What happened
arXiv:2609.12265v1 Announce Type: new Abstract: Large Language Models (LLMs) are increasingly asked to reason over structured data such as graphs, yet how reliably they can carry out multi-step graph algorithms in language remains unclear. Existing evaluations tend to use simple tasks on small graphs, to score code generation rather than reasoning over the graph itself, or to fix a single input format. We introduce Graph Theory Bench (GT Bench), a benchmark covering 24 classical graph problems in 44 task-structure settings, with over 100,000 examples across four representations: natural language, structured language, adjacency list, and adjacency matrix. Evaluating eight LLMs on GT Bench shows that accuracy is strongly tied to the input representation, that the best representation shifts with graph density, size, and topology as well as with the model, and that this sensitivity persists, attenuated, in the strongest reasoning models. Building on these observations, we propose the Graph Theory Agent (GTA), which pairs a preference-trained representation selector with plan-and-decompose scaffolding around a frozen executor LLM. GTA lifts Phi-4 from 53.5% to 69.1% on the benchmark's easy split and from 33.0% to 41.5% on its hard split, outperforming eight prompting and agent baselines, and transfers without retraining to GraCoRe and NLGraph. Code for benchmark generation and evaluation: https://github.com/xzx34/GTA. The project homepage is available at https://xzx34.github.io/gta/. Update (2026-09-16): BLINDSPOT: A Benchmark for Safety and Refusal Calibration in Long-Horizon Tool-Using Agents. arXiv:2609.16305v1 Announce Type: new Abstract: Large language model (LLM) agents increasingly operate over long-horizon interactions involving tool use, persistent state, evolving authorization, and external environment feedback. In such settings, safety failures may emerge only after multiple turns, yet existing evaluations often reduce agent behavior to task or attack success, obscuring whether an agent acts, refuses, or remains appropriately calibrated as the interaction evolves. We introduce Blindspot, a benchmark for trajectory-level safety calibration of long-horizon tool-using agents. Blindspot evaluates complete user-agent-environment trajectories through adaptive adversarial interaction, stateful tool execution, and execution-grounded adjudication. Its current instantiation contains 22 attack families and 35 scenarios across seven domains, yielding more than 2,500 long-horizon trajectories with an average interaction length of 14.7 turns. Each trajectory is assigned one of five outcomes: Safe Completion, Correct Refusal, Unsafe Completion, Over-Refusal, or Update (2026-09-18): BioPhys-Bridge: A Benchmark for Interdisciplinary Scientific Reasoning in Physics-Grounded Biological Research. arXiv:2609.19180v1 Announce Type: new Abstract: Language models face unique challenges in analyzing interdisciplinary scientific research literature. In biophysics research, faithful answers require grounding observed data in source evidence, interpreting it through a quantitative physics model, and linking it to a biological mechanism. To address this challenge, we introduce BioPhys-Bridge, a novel benchmark dataset for evidence-grounded scientific reasoning over biophysical literature. Each case contains evidence blocks, stable evidence IDs, quantitative values, units, equations, assumptions, mechanisms, and next decisions as grounding targets for question answering (QA) and retrieval-augmented generation (RAG). The initial release contains 500 cases, 1,517 agent-facing tasks, and covers six biological domains and nine physical model families, including three sparse families reserved for future expansion. We enforce strict quality gates for all cases in schema, evidence-integrity, quantitative-grounding, source-license, duplicate, unit-normalizat Update (2026-09-18): Do AI Agents Understand Computer Architecture?. arXiv:2609.19387v1 Announce Type: new Abstract: Agents are increasingly asked to design hardware, and increasingly reported to succeed. Such reports establish that a design improved; they cannot establish why. An agent that improves an accelerator may be reasoning about the machine, or may be searching competently over knobs whose meaning it never recovers -- and only the first transfers to the next architecture. Existing evaluations cannot tell the two apart, because they vary the agent while holding the framing of the problem fixed. We do the opposite. AutoTuring hands the same agent the same 15-dimensional accelerator space twice: once as named architectural knobs with simulator counters, once as anonymous variables on [0,1], with the evaluator, the legal space and the reachable optima held identical, so that the only thing that varies is whether the problem means anything. The gap between the two is the measurement. On a nine-kernel FP16 GEMM basket, meaning pays: the architect beats a modeled H200 by 5.4% and its blind counterpart by 12.3% on average, with 70.1% fewer simulator calls. It does not pay uniqu Update (2026-09-18): Interrogating contrastive learning embeddings for structure-based virtual screening: a case study on DrugCLIP . Virtual screening has become central to early-stage drug discovery, and structure-based approaches