overfeed.news
Anuncio

Privum

Construimos, protegemos y operamos tu infraestructura digital.

Software, sistemas de IA, pruebas de penetración y nube segura para empresas.

Hablar con Privum

Tema

Agentes

3048documentos

242últimos 7 días

arXiv AI Papers

From Memory Hits to Answerable Evidence: Query-Conditioned Memory Compilation for Long-Term Agent Memory

Long-term agent memory requires recovering answer-relevant evidence dispersed across turns and sessions. Existing systems increasingly use structured memories and adaptive retrieval, yet often pass retrieved or expanded units directly to the reader, coupling memory addressing with evidence presentation and leaving the final context redundant or incomplete. To address this gap, we propose MemCompile, a query-conditioned evidence compilation framework for long-term conversational memory. Given a query, the Address Plane locates relevant support through compact source-linked descriptors and capacity-aware Cells, while a normalization boundary resolves heterogeneous retrieval hits to stable SourcePacket identities. Its Evidence Plane then allocates a bounded evidence budget across complementary packets, admits limited additional support, and renders the retained claims associated with each selected packet into an answer-ready context. MemCompile achieves 80.52% Judge Accuracy on LoCoMo and extends the empirical quality-cost Pareto frontier to a higher-quality regime. Its strong performance on LongMemEval-S further suggests that the benefits of query-conditioned compilation generalize across long-term conversational-memory benchmarks.

en
arXiv AI Papers

MobileInject: Evaluating Reasoning-to-Action Security of MLLM-Based Mobile Agents under Cross-Modal Consistency Injection

Multimodal large language model (MLLM)-based mobile agents are rapidly evolving from conversational assistants into autonomous systems that perceive, reason over, and act on smartphone environments. This capability also exposes a new security risk: adversaries can embed malicious objectives in cross-application mobile content and steer agent behavior through indirect multimodal injection. Although prompt injection has been studied in desktop and web settings, its cross-modal properties in mobile ecosystems remain poorly understood, and existing security analyses are still limited. To close this gap, we introduce MobileInject, the first benchmark for evaluating mobile agents against multimodal injection attacks and reasoning-to-action security risks. MobileInject provides a high-fidelity interactive mobile evaluation framework covering 11 scenarios, 9 security-risk categories, and 108 executable risk instances. It further introduces Cross-Modal Consistency Injection to exploit corroboration across modalities, two enhanced attack methods, Multi-Role Collaborative Deception and Reasoning-Camouflage Injection, to intensify trust manipulation and reasoning hijacking, and a Reasoning Security Diagnosis Framework for fine-grained failure analysis. Systematic experiments show that mobile agents are broadly vulnerable to multimodal injection, and that many failures stem from reasoning hijacking at early stages. These findings establish MobileInject as a systematic cross-modal benchmark for studying and improving the security of mobile agents. Code release details are provided in the Appendix Open Science section.

en
arXiv AI Papers

Optimist Deep Research: An Iterative, State-Centric Agent for Autonomous Literature Research

Most retrieval-augmented systems treat literature search as a single retrieval step followed by summarization. Real literature research works differently: the investigator's understanding of the question changes as they read, new subquestions appear, and evidence is weighed, not just collected. We present Optimist Deep Research, an open-source agent that runs literature research as an iterative evidence-acquisition process over an explicit, mutable research state. A research question is broken into a tree of subquestions, each served by search intents that are translated into source-specific queries over arXiv, OpenAlex, Crossref, PubMed, Semantic Scholar and the web. Results are merged into a canonical, provenance-preserving document registry through a conservative four-tier deduplication hierarchy. The registry is expanded by citation snowballing until a saturation criterion is met, and then screened, ranked and allocated to subquestions round-robin. Documents are read in parallel into a structured evidence store of claims with support, location, type and strength. A critic reviews the state along eight dimensions and returns research actions rather than a binary verdict: it can add, split, rephrase, deprioritize or close subquestions, so the research plan is an output of the investigation as well as an input. The final report is written section by section from the evidence store, and every citation resolves to a retrieved document. We describe the design, the deterministic machinery that keeps a language-model pipeline auditable, and a case study that read 28 of 237 retrieved documents in about three and a half minutes. We also report weaknesses the case study exposed.

