AI news archive.
10,659 articles filed under Research, newest first, from the outlets listed on the sources page.
- LessWrongresearchHow I discovered an Exoplanet & the science apocalypse
TL;DR: I discovered (a few) exoplanet candidates, I walk through how. Then I talk about the near future of science given the ease of and growing capabilities of agentic systems. These are largely independent sections, yo…
- LessWrongresearchWhich AI economics and governance research most needs independent expert evaluation? (help The Unjournal prioritize it)
The Unjournal commissions public expert evaluations and ratings of research (and “ pivotal questions ”) with potential for global impact. We’re currently making a push to consider AI economics and governance research. [1…
- LessWrongresearchA brief(ish) introduction to LM psychology
Why LM Psychology? One of the great ironies of modern language models is that we create them, we know exactly what computations constitute them, and yet we do not really understand them. More precisely, we do not underst…
- LessWrongresearchACS Infra: free access to large base models for LLM psychology research
TL;DR: We're opening a platform serving large open base models to researchers and tinkerers working on LLM psychology and adjacent areas. It's free and comes with logprobs, activation harvesting and steering, a browser w…
- LessWrongresearchAgent Action Steering
Background The Linear Representation Hypothesis [1] has allowed for many remarkable steering experiments. Anthropic famously demonstrated Golden Gate Claude, where they first extracted a feature associated with the Golde…
- Hugging Face BlogresearchFairStress: A deeper evaluation of fairness in LLM decision-making
Open-source model releases, tooling, and community updates.
- Microsoft ResearchresearchCalled to serve: Tech, research, and positive impact
Lab Director Chris White has worked on research challenges with real-world implications—from new approaches to wartime data analysis to tools for combating human trafficking. He talks to program manager Weishung Liu abou…
- Google ResearchresearchAsk a Scientist: How can AI help doctors spend more time on collaborative care?
AMIE, an AI system people can chat with before doctor’s appointments, securely gathers patient information, and saves doctors time.
- Guardian AIresearchCould this be a Deep Blue moment for the cryptic crossword?
A computer program has finally outdone humans at solving cryptic crosswords. Plus, more from around the puzzleverse • Don’t get Cluesletter, our weekly puzzles newsletter, delivered to your inbox? Sign up here When the I…
- Hugging Face BlogresearchALTK-Evolve: How learned memory tops the τ²-bench leaderboard on customer service tasks without a frontier model
Open-source model releases, tooling, and community updates.
- arXiv cs.AIresearchRethinking User Encoders: Routing Diffusion States for Scenario-Adaptive User Representation
arXiv:2610.22400v1 Announce Type: new Abstract: Existing large language model (LLM)-based user encoders serialize heterogeneous behavioral logs and compress them into static representations through autoregressive (AR) pr…
- arXiv cs.AIresearchFrom Events to Reasoning: Hierarchical Rule Composition over Explicit States
arXiv:2610.22403v1 Announce Type: new Abstract: What a reasoning system emits is a conclusion; what it owes is a justification. Producing one requires every operation to be admissible on the facts actually available, the…
- arXiv cs.AIresearchFrom Natural Language Intent to Executable Control: Hierarchical Feedback-Guided LLM Planning for Multi-component Cyber-Physical Systems
arXiv:2610.22441v1 Announce Type: new Abstract: Large language models (LLMs) provide a convenient interface for translating natural language commands into task plans for cyber-physical systems (CPSs). However, two gaps h…
- arXiv cs.AIresearchNull Controls Are Necessary but Not Sufficient: Evaluating Acceptance Guards for Scientific Discovery and Interpretability
arXiv:2610.22445v1 Announce Type: new Abstract: Automated discovery systems propose scientific explanations and test which to accept. Does passing a test establish the intended claim? We develop four executable operation…
- arXiv cs.AIresearchLearnable Splines for Unstructured Neural Operators
arXiv:2610.22446v1 Announce Type: new Abstract: Neural operators approximate solution operators of partial differential equations at a fraction of the cost of numerical solvers. Efficient grid-based architectures such as…
- arXiv cs.AIresearchFunctional Welfare for AI Safety
arXiv:2610.22460v1 Announce Type: new Abstract: AI welfare is generally treated purely as an ethical issue rather than also as a safety issue. We argue this is a mistake. Whatever their moral status, models exhibit welfa…
- arXiv cs.AIresearchAre Large Reasoning Models Good Everyday Reasoners? A Comparison with Non-Reasoning Models on Logical Reasoning Tasks
arXiv:2610.22538v1 Announce Type: new Abstract: Large reasoning models (LRMs) that leverage test-time computation achieve strong performance on mathematical and scientific benchmarks and are increasingly deployed in real…
- arXiv cs.AIresearchRepairing LLM-Generated Specifications with Deterministic Diagnosis
