AI news archive.
19,861 articles, newest first, from the outlets listed on the sources page.
- arXiv cs.AIresearchCausal Identification from Counterfactual Data: Completeness and Bounding Results
arXiv:2602.23541v3 Announce Type: replace Abstract: Previous work establishing completeness results for counterfactual identification has been circumscribed to the setting where the input data belongs to observational or…
- arXiv cs.AIresearchDon't Ask: Understanding What Numeric Self-Reports Measure in Language Models
arXiv:2603.18893v3 Announce Type: replace Abstract: Language models are often asked to rate their internal states with a number, but it is unclear how reliable this measure is. We train probes for four affective concepts…
- arXiv cs.AIresearchScoringBench: A Benchmark for Evaluating Tabular Foundation Models with Proper Scoring Rules
arXiv:2603.29928v4 Announce Type: replace Abstract: Tabular foundation models such as TabPFN, TabICL, ExaOneTabular, and Nori already produce full predictive distributions, yet prevailing regression benchmarks evaluate t…
- arXiv cs.AIagentsLogarithmic Scores, Power-Law Discoveries: Disentangling Measurement from Coverage in Agent-Based Evaluation
arXiv:2604.00477v2 Announce Type: replace Abstract: LLM-based agent judges are an emerging approach to evaluating conversational AI, yet a fundamental uncertainty remains: can we trust their assessments, and if so, how m…
- arXiv cs.AIresearchMitigating Distribution Sharpening in Math RLVR via Distribution-Aligned Hint Synthesis and Backward Hint Annealing
arXiv:2604.07747v2 Announce Type: replace Abstract: In reinforcement learning with verifiable rewards (RLVR), challenging math questions whose sampled groups remain uniformly incorrect yield no informative update, lettin…
- arXiv cs.AIagentsAgentic Architect: An Agentic AI Framework for Architecture Design Exploration and Optimization
arXiv:2604.25083v2 Announce Type: replace Abstract: Computer Architecture research has traditionally required the exploration of vast, highly complex design spaces through manual human effort. Large Language Models (LLMs…
- arXiv cs.AIresearchOracleProto: A Reproducible Framework for Benchmarking LLM Forecasting via Knowledge Cutoffs and Temporal Masking
arXiv:2605.03762v2 Announce Type: replace Abstract: Forecasting is a composite capability encompassing information gathering, evidence integration, situational assessment, and decision-making. Large language models (LLMs…
- arXiv cs.AIagentsVibeServe: Can AI Agents Build Bespoke LLM Serving Systems?
arXiv:2605.06068v2 Announce Type: replace Abstract: For years, we have built LLM serving systems like any other critical infrastructure, with a single general-purpose stack hand-tuned over many engineer-years to support…
- arXiv cs.AIagentsTools as Continuous Flow for Evolving Agentic Reasoning
arXiv:2605.07339v3 Announce Type: replace Abstract: Large Language Models (LLMs) have demonstrated remarkable capabilities in orchestrating tools for reasoning tasks. However, existing methods rely on a step-wise paradig…
- arXiv cs.AIagentsMemQ: Integrating Q-Learning into Self-Evolving Memory Agents over Provenance DAGs
arXiv:2605.08374v4 Announce Type: replace Abstract: Episodic memory allows LLM agents to accumulate and retrieve experience, but current methods treat each memory independently, i.e., evaluating retrieval quality in isol…
- arXiv cs.AIagentsRewardHarness: Self-Evolving Agentic Post-Training
arXiv:2605.08703v2 Announce Type: replace Abstract: Aligning generative models with human preferences remains a central challenge. While RLHF is widely adopted, it relies on large-scale preference data. This limitation i…
- arXiv cs.AIresearchData-driven Circuit Discovery for Interpretability of Language Models
arXiv:2605.09129v2 Announce Type: replace Abstract: Circuit study aims to explain how language models (LMs) implement a task by localizing and interpreting a circuit: a computational subgraph responsible for a specific m…
- arXiv cs.AIagentsVerifiable Process Rewards for Agentic Reasoning
