Live · updated just now

The AI world,in 5 minutes a day

Models, product launches, funding, papers, tools, and policy — aggregated and deduped, so you only see what's worth reading today.

Models Products Funding Papers Tools Policy

Live aggregationFetched just now · 9/10 sources online

Today's headlines

19 stories

Papers Hot

OpenAI-HuggingFace: A Reproduction & Lessons for Alignment Testing

arXiv:2609.35799v1 Announce Type: new Abstract: In July 2026, OpenAI's agents coordinated over channels outside their intended environment to breach Hugging Face's secured infrastructure. Could existing alignment testing practices have foreseen this incident? If not, what needs to change? We explore these questions. First, we identify the misaligned behaviors that caused this incident. Then, we show how to elicit these behaviors from publicly available models manually and that auditing agents can do the same if given a large compute budget. Based on our results, we propose directions to improv

arXiv cs.AI·just now

Papers Hot

Neurosymbolic Routing for Reliable Reasoning on Resource-Constrained Edge Devices

arXiv:2609.35833v1 Announce Type: new Abstract: Running a language model on edge hardware provides private and low-latency reasoning without a network connection, and yet the small models that fit on such devices are unreliable on the tasks computers are expected to handle well, such as arithmetic, algebra, and formal logic problems. We argue that much of this unreliability is avoidable. Many queries appearing to demand reasoning are in fact structurally deterministic and permit fast and exact symbolic solutions. Therefore, forcing a probabilistic model to approximate them sacrifices accuracy

arXiv cs.AI·just now

Papers Hot

Is Human-Readable Text Necessary for Effective LLM Fine-Tuning?

arXiv:2609.35868v1 Announce Type: new Abstract: Is human readability necessary for effective fine-tuning of large language models? We investigate whether model-conditioned training representations can preserve or improve adaptation utility without requiring a human-readable textual form. We propose Desired-Update-Aligned Synthetic Data (DASA), which uses activation-gradient feedback from a frozen reference model to guide the optimization of continuous synthetic input embeddings. Inspired by the role of activation gradients in local risk reduction, DASA targets useful adaptation updates rather

arXiv cs.AI·just now

Papers Hot

The Price of Token Boundaries: Compression Certificates and Prediction

arXiv:2609.35869v1 Announce Type: new Abstract: Pre-tokenisation restricts which text fragments can become prediction units, but its compression cost is obscured when tokenisers are compared only under the same boundaries. We measure this cost by bounding the minimum token count from both sides, with and without a regular-expression boundary rule. Nonnegative prices on token occurrences yield a lower bound through shortest paths and vocabulary-budget selection; maximising over all prices recovers the linear programming relaxation, and an independent integer checker certifies the reported value

arXiv cs.AI·just now

Papers Hot

Risk-Averse Online POMDP Planning via CVaR of the Immediate Cost with Performance Guarantees

arXiv:2609.35874v1 Announce Type: new Abstract: Online POMDP planners optimize the expected cumulative cost, which can mask dangerous states when the belief places significant mass on high-cost states. Existing risk-averse methods apply static or dynamic Conditional Value at Risk (CVaR) to the value function, capturing trajectory-level risk, but share two gaps: (i) by retaining the immediate cost as an expectation of a state-dependent cost over the belief, the risk \emph{within} the belief is left unaddressed; and (ii) by modifying the value function, they require new tailored algorithms rathe

arXiv cs.AI·just now

Papers Hot

Beyond Symmetric Agents: Cognitive Diversity and Multi-Agent Debate in Small Language Models

arXiv:2609.35875v1 Announce Type: new Abstract: Multi-agent debate (MAD) reportedly improves reasoning and factuality over single-model inference, but prior work treats agents as symmetric peers, leaving open what drives the gains. We test the hypothesis that cognitive diversity among agents is the driver, in the setting where the question is still measurable: small open-weight models with benchmark headroom. Across 23 models from eleven vendor families, five tasks, and 5,500+ debate and control runs, we vary diversity along three axes - personas, sampling temperature, and model identity - pai

arXiv cs.AI·just now

Papers Hot

Representational Simplicity and Circuit Size Dissociate in a Threshold-Dependent Way: A Controlled Test via Adversarial Training

