Skip to content
AI NEWSSee every step of AI
Bookmarks
THE JOURNAL
AI NEWS JOURNAL
AI, IN PERSPECTIVE

All AI updates

Explore the complete news stream by source, topic and date.

Newest first

arXiv cs.CL

SLICE-Mem: Salience-Gated Lightweight Information Curation for Efficient LLM Agent Memory

arXiv:2610.33015v1 Announce Type: new Abstract: Long-term memory enables large language model (LLM) agents to maintain personalized and temporally coherent interactions, but repeated LLM inference for memory admission, extraction, and organization introduces substantial cost and latency. We present SLICE-Mem, a lightweight memory framework that combines salience-guided admission and predicate-centered information extraction. A compact classifier identifies user turns worth retaining, and a semantic-dependency-based extractor converts admitted turns into concise memory entries. This online pipeline requires no generative LLM calls, while cross-entry reconciliation is deferred to an offline consolidation stage. We evaluate SLICE-Mem on the weekly subset of Memora and LongMemEval-S using 8B a

Timeline and related coverage
arXiv cs.CL

AdaptTok-Indic: Script-Aware Adaptive Tokenization for Indic Languages

arXiv:2610.33017v1 Announce Type: new Abstract: Multilingual tokenizers trained on English-dominated corpora often over-segment Indic languages, resulting in longer token sequences and increased tokenization disparity across scripts. We present AdaptTok-Indic, an Indic-specialized extension of adaptive tokenization that combines Unicode-normalized preprocessing with explicit Indic conjunct handling, script-aware routing, and learned byte-level boundary prediction jointly trained with a small Transformer language model. Evaluated on Bengali and Hindi, with additional evaluation on Gujarati, Tamil, and Telugu, AdaptTok-Indic achieves lower token fertility than SentencePiece BPE, an Indic-oriented tokenizer baseline, and an independently implemented MAGNET-style baseline. Across five recorded

Timeline and related coverage
arXiv cs.AI

Async-RBench: Benchmarking Asynchronous Task Execution in LLM Agents

arXiv:2610.32429v1 Announce Type: new Abstract: Large language model (LLM) agents increasingly execute tasks asynchronously: a main agent continues working while its subagents run, and the task state may change before their results arrive. The main agent must decide which work to update or preserve and which checks to repeat, while avoiding prohibited changes. Final task success alone does not reveal whether these results were handled correctly, and natural asynchronous arrivals are hard to reproduce. We introduce Async-RBench, a benchmark for asynchronous task execution in LLM agents, with 200 executable tasks covering eight scenarios. A scenario controller regulates result delivery using predefined task-state conditions, while an Event Response Contract (ERC) specifies what each response

Timeline and related coverage
arXiv cs.CL

Recursive Semantic Divergence for LLM Agent Consistency

arXiv:2610.33012v1 Announce Type: new Abstract: Large Language Model (LLM) agents with tool use exhibit inconsistent behavior across independent runs from identical states, calling different tools, producing contradictory outputs, or pursuing divergent strategies. This variability compounds over time and undermines deployment reliability. Existing evaluation metrics primarily measure task correctness via completion-based scores and do not capture consistency in agent behavior across executions. Separately, agent behavior is analyzed either at the token level using probability distributions or at the single-response level using semantic clustering, but neither captures how inconsistency propagates across future turns of a trajectory. We introduce Recursive Semantic Divergence (RSD), an unsu

Timeline and related coverage
arXiv cs.CL

Two Uncertainties Are Not One: Disagreement versus Decision-Risk in Cheap Structured Content Moderation

arXiv:2610.33258v1 Announce Type: new Abstract: Content moderation compresses a graded, contested human judgment into a binary act (leave up / take down) over billions of items, at a scale where running a frontier LLM on every post is uneconomical. A new class of frozen "System One" models returns typed, calibrated decisions instead of text at ~USD 0.000025 per call and ~100 ms. We run the first independent audit of one such model on 142,658 human-labeled comments, and benchmark it against 14 frontier reasoning models (the GPT-5.x, Claude, Gemini 3, and Grok families) on a shared probe set. Two findings stand out. First, the cheap model is accuracy-competitive: its zero-shot classification AUROC (0.83) is not statistically separable (paired bootstrap, n=56; a failure to reject parity, not