en
arXiv AI Papers

Annotrace: A Workbench for Step-Level Annotation of Agent Traces

Every study of why LLM agents fail begins by labelling traces by hand, and every such study builds its own throwaway tool. Observability platforms record agent traces but offer no structured labelling; annotation tools label text but have no notion of a step, a delegation or a tool call, leaving it unclear what the smallest unit of execution to label should be. Annotrace reads six trace formats, including OpenTelemetry GenAI, LangSmith and Langfuse, and turns each run into an ordered, nested list of steps. The annotator writes their own labelling codebook; a frontier model proposes a starting set from a sample of their own traces, answers first, and is asked exactly the questions the human is asked, making annotation a joint human-AI process. Annotrace measures agreement between any two annotators, human or AI. On a multi-agent question-answering corpus it reproduces a previous manual effort's 235 annotation units exactly, and two models labelling the same traces agree 91% of the time at κ= 0.82.

en
arXiv AI Papers

NestedVLA: Learning to Consolidate and Generate Skills for Vision-Language-Action Models

Vision--Language--Action (VLA) models promise generalist robotic agents, yet consolidating skills learned across heterogeneous tasks and environments remains difficult: training data is fragmented across platforms, joint multi-task training suffers from interference, and model merging tends to introduce parameter conflicts or require architectural changes. We instead advocate a paradigm in which skills are first learned independently and then consolidated post hoc. To this end, we propose NestedVLA, which replaces parameter aggregation with parameter generation: a nested hypernetwork, conditioned on the target task, synthesizes task-adaptive action-expert parameters that compose with a frozen base VLA. Task-specific compressed VLM residuals are retained separately. This formulation enables flexible task-conditioned skill reuse while mitigating interference. Across three RL benchmarks (MetaWorld, ManiSkill, CALVIN), NestedVLA outperforms the strongest model-merging baseline by 41 pp on average, matches per-task fine-tuning within 1 pp on ManiSkill, and substantially closes the gap on CALVIN, pointing toward a storage-efficient route to skill consolidation. Code is available at https://github.com/WanyuGroup/NeurIPS2026-NestedVLA.

en
arXiv AI Papers

Beyond Marginal Influence: Interaction-Aware Memory Selection for LLM Agents

LLM-agent memory selection often uses retrieval rankings based on record relevance or individual influence. Such rankings cannot identify sufficient subsets under redundant or jointly necessary evidence. We study per-decision memory sufficiency: selecting a small subset that preserves full-memory behavior. To separate search error from model error, we introduce JointCoreBench, a benchmark with nine interaction families, six workflow domains, natural-language decisions, and exact sufficient-set oracles, and JointCore, a relevance cost-ordered group-deletion baseline that tests blocks before individual records. On 6,912 exact conditions, cost-ordered JointCore recovers a minimum-cost sufficient set in 100.0% of cases, reduces subset evaluations from 30.00 to 11.13 (62.9%), and achieves 87.8% active-memory savings. Across four 12B-70B model families and 432 tasks per model, its unweighted mean is 10.28 versus 16.00 model queries and 50.6% versus 43.1% minimum-cost recovery relative to cost aware singleton deletion. Both methods preserve full-memory behavior under the deterministic primary interface. Tests with physical deletion, UNKNOWN masks, PENDING sentinels, counterfactual values, and alternative labels identify interface dependent behavior. JointCore is an efficient benchmark baseline; the study does not establish deployment-ready memory compression.

en
arXiv AI Papers

Beyond Reward Scoring: Online Multi-Agent Preference Learning for Multimodal Response Generation

Multimodal preference alignment often follows a score-based RLHF pipeline: a reward model is first trained to learn human preferences, then used to score on-policy responses and optimize the response model's generation. This turns preference supervision into a scalar signal for generation: a model may learn to produce answers with higher preference scores, but is rarely trained explicitly to learn the reasons underlying human preferences. We therefore ask whether making preference understanding an internal capability of the response model can improve its generation. To investigate this question, we propose PrefMind, an online dual-agent reinforcement learning framework with two trainable agents: a response Generator and a preference Critic. Given a pair of candidate responses, the agents analyze and discuss which response better aligns with human preference. Human labels supervise their judgments and corrections. For pairs on which both the Generator and revised Critic correctly identify the human-preferred response, the Generator produces an improved answer, and the Critic compares it against the original preferred response to provide a generation reward. Both agents are jointly updated from interactions sampled with their current policies. Through this process, PrefMind trains the Generator to understand human preferences via explicit judgment and correction, and to translate this understanding into better responses. Experiments across three model scales show improvements in both standalone preference judgment and downstream response generation.