arXiv:2605.10325v3 Announce Type: replace Abstract: Reinforcement learning from verifiable rewards (RLVR) has improved the reasoning capabilities of large language models (LLMs), yet existing approaches predominantly rel…
- arXiv cs.AIagentsArgumentation-Based Person-Tailored Storytelling for Older Adults: A Reflective Hybrid AI Architecture
arXiv:2605.10531v2 Announce Type: replace Abstract: This work investigates knowledge-driven, large language model (LLM)-based storytelling for older adults. We present a reflective storytelling agent integrating knowledg…
- arXiv cs.AIagentsEnergy per Successful Goal: Goal-Level Energy Accounting for Agentic AI Systems
arXiv:2605.22883v2 Announce Type: replace Abstract: Current AI energy benchmarks measure consumption per model invocation. For agentic systems, where a single user goal may trigger multistep orchestration, tool calls, re…
- arXiv cs.AIagentsTADDLE: A Tool-Augmented Agent for Detecting Deficient LLM-Generated Peer Reviews
arXiv:2605.26911v2 Announce Type: replace Abstract: LLM-generated peer reviews are increasingly common at major venues, yet their deficiencies are hard to detect because they are uniformly fluent and well-structured. Exi…
- arXiv cs.AIresearchConMoE: MoE Compression as Expert Selection and Functional Assignment
arXiv:2605.29350v2 Announce Type: replace Abstract: Sparse Mixture-of-Experts (MoE) models scale model capacity through sparse activation, but storing their full parameters remains costly in GPU memory. Existing expert c…
- arXiv cs.AIresearchConformal Certification of Reasoning Trace Prefixes
arXiv:2605.30085v2 Announce Type: replace Abstract: Language model reasoning traces are rarely all-or-nothing; they frequently contain valid intermediate steps before a critical error occurs. Existing uncertainty quantif…
- arXiv cs.AIagentsCoMIC: Collaborative Memory and Insights Circulation for Long-Horizon LLM Agents in Web Cloud-Edge Systems
arXiv:2606.00756v2 Announce Type: replace Abstract: LLM-based Web agents are increasingly deployed on edge servers to carry out long-horizon tasks on behalf of users with low latency. However, the lightweight models that…
- arXiv cs.AIresearchRevisiting Ripple Effects in Knowledge Editing through Pressure-Aware Joint Neighborhood Optimization
arXiv:2606.01610v2 Announce Type: replace Abstract: Single-edit updates in large language models can trigger ripple effects across local knowledge neighborhoods: desirable propagation to related facts and unintended pert…
- arXiv cs.AIresearchTrajectory-Refined Distillation
arXiv:2606.08432v2 Announce Type: replace Abstract: On-policy distillation (OPD) has become a central post-training tool for large language models (LLMs), providing dense per-token teacher supervision along the student's…
- arXiv cs.AIresearchLATTEArena: An Evaluation Framework for LLM-powered Tabular Feature Engineering (Extended Version)
arXiv:2606.09004v3 Announce Type: replace Abstract: Feature engineering remains a cornerstone of tabular data analysis, and Large Language Models (LLMs) have emerged as a promising paradigm for its automation, giving ris…
- arXiv cs.AIagentsBusiness World Model
arXiv:2606.10044v3 Announce Type: replace Abstract: World model has emerged as a powerful paradigm in artificial intelligence, enabling agents to represent their environments, predict future states, and evaluate possible…
- arXiv cs.AIresearchIncumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems
arXiv:2606.17443v3 Announce Type: replace Abstract: Large language models (LLMs) are becoming a major way for consumers to find products, but we do not yet understand how brands compete in this new channel. We study bran…
- arXiv cs.AIresearchFrom Brewing to Resolution: Tracing the Internal Lifecycle of Code Reasoning in LLMs
arXiv:2606.17648v3 Announce Type: replace Abstract: Standard accuracy metrics cannot explain why LLMs handle variable tracking but fail on semantically equivalent loops. We study an internal lifecycle of code reasoning i…