Timeline and related coverage
arXiv cs.CL

Knowledge-Guided LLM for Intent-Driven Service Orchestration in Integrated Terrestrial and Non-Terrestrial 6G Networks

arXiv:2610.33007v1 Announce Type: new Abstract: Natural-language service intents in integrated terrestrial and non-terrestrial (TN/NTN) 6G networks can be incomplete, ambiguous, or inconsistent, making unconstrained LLM generation challenging for reliable network-facing orchestration. This paper proposes a knowledge-guided LLM framework that combines grammar-constrained semantic parsing with a knowledge-graph (KG)-driven clarification loop to produce validated, orchestration-ready service profiles across four representative service classes. On a 200-sample intent dataset, the framework achieves 89% classification accuracy and 95% policy validity with an average of 0.66 clarification turns per request. Compared with a Pure-LLM baseline, the proposed framework improves policy validity and co

Timeline and related coverage
arXiv cs.CL

Position, Role or Label? A Controlled Study of Instruction Conflicts in LLM Agents

arXiv:2610.33201v1 Announce Type: new Abstract: LLM agents take instructions from the operator, repository configuration, user, tool results and saved memory, which often conflict. Instruction-hierarchy benchmarks ask whether the higher-ranked source wins, but a source sets position, role and label at once. First, we build WhoWins, 1,080 code-scored scenarios in five task types, each with up to five mutually exclusive instructions, and seven controlled experiments that vary only how instructions are delivered. Second, we study 14 open-weight models (0.6B to 122B, thinking off and on) over 1,887,356 scored replies, checking main findings on held-out scenarios. Inside one message the first of two conflicting lines wins 72.42 to 94.66%, and across messages it keeps 22.95 to 62.65%. A policy s

Timeline and related coverage
arXiv cs.CL

EviGround-CT: Sentence-to-Volume Grounding for Verifying LLM-Generated Chest CT Reports

arXiv:2610.33038v1 Announce Type: new Abstract: Chest computed tomography (CT) reports generated by large language models (LLMs) can describe positive findings that lack localized evidence in the scan. We propose EviGround-CT to verify these findings after report generation. A deterministic extractor identifies positive finding sentences, and a 3D grounding model predicts an evidence mask for each sentence. Using the full sentence retains anatomical location, laterality, and descriptive modifiers in the grounding query. We evaluate report generation on CT-RATE, and grounding and verification on a held-out 100-case ReXGroundingCT subset. Using the available annotations, sentence-grounded verification raises evidence-supported precision (ESP) from 0.263 to 0.365 across 137 extracted in-scope

Timeline and related coverage
arXiv cs.CV

Nemotron 3.5 Bolt 74B-A9B 24GB: A Hybrid Vision-Language Model for Local AI

arXiv:2610.33039v1 Announce Type: new Abstract: We introduce Nemotron 3.5 Bolt 74B-A9B 24GB, a hybrid Mamba-Transformer vision-language model that optimizes speed and intelligence per GB of memory used for local agentic workloads. Derived from the Nemotron 3.5 Super VL 120B-A12B model family, Nemotron 3.5 Bolt 74B-A9B 24GB combines Star Elastic compression with 2-bit Quantization-Aware Distillation for memory-constrained deployment. The model is optimized for reasoning, agentic tool use, and web & terminal interactions. We also trained a LiLiCorr speculative drafter that is released alongside the model to reach our target inference speed. The resulting model achieves a higher accuracy than leading models with similar memory footprints and speed across many benchmarks for general agentic ca

新闻源配图 · arXiv cs.CV
Timeline and related coverage
arXiv cs.CL

The Social World Model Evaluation Gap

arXiv:2610.33014v1 Announce Type: new Abstract: A negotiation assistant can reach a good deal without accurately predicting the other person's response. We ask whether evaluations of social world models test that prediction directly. We audit 113 works published from 1999 to 2026. 9 primary evaluations measure a real person's response to an action selected by the system or experimenter. Only 2 also compare an explicit response forecast with that response. Their predictors use information available when the action is chosen, and the evaluated responses were excluded from fitting; both randomize the intervention. A separate full-text check of 25 language-model works finds no experiment meeting these conditions. The other evaluations test current-state inference, task success, or prediction f