en
arXiv AI Papers

Sample, Mix, or Verify? Allocating Test-Time Compute under Imperfect Verifiers

A common way to make language models and agents more accurate is to spend more compute at inference time: generate many candidate solutions and submit the one a verifier prefers. Success then requires that some candidate is correct and that the verifier picks it. The first grows predictably with the number of samples; the second does not, because real verifiers (unit tests, majority votes, LLM judges, reward models) accept wrong answers, reject right ones, and make correlated mistakes. With a fixed budget, a practitioner must decide how many samples to draw, which models to draw them from, and how much to spend on verification, and today these choices are made by rules of thumb. We introduce SPLIT, which makes them from a small labelled pilot. It rests on an exact formula for the probability of submitting a correct answer under accept/reject and top-score selection that accounts for varying task difficulty, blind spots shared across models, and correlated repeated verifier calls. SPLIT fits the formula by empirical Bayes and uses it to plan budgets on unseen tasks. Across seven benchmarks spanning math, science QA, code and software-engineering agents, 26 models, 175 agent systems and six kinds of real verifiers, all from public releases, SPLIT lands within 0.02-0.8 percentage points of the best allocation in hindsight, while every fixed rule we test loses at least 2.5 points in some setting. Regret depends only on how well SPLIT ranks configurations, and it stays near-optimal under compute, price and latency costs and online. The formula also explains when asking more LLM judges lowers precision. As a forecaster far beyond the pilot, SPLIT beats power-law fitting when the verifier caps success, and we report where it loses.

en
arXiv AI Papers

Ignored, Not Refused: What Low Prompt-Injection Success Rates Hide in Small Tool-Using Agents

Tool-using agents read untrusted external content, which exposes them to indirect prompt injection (IPI), where hidden instructions hijack the agent's tool calls. Benchmarks measure IPI security by the attack success rate (ASR), which treats every failed attack as a successful defense. To test this assumption, we audit 33,000 trajectories from eleven open-weight agents (2-14B parameters) on InjecAgent and AgentDojo. A label-blind LLM judge shows that most failed attacks are ignored (76-80%) rather than refused (17-18%). With identical model weights, changing only the system prompt shifts InjecAgent ASR from 0.2% to 43%. Our Attack-Task Outcome Matrix (ATOM) further shows that in 21.7% of AgentDojo episodes, the agent stayed safe but did not complete the user's task. A low ASR therefore mostly reflects agents silently ignoring injections, not refusing them. Evaluations should report how attacks fail and whether the user's task is completed, alongside ASR. We release the labeled corpus, judge prompt, and analysis code.

en
arXiv AI Papers

FLARE: Physics-Grounded Evaluation of Language-Model Agents for Feeder Restoration with Degraded Observations

Restoring service after distribution-grid faults requires decisions from incomplete and conflicting information while respecting electrical constraints. Addressing this need, we introduce FLARE (Feeder-Level Agent Restoration Evaluation), a physics-grounded benchmark for post-isolation feeder restoration. FLARE con- tains 800 AC-feasible cases across five observation settings and allows agents to gather evidence, evaluate switches, and perform restoration actions under fixed operational limits. We evaluate five instruction-tuned models over 78,750 episodes, including topology, distributed-generation, and loading shifts. Mean normalized regret ranges from 0.082 to 0.148. Although every model has zero median regret, P95 regret ranges from 0.814 to 1.000, revealing an important failure tail. Shadow replay shows that 96.4% of 15,706 guard-rejected actions would have caused a physical violation. FLARE enables reproducible evaluation of language-model based restoration support while emphasizing the need for external safety checks.