- arXiv cs.AIagentsPseudoBench: Measuring How Agentic Auto-Research Fuels Pseudoscience
arXiv:2606.18060v2 Announce Type: replace Abstract: As Large Language Model based agents enter autonomous scientific research, their ability to resist pseudoscience becomes increasingly important. Otherwise, such systems…
- arXiv cs.AIagentsDecoupling Search from Reasoning: A Vendor-Agnostic Grounding Architecture for LLM Agents
arXiv:2606.18947v2 Announce Type: replace Abstract: Production LLM agents increasingly depend on real-time search, yet native search grounding bundles retrieval policy, provider choice, evidence injection, cost, latency,…
- arXiv cs.AIagentsReward as An Agent for Embodied World Models
arXiv:2606.19990v3 Announce Type: replace Abstract: While RL has become a promising tool for refining world models, existing methods largely rely on conservative rollouts near the training distribution, limiting explorat…
- arXiv cs.AIagentsWhen Agents Commit Too Soon: Diagnosing Premature Commitment in LLM Agents
arXiv:2606.22936v2 Announce Type: replace Abstract: Tool-using LLM agents make early choices about what to search for, which evidence to trust, and what to do next. A wrong early choice can steer every later tool call, s…
- arXiv cs.AIagentsPlans Fade Fast: Why Context Management Is Load-Bearing for LLM Agents
arXiv:2606.22953v2 Announce Type: replace Abstract: Context managers summarize or evict old messages so agents can operate beyond a finite window. This creates a reliability problem: removing history that still shapes th…
- arXiv cs.AIagentsLitmus: Zero-Label, Code-Driven Metric Specification for Evaluating AI Systems
arXiv:2606.23403v2 Announce Type: replace Abstract: As agentic LLM systems move from prototypes to deployment, evaluating them has become more important and more difficult. Evaluation goals are often left implicit. Witho…
- arXiv cs.AIresearchBeyond Trajectory Imitation: Strategy-Guided Policy Optimization for LLM Reasoning
arXiv:2606.24064v3 Announce Type: replace Abstract: Distilling reasoning capabilities from strong to weak language models typically involves imitating specific solution trajectories, effectively transferring what to answ…
- arXiv cs.AIagentsUnderstanding Rollout Error in Graph World Models
arXiv:2606.27780v3 Announce Type: replace Abstract: World models are increasingly used for planning by predicting future states under candidate actions. Many planning environments, however, are naturally graph-structured…
- arXiv cs.AIagentsMedEvoEval: Evaluating Continual Evolution of Doctor Agents through Simulated Clinical Episodes
arXiv:2606.28900v3 Announce Type: replace Abstract: Doctor agents are moving beyond single-turn answer generation toward evolving clinical decision systems that acquire evidence within episodes and reuse experience acros…
- arXiv cs.AIresearchWhat a Pooled Leaderboard Does Not Say: Auditing the Scope and Provenance of Method Comparisons in Microservice RCA Benchmarks
arXiv:2606.29159v2 Announce Type: replace Abstract: Offline benchmarks for microservice root cause analysis (RCA) rank methods by a score pooled over several applications, and a pooled lead leaves two things unstated: on…
- arXiv cs.AIresearchProcess Advantage Signal Shaping: Advantage Construction for Process-Supervised Reinforcement Learning in LLM Reasoners
arXiv:2606.29296v2 Announce Type: replace Abstract: Dense process supervision supplies local feedback but leaves open how that feedback should become a policy advantage. We introduce PASS (Process Advantage Signal Shapin…
- arXiv cs.AIagentsWhen LLMs Develop Languages: Symbolic Communication for Efficient Multi-Agent Reasoning
arXiv:2606.29354v2 Announce Type: replace Abstract: Chain-of-Thought (CoT) improves large language models (LLMs) on difficult reasoning tasks, but it often incurs long natural-language rationales that are poorly aligned…
- arXiv cs.AIagentsLong-Horizon-Terminal-Bench: Testing the Limits of Agents on Long-Horizon Terminal Tasks with Dense Reward-Based Grading