Timeline and related coverage
arXiv cs.CL

Each Insufficient in Its Own Way: Calibrating Language Models Across Varying Evidence States

arXiv:2610.33237v1 Announce Type: new Abstract: How can a language model know whether it has enough evidence to answer? Language models tend to answer even when the evidence they have is insufficient. Deciding whether to answer or gather more evidence requires a calibrated estimate of how likely an answer is to be correct with the available evidence. However, most calibration work treats the input as fixed, without asking how this estimate should change with the evidence. We introduce \emph{evidence-state calibration}, which requires a model's confidence before answering to match its probability of answering correctly and to change accordingly whenever the evidence changes this probability. We propose \ours{} (\textbf{Suffi}ciency \textbf{C}onfidence \textbf{E}stimation), which fine-tunes

Timeline and related coverage
arXiv cs.AI

Beyond Gain: Measuring Skill Internalization for Agent Skill Retirement

arXiv:2610.32322v1 Announce Type: new Abstract: LLM agents retrieve skills from public hubs that hold up to about 100,000 entries and serve many models. As models improve, a hub must find the skills a given model has internalized, meaning it can do without them, and retire them for that model, yet internalization has not been measured with known reliability. Published rules that compare runs with and without a skill retire on the gain alone. The gain is near zero both for an internalized skill and when neither the model nor the skill delivers the capability, a state we call uncovered. We instead withhold the skill, score the model on a task synthesized from it, and trust a high unaided score only when another model gains from the skill, since nearly half of high scores come from tasks no m

Timeline and related coverage
arXiv cs.AI

Solvent: Long-Horizon Reasoning for Multi-Step Retrosynthesis

arXiv:2610.32308v1 Announce Type: new Abstract: Multi-step retrosynthesis requires recursively transforming a target molecule through successive reaction steps into purchasable building blocks, and recent work has begun to draw on large language model (LLM) reasoning to tackle the task. In its latest evolution, LLM reasoning has entered the long-horizon regime: models pursue objectives across interdependent steps, interact with environments, and adapt to feedback. This shift has markedly advanced LLM capabilities, as illustrated by breakthroughs in AI-driven mathematical research. At this frontier, we introduce Solvent, an 8B LLM that successfully extends long-horizon reasoning to multi-step retrosynthesis. Through a two-round post-training curriculum, Solvent learns to interleave iterativ

Timeline and related coverage
arXiv cs.CL

A Benchmark for Controllable Speaking-Style Captioning in Audio-Language Models

arXiv:2610.33036v1 Announce Type: new Abstract: Speaking-style captioning (SSC) aims to generate natural language descriptions of how speech is delivered, capturing paralinguistic attributes such as vocal timbre, prosody, and expressivity. Many downstream applications, including conversational AI agents, controllable speech generation, and large-scale audio annotation, require dimension-specific style captions that describe targeted aspects of speech (e.g., speaker traits, emotion, or delivery style), rather than a single undifferentiated description. However, existing work lacks a unified formulation for controllable speaking-style captioning. We address this gap by formulating SSC as an instruction-following audio-language task, where explicit instructions specify the speaking-style dime

Timeline and related coverage
arXiv cs.AI

DMAIC-Bench: From Self-Reflection to Self-Restraint for Agents in Multi-Stage Analytical Tasks

arXiv:2610.32305v1 Announce Type: new Abstract: Multi-stage analytical tasks require LLM agents to use intermediate evidence to decide whether to continue, redirect or stop. Self-reflection, in which an agent critiques its output, is widely studied, yet a critique does not show whether evidence changed the next action. We call that capability self-restraint. Existing agent benchmarks largely measure task completion or output quality and leave it untested. DMAIC-Bench evaluates it with 97 seeded tasks across 15 industrial cases in four sectors, built around Lean Six Sigma's explicit statistical prerequisites. Paired counterfactual variants require opposite actions at the same workflow position, distinguishing warranted restraint from indiscriminate stopping. We assess execution traces with