arXiv:2610.22568v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used as formalizers: given a reasoning problem expressed in natural language, they produce a formal specification that a symbo…
- arXiv cs.AIresearchFlexUMM: Flexible Representation Learning for Unified Multimodal Models
arXiv:2610.22682v1 Announce Type: new Abstract: Unified multimodal models (UMMs) can integrate understanding and generation within a single backbone. However, it is commonly known that these two capabilities can cause co…
- arXiv cs.AIresearchRepair, Retry, and the Cost of Hindsight: Verifier Feedback in Formal Theorem Proving
arXiv:2610.22698v1 Announce Type: new Abstract: Verifier-guided self-repair conditions a model on feedback from failed attempts before it tries again, without weight updates. Yet two findings in prior work are in tension…
- arXiv cs.AIresearchBrain-Aligned Multimodal LLMs for Social and Emotional Understanding of Cartoon Movies
arXiv:2610.22706v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) offer scalable annotations of social and affective content, but their temporal agreement with human judgments and neural predictive…
- arXiv cs.AIresearchGlobeBench: Evaluating Text-Based World Model Capabilities for Scalable Environment Simulations
arXiv:2610.22708v1 Announce Type: new Abstract: Text-based world models have recently shown potential to simulate complex RL environment state transitions for a diverse set of use cases. However, no standardized benchmar…
- arXiv cs.AIresearchLEMON: Equivariant Learning over Attention Maps for Zero-Shot Misbehavior Monitoring on New LLMs
arXiv:2610.22723v1 Announce Type: new Abstract: Large language models exhibit misbehaviors that hinder deployment in high-stakes settings. One approach to monitor such failures is to use an external LLM as a monitor, but…
- arXiv cs.AIresearchGraph Serializations for Reasoning LLMs: A Study Across Knowledge Extraction and Structural Reasoning
arXiv:2610.22734v1 Announce Type: new Abstract: The way a knowledge graph is serialized as text for inclusion into LLM context can substantially affect downstream LLM performance, with prior work reporting tens of percen…
- arXiv cs.AIresearchBetween Spoilers and Guesswork: Avoiding Over-Specification in Coding Benchmarks
arXiv:2610.22760v1 Announce Type: new Abstract: Benchmarks drive AI progress, but are hampered by task under-specification and over-specification. Task under-specification causes guesswork, where solutions have to make t…
- arXiv cs.AIresearchStoBasket: Joint Upsell and Cross-Sell Optimization for Contribution Margin
arXiv:2610.22768v1 Announce Type: new Abstract: Retail recommenders rank relevance, but retailers earn contribution margin: an upsell earns the margin difference over the item it replaces, whereas a cross-sell earns its…
- arXiv cs.AIresearchCompression Precedes, Content Decides: Emergent Misalignment in Reward Models
arXiv:2610.22805v1 Announce Type: new Abstract: Emergent Misalignment - the out of domain generalization of narrow harmful fine-tuning first shown by Betley et al. [2025] has been widely studied in language models but no…
- arXiv cs.AIresearchWorld Action Critic (WAC) Model: Joint Foresight and Criticism for Policy Learning
arXiv:2610.22825v1 Announce Type: new Abstract: World models have shown considerable promise in sequential decision-making by anticipating the consequences of actions and providing predictive foresight for policy learnin…
- arXiv cs.AIresearchEvo-B&B: Behavior-Aware LLM-Guided Joint Evolution of Branching and Node Selection Policies for MILP
arXiv:2610.22861v1 Announce Type: new Abstract: In branch-and-bound for Mixed-Integer Linear Programming (MILP), branching and node selection are two critical and tightly coupled decisions, yet most existing learning-bas…
- arXiv cs.AIresearchShadowFPT: Backdooring Federated Prompt Tuning via Shadow Triggers
arXiv:2610.22871v1 Announce Type: new Abstract: Federated Prompt Tuning (FPT) adapts large vision--language models by freezing the pretrained backbone and optimizing only lightweight prompt parameters across clients. Alt…
- arXiv cs.AIresearchLook Back, Correct Forward: Error Feedback Calibration for Time Series Forecasting
arXiv:2610.22872v1 Announce Type: new Abstract: Time series forecasting models are increasingly deployed in continuously evolving environments. After a forecast is issued, future observations gradually arrive and reveal…
- arXiv cs.AIresearchToPA: Block-wise Toeplitz Adaptation for Expressive and Efficient Fine-Tuning
arXiv:2610.22883v2 Announce Type: replace Abstract: Parameter-Efficient Fine-Tuning (PEFT) has emerged as a prevalent strategy for adapting large pre-trained models. Among PEFT techniques, reparameterization-based method…
- arXiv cs.AIresearchSep-Latent: Separator Tokens as Natural Compression Anchors for Implicit Reasoning
arXiv:2610.22924v1 Announce Type: new Abstract: Large Language Models (LLMs) have demonstrated remarkable success in complex reasoning through explicit Chain-of-Thought (CoT), but the associated computational overhead an…
- arXiv cs.AIresearchMultiple Turns, Short Horizons: Measuring Effective-Horizon Compression in Jailbreaks
arXiv:2610.22928v1 Announce Type: new Abstract: Multi-turn jailbreaks use feedback from a victim large language model to adapt their queries over several turns. However, once an effective trajectory has been found, it is…
