Daily AI News — 2026-08-07
Generated at 2026-08-07T06:39:13.144903-07:00 by a GitHub Actions GitOps pipeline.
Top stories
- Human-Like Anaphor Resolution in Large Language Models — arXiv cs.CL, 2026-08-07 04:00 UTC. Score 10.1 — arXiv:2608.05630v1 Announce Type: new Abstract: Anaphors are expressions that refer to other expressions, called antecedents. The process of connecting the two is called resolution. Cognitive science has identified multiple factors that affect the speed and success of anaphor resolution, including discourse structure, situation-model properties, and semantic factors. Here, we investigate whether these factors also affect anaphor resolution in five Large Language Models (LLMs) with open weights: GPT-2-XL, Llama-3.1-8B, Pythia-12B, Mistral-7B, and Mistral-24B. To model processing difficulty, we adopt the standard linking hypothesis that relate…
- The Bitter Lesson of Tool Calling — arXiv cs.CL, 2026-08-07 04:00 UTC. Score 10.1 — arXiv:2608.06370v1 Announce Type: new Abstract: Tool use transforms LLMs into agents that act beyond their training data, and for code-capable models, programmatic tool calling extends this further by replacing rigid JSON calls with scripts that chain and parallelize naturally. However, a systematic evaluation of tools as code on an established benchmark across current and prior model generations under real-world task conditions has not been conducted. In this work, we empirically compare programmatic tool calling (PTC) to native JSON tool calling across 14 language models on BFCL v4. In the programmatic tool calling paradigm, tools are expo…
- Agentic self-driving microscopy benchmarks support qualification but do not necessarily generalize to unseen tasks — arXiv cs.AI, 2026-08-07 04:00 UTC. Score 9.2 — arXiv:2608.05266v1 Announce Type: new Abstract: Large language model agents are increasingly being developed to control a wide range of scientific characterization tools including microscopes and synchrotron beamlines. Research into agentic control of physical infrastructure is nascent and there are few well-established paradigms for how to engineer an agentic system. There are many choices to make when designing a microscopy agent, including the choice of LLM, the number of agents to use, agent responsibilities and delegation rules, retrieval-augmented generation parameters, and more. When designing and optimizing an agentic microscope cont…
- EcoAgent-Bench: Evaluating Economic Decision-Making in Budget-Constrained LLM Agents — arXiv cs.AI, 2026-08-07 04:00 UTC. Score 9.2 — arXiv:2608.05519v1 Announce Type: new Abstract: Agent benchmarks usually measure task completion and treat resource use as an auxiliary statistic. In deployment, however, the choice among a local lookup, broad search, composite research tool, stronger model, or human escalation is part of the task itself. We introduce EcoAgent-Bench, in which every task specifies priced actions and an explicit budget. Its 304 real-derived tasks span five families adapted from GAIA, HotpotQA, and MuSiQue, and test four decisions: avoiding unnecessary escalation, escalating when local evidence is insufficient, selecting a model tier, and stopping on unsupporte…
- Seeing Is Not Deciding: Can Multimodal LLMs Act as Effective CEOs? — arXiv cs.AI, 2026-08-07 04:00 UTC. Score 9.2 — arXiv:2608.05864v1 Announce Type: new Abstract: Large language models are increasingly applied as autonomous decision-making agents. However, in executive business decisions, existing benchmarks are limited to textonly settings. This makes it unclear whether models can perceive visual business evidence and effectively integrate it to improve decision quality. We introduce C-SUITEBENCH, a controlled multimodal benchmark that includes five decision tasks under paired text-only and multimodal conditions across 50 scenarios. We place nine frontier models in the role of a chief executive officer and evaluate their decision-making ability. Multimo…
- Recursive Synthesis for Long-Horizon Terminal Tasks — arXiv cs.AI, 2026-08-07 04:00 UTC. Score 8.4 — arXiv:2608.05466v1 Announce Type: new Abstract: High-quality long-horizon training data for terminal agents is expensive to produce, often costing hundreds to thousands of dollars per task, because each task must keep the instruction, environment, reference solution, and verifier mutually consistent. Human authoring does not scale, and direct generation with large language models (LLMs) often breaks these dependencies. We present Recursive Synthetic Terminal Tasks (RST), a recursive verified synthesis framework for constructing long-horizon terminal-agent tasks at scale. Starting from verified seed tasks, RST extends the reference solution,…
- Simulator-Grounded Large Language Models for Industrial Causal Reasoning: Tool-Use, Structured Injection, and Plant-Portable Retrieval for Wastewater Treatment Decision Support — arXiv cs.CL, 2026-08-07 04:00 UTC. Score 8.4 — arXiv:2608.05151v1 Announce Type: new Abstract: Wastewater operators need answers grounded in how their plant's variables interact and how fast effects propagate, not in generic pretraining text, when asking causal questions such as "why is N2O rising?" or "what happens if I cut aeration by 20%?". We compare three concrete ways to ground a frozen Qwen2.5-32B-Instruct model in an architecturally interpretable wastewater simulator (CCSS-IX): a live simulator oracle (Method 1), structured parameter injection (Method 2), and a Decoupled Recall-Reasoning (DRR) retriever (Method 3). On a 198-question causal benchmark the three reach 99.5%, 79%, an…
- Scaffold-Mediated Post-Training: Co-Evolving Model Parameters and Procedural Scaffold Graphs — arXiv cs.CL, 2026-08-07 04:00 UTC. Score 8.4 — arXiv:2608.05156v1 Announce Type: new Abstract: Post-training of large language models optimizes only parameters, while inference-time procedural scaffolds are typically designed independently of parameter training. This disconnect makes it difficult to automatically acquire and internalize complex strategies. We propose scaffold-mediated post-training: procedural scaffolds are organized into an evolvable graph structure that co-evolves with model parameters through discovery, distillation, and dynamic recompilation. We instantiate this paradigm as Skill Training. On FeatureBench, automatically discovered skills improve the passed rate by 8.…
- On the Anisotropy of Score-Based Generative Models — arXiv stat.ML, 2026-08-07 04:00 UTC. Score 8.4 — arXiv:2510.22899v2 Announce Type: replace-cross Abstract: We investigate the role of network architecture in shaping the inductive biases of modern score-based generative models. To this end, we introduce the Score Anisotropy Directions (SADs), architecture-dependent directions that reveal how different networks preferentially capture data structure. Our analysis suggests that SADs form adaptive bases aligned with the architecture's output geometry, providing a principled way to predict generalization ability in score models prior to training. Through both synthetic data and standard image benchmarks, we demonstrate that SADs reliably captur…
- How HSP GRUPPE builds AI capabilities for tax advisory — OpenAI Blog, 2026-08-07 09:00 UTC. Score 6.8 — Discover how HSP GRUPPE uses ChatGPT Enterprise to boost productivity, improve work quality, and create more capacity for tax advisory and client service.
Signals to watch
- Most represented sources: arXiv cs.CL (4), arXiv cs.AI (4), arXiv stat.ML (4), AWS Machine Learning Blog (3).
- Recurring themes: model (13), benchmark (7), training (7), agent (6), gpt (4), inference (4), research (2), openai (2).
- Review the raw JSON output in
data/items/ if you want to audit scoring or feed coverage.
All links
- Selected items: 18
- AI summarization: deterministic fallback
- Source data:
data/items/ in this repository