophisticated statistical pattern matchers? Classical flat Euclidean...
Design-CP: Context Parallelism for Design of Protein Nanoparticles
arXiv:2607.05439v1 Announce Type: new
Abstract: Many all-atom generative protein models can in principle design large multimeric complexes by jointly modelling all chains, but their quadratic token- and atom-pair representations quickly exceed single-GPU memory as the number of chains and residues ...
Exogenous Dropout: A Simple, Strong Baseline for Corruption-Robust Time Series Forecasting with Covariates
arXiv:2607.05452v1 Announce Type: new
Abstract: Time series forecasters that use exogenous covariates are fragile in deployment: when those covariates are noised, temporally misaligned, or missing, strong exogenous-fusion and exogenous-adapted models can degrade far above the endogenous-only floor....
Prompt-to-Paper: Agentic AI System for Bioinformatics
arXiv:2607.05456v1 Announce Type: new
Abstract: While recent advances in large language models have enabled end-to-end automated manuscript generation, existing systems suffer from three critical deficiencies: (i) generated claims are not deterministically grounded in verifiable literature, (ii) ex...
CSTutorBench: Benchmarking Small Language Models as Tutors for Block-Based Programming
arXiv:2607.05571v1 Announce Type: new
Abstract: Large language models are increasingly explored as AI tutors, yet deploying them in K-12 settings raises concerns around privacy, cost, and reliance on proprietary models. Small language models (SLMs) offer a promising alternative, but selecting the r...
Narrative World Model: Narratology-Grounded Writer Memory for Long-Form Fiction
arXiv:2607.05577v1 Announce Type: new
Abstract: Long-form fiction writers need memory that answers multi-hop questions about evolving story state: who knows a secret and when they learned it, whether an event preceded the narration that revealed it, whether a setup paid off, and how a relationship ...
Q&A: How Headroom went from side project to enterprise infrastructure.
Tejas Chopra built Headroom, an open-source context compression layer for Claude and Codex, to stop burning through his own token budget. Six months on, he's left Netflix to build Headroom Labs full time. In this Q&A, he walks through the agent-to-agent context problem he's building toward next...