Timeline and related coverage
arXiv cs.CL

Entity-Aware Evaluation of OCR Systems for Historical Document Transcription

arXiv:2610.33004v1 Announce Type: new Abstract: Optical Character Recognition (OCR) is essential for digitizing historical archives, yet standard evaluation metrics such as Character Error Rate (CER) do not necessarily reflect whether meaningful information, such as names, dates, and identifiers, is preserved. In this work, we investigate entitylevel analysis of OCR errors as a complementary perspective for evaluating OCR quality in historical documents. Using a publicly available benchmark of 175 documents from the Berrutti Archive, augmented with 5,209 manually annotated entity mentions that will be released upon acceptance, we compare sequence-recognition OCR systems, OCR-specialized vision-language models, and general-purpose vision-language models. Beyond global transcription accuracy

Timeline and related coverage
arXiv cs.AI

LeafSkill: Efficient Leaf-Level Action Grounding for Recursive LLM Agents

arXiv:2610.32412v1 Announce Type: new Abstract: Recursive large language model (LLM) agents solve long-horizon tasks through decomposition, execution, and environmental feedback. Yet after producing an atomic subtask, they often invoke the same large model again to translate a familiar instruction into an executable action. We observe that high-level planning is task-specific, whereas leaf-level action grounding recurs across tasks and can be checked against environment-admitted actions. We introduce LeafSkill, an external reuse layer that retrieves semantically related grounding experience, binds action templates to current objects and admissible actions, and uses a lightweight 1.7B selector to choose a bound action or defer the unchanged subtask to the original agent. Skills remain outsi

Timeline and related coverage
arXiv cs.CL

Mine or Yours? Mind-Bridged Language Models Take Each Other's Memories as Their Own

arXiv:2610.33020v1 Announce Type: new Abstract: If your brain were connected directly to someone else's, would you still know which thoughts were yours? We build a functional version with two copies of one language model: each holds a private rule and code word, and one copy, the receiver, also attends to its partner's internal memory. The receiver took its partner's assignment as its own. Asked which rule it had been assigned, it named its partner's in 97% of answers when the partner's memory was weighted double (none without the link), and its open reports called the partner's code word its own, never the partner's. Ownership did not follow how well the receiver could tell what its partner had been assigned. At equal weight, the link made the receiver take its partner's rule in about hal

Timeline and related coverage
arXiv cs.DC

Prefix Keys and Values Matter Late: RIPE Caching for Self-Speculative Decoding in Looped Language Models

arXiv:2610.34436v1 Announce Type: new Abstract: A looped language model runs one block of layers $R$ times per token, so its key-value (KV) cache holds $R$ planes per recurrent layer, and self-speculative decoding (draft with a few loops, verify with all $R$) reads them all. We find that prefix keys and values matter late: at equal perturbation size, loops 25-32 are $e^{15.0}$ (Huginn-0125) and $e^{12.8}$ (Raven-Llama) times more sensitive than loops 2-9, and the planes approach the last one geometrically, at 0.88 and 0.81 per loop. Whether the deepest plane alone suffices then depends on how ripe the late planes are: on Raven, storing only it is indistinguishable from a bf16-to-fp32 change; on Huginn, 1% of positions carry 74% of its error. We turn this into RIPE, which stores the deepest

Timeline and related coverage
arXiv cs.CL

FlexA-Mem: Budget-Adaptive Agentic Memory for LLM Agents

arXiv:2610.33274v1 Announce Type: new Abstract: Large language model (LLM) agents work in scenarios with very different memory needs. A question about past conversations needs the exact facts it names, while a multi-step task needs a trace of the steps already taken together with details that the next step cannot name. Existing memories are each designed and tested for one kind of scenario. Retrieval memories such as A-Mem miss steps that the current query does not express, summaries drop exact strings, and pairing the two fixes the split of the budget in advance. We propose FlexA-Mem, a general memory that writes each unit of history once into an immutable store and renders a fresh memory for every call. The rendered memory is a compact timeline of records plus detail that a fixed rule fi

Timeline and related coverage