arXiv:2609.35890v1 Announce Type: new Abstract: Sparse-autoencoder decomposability and concentrated feature attribution are increasingly treated as evidence that a model's computation is easier to reverse-engineer. Whether this representational and attributional cleanliness actually predicts a smaller or more tractable causal circuit remains an open question. We test this directly using adversarial training as a controlled instrument: it reliably reshapes internal representations, but this alone does not constitute a test of circuit size. We investigate this question through reverse-engineerin

arXiv cs.AI·just now

Papers Hot

Self-discovering RL in the Era of Experience: Is Learning History an Asset or a Burden?

arXiv:2609.35897v1 Announce Type: new Abstract: The pursuit of recursive self-improvement (RSI) toward general intelligence is divided between macro-level language model scaling and the interaction-driven principles of "Era of Experience". Yet, any self-improving architecture ultimately rests upon its underlying optimization engine: if general intelligence requires learning from grounded interaction, the reinforcement learning (RL) update rule itself must be capable of cumulative adaptation. While algorithm self-discovery has produced Disco103 that surpassed PPO to achieve SOTA benchmark perfo

arXiv cs.AI·just now

Papers Hot

Grab a Coffee: Future-Aware Guidance for Discrete Diffusion with Compiled Objectives

arXiv:2609.35924v1 Announce Type: new Abstract: Discrete diffusion models generate sequences by iteratively resolving multiple tokens in parallel, offering a flexible alternative to left-to-right generation. However, guiding this process with a sequence-level objective is difficult because the value of one unresolved token depends on the other tokens with which it can form a high-reward sequence. Enumerating all such completions makes the whole guidance computation grow exponentially with the number of unresolved positions. We introduce COFFEE, a plug-and-play framework that avoids this enumer

arXiv cs.AI·just now

Papers Hot

Right Words, Wrong Moment: A Clinician-Grounded Analysis of Distress in 19,930 Conversations between Young People and ChatGPT

arXiv:2609.35953v1 Announce Type: new Abstract: Young people increasingly turn to General-Purpose Conversational Agents (GPCAs), such as ChatGPT, in moments of distress. We examine young adults' (ages 18-25) experiences using ChatGPT. We first collected 19,930 ChatGPT conversations and survey data from 158 young adults. We then selected five example conversations reflecting user distress. Finally, we asked ten clinicians to review those five conversations. We found distressed participants reported greater emotional engagement with ChatGPT and greater behavioral change from using it than their

arXiv cs.AI·just now

Papers Hot

FD-VAD: Semantic Endpoint Detection for Streaming Full-Duplex Speech

arXiv:2609.35791v1 Announce Type: new Abstract: Natural turn-taking in full-duplex voice interaction requires determining from partial speech whether a pause reflects hesitation or a completed conversational intent. Acoustic voice activity detection lacks this semantic information, while cascaded ASR-based endpointing introduces transcription dependence and additional processing stages. We formulate semantic endpoint detection as a causal audio-language reasoning task and introduce FD-VAD, an ASR-free streaming endpointer that maps bounded causal audio windows directly to Continue/Stop decisio

arXiv cs.CL·just now

Papers Hot

Sieve and Sage: Efficient Distraction Filtering for Reliable RALM Abstention

arXiv:2609.35794v1 Announce Type: new Abstract: Just as Socrates recognized the limits of his own knowledge, Retrieval-Augmented Language Models (RALMs) should learn to abstain when the retrieved evidence cannot support a reliable response. Existing approaches largely rely on monolithic LLMs to handle heterogeneous retrieval failures in a single step, resulting in limited abstention performance and high computational costs. We instead decompose retrieval failures into two distinct states: (i) the unanswerable state, where the required evidence is absent, and (ii) the distracted state, where re

arXiv cs.CL·just now

Papers Hot

Developing an OCR model for Extracting Information from Invoices with Korean Language

arXiv:2609.35796v1 Announce Type: new Abstract: Invoices are commercial documents that contain various pieces of information, including the purchased items, time, and total money. Making the extraction of important information crucial. The stored information serves different purposes. Korean language is the native language of about 80 million people, playing an important role in not only South and North Korea but also in many other countries such as Vietnam, Philippine where a large number of Korean companies are located. In this context, to automatically extract proper information from the in