en
arXiv AI Papers

Think More or Read More? A Token-Budget Theory of Reasoning with Shared Context

Reasoning systems increasingly improve answers by incorporating additional context into the model's input, from multi-agent debate, where agents read their peers' responses, to self-refinement, where a model revisits its own drafts. In these systems, communication consumes context as one agent's output becomes another's input. We study the regime where token reading and generation draw on one fixed token window, so every token spent reading is a token that cannot be spent reasoning. We develop a token-budget theory that formalizes this trade-off, modeling accuracy as a function of the reasoning budget remaining after reading and aggregating votes with a Condorcet jury model that permits correlated errors. For multi-agent debate, the theory gives a closed-form prediction for the optimal number of agents. This quantity is estimated from single-agent measurements, allowing the optimal group size to be determined without running debate, and the same accounting extends to a heterogeneous set of different models. We empirically verify our theory and show that, at the predicted group size, our method outperforms strong baselines under the tightest calibration spend, where debate-calibrated rules can afford only one or two questions. Self-refinement obeys the same accounting, with its own draft in place of a peer message. The theory further predicts that communication pays only when the gain in the accuracy ceiling exceeds the reasoning room spent on reading, with this condition tightening as the window shrinks. Across five open models and four reasoning tasks, self-consistency matches or beats deployed debate at 93\% of 980 matched window-and-group-size settings, with the gap being largest under tight windows and nearly disappearing at a loose one, consistent with the theory. Under a shared window, how much room a model has left to think matters more than what it reads.

en
arXiv AI Papers

MultiAgent-OPD: End-to-End Training of Hierarchical Multi-Agent Systems with On-Policy Distillation

In a hierarchical multi-agent system, a Leader assigns tasks and subagents carry them out. Jointly training the Leader and the subagents is difficult because a final answer gives only indirect feedback to the subagents. An LLM judge can score the performance of the subagents, but these scores depend on the judge's own assessment of the quality of subagents' responses. We present MultiAgent-OPD, which combines on-policy distillation with reinforcement learning to jointly train a shared-parameter Leader-Searcher-Answerer team end to end. We first train a Teacher in a Searcher-Answerer workflow using answer correctness. During team training, the frozen Teacher scores student-generated search and summary tokens to provide local process supervision for the Searchers, while the Leader learns from team success and the Answerer from candidate correctness. Across seven datasets, the trained system reaches 38.68% macro avg@4, exceeding Prompted Critic by 4.06 percentage points and C-MAS + RL, the trained cascaded multiagent system, by 2.61 percentage points. The team also solves more questions within four attempts.

en
arXiv AI Papers

Not All Test-Time Compute Is Evidence: Model-Specific Bias in LLM Reasoning

Test-time scaling methods implicitly assume that additional computation from the same model provides independent evidence. We show that this assumption fails within a single reasoning model: errors are correlated across repeated samples, across reasoning depth, and in the model's own self-evaluation, so more compute from the same model is not more evidence. We introduce DIA (Disagreement-triggered Independent Arbitration), which treats disagreement between an intermediate-stage and the final-stage prediction as a per-question signal of reasoning instability and resolves it by asking a small panel of heterogeneous models to solve the question independently, without seeing either candidate, and aggregating their answers directly. Across seven benchmarks and two base models, DIA outperforms full chain-of-thought in 12 of 14 settings, including a 7.00% gain on MuSiQue, while activating on only 17\% of examples and using up to 47.2% fewer tokens than a multi-agent baseline. Ablations show that both independent solving and solver heterogeneity are necessary for these gains.

en
arXiv AI Papers

MAS-Bai: Linguistically Informed Adaptive Multi-Agent Translation for Bowen-Script Bai

Large Language Models (LLMs) remain unreliable for extremely low-resource languages whose writing systems conflict with high-resource pretraining priors. We study Bai-Chinese translation in the Bowen script, where Chinese characters are frequently borrowed phonetically rather than semantically, causing severe literal-translation hallucinations. We propose MAS-Bai, a linguistically informed adaptive multi-agent framework for Bowen-script Bai-Chinese translation. MAS-Bai routes each input through either a lightweight retrieval-translation path or a deeper philological path with etymological and syntactic agents, and uses cycle-consistency with a lightweight reverse translator as an inference-time reliability signal. We construct a 6,536-sentence Bai-Chinese corpus and evaluate on a 1,536-sentence test set. MAS-Bai achieves 16.23 BLEU and 62.15 COMET, improving over Standard RAG by 8.11 BLEU and 6.85 COMET. Forward LoRA, expert ablations and controlled routing experiments distinguish the roles of supervised adaptation, Bai-specific expertise and conditional routing. The largest gains occur on Bowen phonetic loans and divergent Bai word order, while human evaluation and reverse-verifier analyses support the automatic results.

en