have recently been reframed as a retrieval problem through contrastive learning methods such as DrugCLIP, which project protein pockets and ligands into a shared embedding space. However, what these abstract representations exactly encode, and how they relate to conventional notions of structural and chemical similarity, remains unclear. Here we present a systematic dissection of DrugCLIP's latent space. We show that its pocket embeddings, despite not being explicitly trained for the task, set a new state of the art in pocket similarity search while running over 100 times faster than existing structural descriptors, and that this embedding space is structurally coherent and robust to conformational variation. Ligand embeddings, by contrast, encode a pocket-aware notion of chemical similarity that only partially mirrors fingerprint-based measures. Using a rigorous de-leakage benchmark, we further show that DrugCLIP generalises to unseen proteins and Update (2026-09-21): Detecting Hallucination in LLMs: Tracing the Topological Signatures of Impaired Context Sharing. arXiv:2609.21096v1 Announce Type: new Abstract: In this work, we examine the topology of information flow patterns within attention graphs to effectively distinguish hallucinated from non-hallucinated responses. We analyze the Forman-Ricci curvature to identify structural patterns indicating information bottlenecks in attention graphs. We then introduce a method that captures both semi-local and global information-flow characteristics of attention heads associated with hallucinated responses. We evaluate our approach extensively across several LLMs and established benchmarks. Empirical results demonstrate that our proposed single-pass approach provides consistent improvements over existing attention-based and multi-response baselines across two hallucination-detection benchmarks, while achieving competitive performance across diverse LLM architectures. Further analysis reveals that impaired context sharing among tokens during causal generation is strongly associated with hallucination occurrences in LLMs. In particular, hallucinated responses are consistently cha Update (2026-09-21): PlaceReasoner-Beta: Reasoning-Driven Macro Placement and Benchmarking. arXiv:2609.21263v1 Announce Type: new Abstract: Automated macro placement remains a fundamental challenge in VLSI physical design. Despite decades of research, existing approaches predominantly optimize hand-crafted proxy objectives, such as estimated wirelength, and typically produce placements through one-shot numerical optimization, limiting their ability to incorporate visual layout context, codified design expertise, and downstream physical-design feedback in a unified loop. We present PlaceReasoner-Beta, a verifier-guided multi-agent framework that reformulates macro placement as a closed-loop reasoning problem rather than black-box optimization. A vision-language model (VLM) planner generates candidate placements from the floorplan image, macro specifications, and connectivity structure; a geometric verifier enforces physical legality and expert placement principles; a physical verifier refines candidates using early implementation feedback; and a post-route optimizer further improves promising layouts using final PPA. To enable reproducible evaluation, we introduce PlaceReasoner-B Update (2026-09-22): IntLawNER: A Named Entity Recognition Dataset and Benchmark in International Law. arXiv:2609.22529v1 Announce Type: new Abstract: International law provides the normative framework through which states coordinate action, regulate armed conflict, and protect human rights, yet its texts remain without token-level named entity recognition (NER) resources. We introduce IntLawNER, a NER dataset and benchmark for codified sources of international law, covering 2,987 gold-annotated sentences and 8,094 entity spans from International Court of Justice (ICJ) decisions, UN Security Council resolutions, and European Court of Human Rights (ECtHR) judgments, annotated with seven institution-specific entity types. We construct IntLawNER with a cost-effective hybrid algorithmic-agentic pipeline that reduces 468k source sentences to a compact annotation set through candidate retrieval, LLM-based vetting, and human review, with 89.6% of gold spans accepted unchanged from the silver layer. However, the silver-to-gold analysis reveals that human-machine aggregate agreement metrics can be misleading in domain-specific NER: Cohen's kappa=0.964 on boundary-matched spans masks a ma Update (2026-09-22): AutoGym: Blueprint-First Generation of Verifiable Agent Gyms. arXiv:2609.22592v1 Announce Type: new Abstract: Training agents with reinforcement learning requires a gym, comprising a task, an executable environment in which the task can be attempted, and a verifier that reliably distinguishes success from failure. Constructing such gyms remains manual, expensive, and static. Task sets saturate as models improve and are increasingly exposed to contamination. Synthetic generation offers scale, but single-pass synthesis produces tasks whose difficulty is largely cosmetic. Models comparable in capability solve them despite convoluted phrasing, and correctness must be adjudicated post-hoc by unreliable LLM judges. We present AutoGym, a framework that