- arXiv cs.AIresearchDiffusionRVGE: Reinforcement Learning via Regression-Based Value Gradient Estimation
arXiv:2610.22973v1 Announce Type: new Abstract: Reinforcement learning improves diffusion models using rewards on generated images, but repeated denoising and gradient estimation make training expensive. We introduce \me…
- arXiv cs.AIresearchGOLD: Geometric Optimized Latent Diffusion for Structure-Aware RNA Inverse Folding
arXiv:2610.22992v1 Announce Type: new Abstract: Designing RNA sequences that fold into specific 3D structures is a fundamental challenge in therapeutics. Current RNA inverse folding methods typically condition on 3D back…
- arXiv cs.AIresearchEfficient CPU-GPU collaborative MoE inference via Adaptive Expert Assignment
arXiv:2610.23006v1 Announce Type: new Abstract: Mixture-of-Experts (MoE) models reduce inference computation through sparse expert activation, but their large expert memory footprint often exceeds GPU capacity, making ex…
- arXiv cs.AIresearchCausal Value Attribution of Marketing Labels in LLM-Generated Ads: A Deconfounder Approach
arXiv:2610.23025v1 Announce Type: new Abstract: As AI-generated content becomes commoditized, economic value increasingly shifts from final artifacts to the upstream expertise used to specify inputs that steer LLM genera…
- arXiv cs.AIresearchASE: Attribution-Guided Semantic Evolution for Time Series Forecasting
arXiv:2610.23027v1 Announce Type: new Abstract: External text can supply predictive information absent from numerical histories, but its value depends on how it is represented, combined and deployed. We present Attributi…
- arXiv cs.AIresearchWhere Does the Performance Go? Understanding and Recovering Performance Regressions in C-to-Rust Translation
arXiv:2610.23044v1 Announce Type: new Abstract: Rust is increasingly adopted as a memory-safe successor to C, and transpilers such as \crust{} can migrate entire C projects while preserving their behavior. Preserving beh…
- arXiv cs.AIresearchRethinking GRPO for Large Reasoning Model Safety Alignment
arXiv:2610.23085v1 Announce Type: new Abstract: Large reasoning models (LRMs) exhibit strong reasoning capabilities but remain vulnerable to unsafe outputs. While Group Relative Policy Optimization (GRPO) is widely used…
- arXiv cs.AIresearchLexPilot: Benchmarking the Proactive Interaction Ability of Legal LLMs with Laypeople in Chinese Civil Case Consultation
arXiv:2610.23141v1 Announce Type: new Abstract: Large Language Models (LLMs) have greatly assisted legal professionals. However, our empirical studies reveal that, when faced with underspecified consultations from non-ex…
- arXiv cs.AIresearchCIIR - Class-Indexed Interface Representation Learning
arXiv:2610.23151v1 Announce Type: new Abstract: Multimodal learning commonly assumes paired or synchronized observations, yet independently collected datasets rarely provide such correspondence. We introduce CIIR, a modu…
- arXiv cs.AIresearchAlgorithm Modelization: Transforming Optimization Algorithms into Evolvable Intelligence
arXiv:2610.23161v2 Announce Type: replace Abstract: Can algorithms be learned and evolved as models, rather than repeatedly redesigned as programs? We explore this question by introducing Algorithm Modelization, a new pa…
- arXiv cs.AIresearchLongForge: Measuring and Improving Long-Context Instruction Data via Evidence-Assertion Reasoning Graphs
arXiv:2610.23167v1 Announce Type: new Abstract: Existing quality control for long-context instruction-tuning data is a one-shot judgment inside the generation pipeline that leaves only a scalar, revealing neither which d…
- arXiv cs.AIresearchFuzzInsight: Navigating the Efficiency-Effectiveness Trade-off in Coverage-Guided DNN Fuzzing
arXiv:2610.23195v1 Announce Type: new Abstract: Collecting and labeling diverse test datasets for evaluating Deep Neural Networks (DNNs) is costly and time-consuming. This has motivated coverage-guided fuzzing techniques…
- arXiv cs.AIresearchNot All Test-Time Compute Is Evidence: Model-Specific Bias in LLM Reasoning
arXiv:2610.23213v1 Announce Type: new Abstract: Test-time scaling methods implicitly assume that additional computation from the same model provides independent evidence. We show that this assumption fails within a singl…
- arXiv cs.AIresearchCharacterising and Analysing Retrieval-Augmented Generation Techniques
arXiv:2610.23226v1 Announce Type: new Abstract: The advent of Large Language Models (LLMs) across many application domains has increased the need for Retrieval-Augmented Generation (RAG) to reduce hallucinations and impr…
- arXiv cs.AIresearchReasoning Models Can Control Their Chains of Thought When They Tell Themselves To
arXiv:2610.23257v1 Announce Type: new Abstract: Chain-of-thought (CoT) controllability, the ability of reasoning models to control properties of their CoT, is consequential for both their usefulness and reliable oversigh…
- arXiv cs.AIresearchCoTA++: Understanding the Repeat Curse in dMLLMs from an Information Flow Perspective
arXiv:2610.23290v1 Announce Type: new Abstract: Diffusion-based multimodal large language models (dMLLMs) decode by iterative denoising with bidirectional attention, which precludes the standard autoregressive key--value…