arXiv cs.CL·just now

Papers Hot

From Lexical Baselines to Agentic Retrieval-Augmented Generation: Structured Skill and Responsibility-Level Extraction with the SFIA Framework

arXiv:2609.35806v1 Announce Type: new Abstract: Automated skill extraction underpins workforce planning, yet most systems represent skills as flat labels with no notion of the responsibility level at which a skill is practiced. The Skills Framework for the Information Age (SFIA) captures exactly this dimension, defining 147 professional skills across seven responsibility levels, but no automated LLM-based extraction targeting SFIA has been reported. We formalize the task as structured prediction of (skill, level) pairs from free text and ask three questions: how accurately can text be mapped o

arXiv cs.CL·just now

Papers Hot

Environment Steering: Using Data Flow Control to Improve Agent Utility and Safety

arXiv:2609.35807v1 Announce Type: new Abstract: LLM agents can make unsafe tool calls even when instructed to behave safely. Existing defenses constrain agents before execution, modify tool inputs/outputs, or rely on LLM judges; these approaches may depend on model behavior or block unsafe actions without helping the agent recover. We argue that the execution environment should instead enforce safety as the agent runs and steer it toward safe alternatives when violations occur---we call this Environment Steering. We implement this by modeling the agent and harness execution state as database t

arXiv cs.CL·just now

Papers Hot

When Successful Memories Mislead Embodied Agents:Memory Adaption For Task-Conditioned Execution

arXiv:2609.35808v1 Announce Type: new Abstract: Experience reuse can reduce repeated exploration in embodied agents, but a trajectory that succeeded previously may be unsuitable for the current execution context. Existing memory systems pri marily optimize construction and retrieval; semantic relevance and historical success therefore remain insufficient when retrieved ex perience contains incompatible actions or an inappropriate level of structure. We introduce Memory Adaptation for Task-Conditioned Execution (MATE), a deterministic post-retrieval procedure that converts trajectories into exe

arXiv cs.CL·just now

Papers Hot

TRACE: Deployable Tree-Relational Structure Enhancement for Oncology LLMs

arXiv:2609.35810v1 Announce Type: new Abstract: Large language models are increasingly used in oncology applications, but their predictions are often weakly grounded in explicit medical structure. We present TRACE, a deployable tree-relational enhancement framework for oncology LLMs. TRACE separates expensive offline structure learning from lightweight online inference: oncology concepts and relations are organized into an updatable tree-relational structure, refined using LM-loss-derived evidence, and retrieved at inference time as compact prompt evidence. This design supports task-adaptive e

arXiv cs.CL·just now

Papers Hot

Lookahead-R: Budget-Aware Tool Retrieval via Execution-Centric Planning

arXiv:2609.35811v1 Announce Type: new Abstract: Tool retrieval is a critical bottleneck for LLM-based agents operating over large, heterogeneous API ecosystems. Existing approaches face an inherent trade-off: semantic retrievers are fast but suffer from the semantic-functional gap, while execution-based validation improves precision at the cost of prohibitive latency. We propose Lookahead-R, a planning-based framework that reformulates tool retrieval as a resource-constrained sequential decision-making problem. At its core, Lookahead-R introduces a lightweight execution-aware surrogate world m

arXiv cs.CL·just now

Papers Hot

Quoting Anthropic Frontier Red Team

<blockquote cite="https://www.anthropic.com/research/glm-5-3-and-the-spread-of-advanced-cyber-capabilities"><p>We evaluate several models on 100 tasks from the [internal Binary Exploitation benchmark] (selected at random), and find that GLM-5.3 develops full control flow hijacks in 4% of the trials; Claude Mythos Preview did so in 6%. Although GLM-5.3 performs below Claude Mythos Preview here, a meaningful threshold has clearly been crossed: earlier models, like Claude Opus 4.6 and GLM-5.2, do not succeed in any of them.</p></blockquote> <p class="cite">— <a href="https://www.anthropic.c

Simon Willison·just now

Trending tags