generates complete gyms (tasks, executable environments, and verifiers) from a minimal domain seed or prior model trajectories. AutoGym introduces three mechanisms. (1) Blueprint-first generation specifies the valid solution space, environment requirements, and verification criteria before the environment is materialized, making solvability a construction prerequisite rather than a property verified after the fact. ( Update (2026-09-22): Self-Organizing Agent Teams Learn to Reason Together. arXiv:2609.22682v1 Announce Type: new Abstract: Collective intelligence depends not only on what team members know, but also on how they organize their work. When the structure of a solution is unknown, useful roles and divisions of labor cannot be specified in advance; teams must learn from experience how to organize reasoning as it unfolds. Human teams routinely adapt this way, while existing AI agent teams rely on fixed protocols, explicit task decomposition, or routing. We introduce Self-Organizing Agent Teams (SAT), fixed teams of AI agents that learn reusable strategies from prior collaborations to organize roles, conversational phases, participation, and information flow. These strategies enable what we call collaborative computation: agents exchange, challenge, repair, and synthesize partial reasoning into solutions no member produced independently. In two independent settings, we learn teamwork strategies that transfer unchanged to unseen benchmarks, using only 15 mathematics and 25 graduate-level knowledge problems. Across five mathematics and physics benchmarks, self-organizing teams average 66 Update (2026-09-23): Clarification Is Not Correction: LLMs Fail to Let Go. arXiv:2609.25337v1 Announce Type: new Abstract: Dialogue failures in language models are usually framed as memory failures: context too long, summaries lossy, a constraint forgotten. We argue this misses a deeper problem: in many conversations the model does not forget, it commits too early. An ambiguous early turn collapses into a single hidden interpretation, and later clarification is filtered through that commitment. We call this early posterior collapse: unresolved user intent collapsing into a committed task state before ambiguity is resolved. We study it with controlled dialogue tasks in writing, planning, and coding using Gemini-2.5-Pro and Gemini-2.5-Flash. Across thousands of trials, the same information in different orders yields different outcomes, even when the final dialogue contains equivalent task-relevant information. This order effect suggests later clarification is treated as extra context rather than a corrective signal: it refines a stale task state without invalidating it. Coding tasks are especially vulnerable, suggesting early assumptions get embedded in structured artifacts such a Update (2026-09-23): Show HN: RxFilm Studio–Create and edit your product videos with AI agent. Hi HN, I built RxFilm Studio, a video workspace that lets you create and revise videos with AI agent. The reason I started this project is simple: I’ve noticed that many independent developers and small teams want to create marketing videos for their product, but producing these videos requires a lot of time and effort — from editing and visual effects to voiceovers and subtitles. So I built Rxfilm Studio to simplify the entire video creation process. Start with an idea, a product website, images, or existing footage, and then generate a complete video with: - Story and structure - Editing and timeline - Visual and sound effects - Voiceovers, background music - Subtitles and translation Github: https://github.com/rxtech-lab/film-workflow Here's a demo marketing video created using RxFilm Studio: https://youtu.be/9_M15fRdZQE Welcome to try it out and I would love to hear your feedback! Comments URL: https://news.ycombinator.com/item?id=49815095 Points: 5 # Comments: 1 Update (2026-09-24): Oracle cites 'force majeure' to shield itself on controversial data center. https://qz.com/oracle-force-majeure-new-mexico-ai-data-cente... Comments URL: https://news.ycombinator.com/item?id=49830037 Points: 103 # Comments: 91 Update (2026-09-24): When Prognostic Compatibility Does Not Guarantee Transfer Utility in Event-Limited Cross-Species Survival Modeling . Cross-species molecular transfer may improve prognostic modeling in rare cancers, but under severe target-event scarcity the same data can easily be used to fit, choose, and evaluate adaptation, increasing the risk of negative transfer and model-selection bias. We evaluated canine-to-human osteosarcoma survival transfer using a chronologically frozen design. DOG2 served as the canine source domain, 50 MSigDB Hallmark modules defined the shared representation, and a known-truth benchmark comprised 180 scenarios and 21,600 replicates spanning 5 - 40 target events and multiple transport regimes. A frozen safety rule compared low-rank and module-selective adaptation; later diagnostics and a 6,000-replicate disjoint-seed mechanism experiment could not alter that decision. Neither selectable architecture met the negative-transfer limit (0.215 and 0.486 versus 0.10), although oracle analyses showed that the threshold was attainable. Prespecified post-HOLD weighting and threshold sensitivities showed that benchmark composition amplified the magnitu