arXiv:2607.08964v3 Announce Type: replace Abstract: AI agents have become capable of autonomously completing short, well-specified tasks. However, existing terminal benchmarks largely focus on simple problems that finish…
- arXiv cs.AIresearchWhat We Talk About When We Talk About LLM Planning: Evidence for Two Distinct Planning Abilities
arXiv:2607.11197v2 Announce Type: replace Abstract: When LLMs exhibit uneven performance across planning tasks, these gaps are often attributed to task difficulty. We argue that this explanation is incomplete, as task-le…
- arXiv cs.AIagentsTracing Agentic Failure from the Flow of Success
arXiv:2607.12747v2 Announce Type: replace Abstract: Failure attribution for LLM-based agentic systems, i.e., identifying which steps in a failure trajectory caused the task to fail, is critical for debugging and improvin…
- arXiv cs.AIagentsPRO-LONG: Programmatic Memory Enables Long-Horizon Reasoning
arXiv:2607.20064v3 Announce Type: replace Abstract: Long-horizon tasks require sustained perception, reasoning, and exploration, and are a persistent challenge for large language model (LLM) agents. This gap is reflected…
- arXiv cs.AIagentsAgent-UCT: Upper Confidence Bounds Applied to Trees for Cost-Aware Agentic Workflow Optimization
arXiv:2607.24162v3 Announce Type: replace Abstract: Workflow search pays for complete quality observations, whose execution cost changes as reusable prefixes accumulate. AgentUCT uses an economic model of the remaining e…
- arXiv cs.AIresearchInstruction-Tuned Language Models Cannot Sample from Distributions They Can Describe
arXiv:2607.25292v3 Announce Type: replace Abstract: Silicon sampling uses language models as proxies for human survey respondents, treating each model call as an independent draw from the persona's response distribution.…
- arXiv cs.AIagentsMIND: Lightweight and Effective Memory Injection Defense for LLM Agents via Intent-Aware Information Bottleneck
arXiv:2607.28103v2 Announce Type: replace Abstract: Memory-augmented LLM-based agents are vulnerable to memory injection attacks: Agents may retrieve poisoned memory from attackers, which diverts their behavior from init…
- arXiv cs.AIresearchLEMUR: Learning to Align with Multi-Objective Reinforcement Learning from Preference Feedback
arXiv:2607.29559v2 Announce Type: replace Abstract: Reinforcement Learning (RL) systems are typically trained using a single, well-specified scalar reward function. However, real-world decision-making tasks often involve…
- arXiv cs.AIresearchToward Fine-Grained Forgetting:Attribute Unlearning for Multimodal Large Language Models
arXiv:2608.01008v2 Announce Type: replace Abstract: Multimodal large language models (MLLMs) can memorize and disclose sensitive information, motivating machine unlearning to remove designated knowledge while preserving…
- arXiv cs.AIresearchLaCache: Robust Semantic Caching for LLM Serving
arXiv:2608.01718v2 Announce Type: replace Abstract: Semantic caching, reusing responses to answer semantically similar queries, has seen growing adoption in LLM serving, offering faster responses and reduced costs. Yet e…
- arXiv cs.AIagentsCockpitHAT: Dependency-Graph-Driven Hierarchical Attribution for Embodied Multi-Agent Cockpits
arXiv:2608.01805v2 Announce Type: replace Abstract: LLM multi-agent systems suffer from Correctness Collapse, where high task-level accuracy conceals severe process-level failures. This is especially hazardous in safety-…
- arXiv cs.AIagentsSearchMaster: Grounded and Regulated Self-Play for Search Agents
arXiv:2608.01822v2 Announce Type: replace Abstract: Training LLM-based search agents requires high-quality search data: tasks that demand genuine multi-hop retrieval and trajectories that use search tools effectively. Ex…
- arXiv cs.AIresearchSurrogate Substitution Preserves PHI Detectability: A Multi-Detector Equivalence Study
arXiv:2608.03172v5 Announce Type: replace Abstract: Structure-preserving de-identification replaces each detected identifier with a realistic same-type surrogate ("Anna S." -> "Maria S.") rather than a tag such as [NAME]…