overfeed.news
Anuncio

SRExpert

Deja de saltar entre 6 herramientas de Kubernetes.

Monitoreo, alertas, seguridad, despliegues Helm y operaciones con IA en una sola plataforma.

Probar 30 días gratis

Tema

Agentes

3029documentos

231últimos 7 días

arXiv AI Papers

TradeWar: A Benchmark for Execution-Grounded Trade Negotiation with Adaptive LLM Agents

Multi-turn negotiation remains a challenging problem for large language model (LLM) agents. While LLMs can conduct natural-language dialogue, existing benchmarks predominantly assess only agreement rates, overlooking whether negotiated commitments actually create value once executed. To address this gap, we introduce TradeWar, a multi-country simulation benchmark that translates negotiation dialogues into concrete tariff and trade-share policies, enforces capacity and network constraints during settlement, and evaluates outcomes via an Economic Health Index (EHI). To solve this execution-grounded task, we propose TACTIC (Trade-aware Adaptive Consolidation and Theory-of-mind for International Commerce), an agent that iteratively refines its negotiation strategy across episodes-without updating base LLM weights-by leveraging prior experience, opponent behavior, and past settlement outcomes. Despite using zero-shot chain-of-thought (CoT) prompting, PromptLLM attains a 75% agreement rate but only 57.1 final EHI (*100), whereas TACTIC reaches 68.8. Across 20 sequential episodes and three seeds, TACTIC's final EHI improves from 58.2 to 73.2, compared with 65.2 for an ablation without cross-episode updates. Under technology-controls and energy-crisis shocks, TACTIC also exhibits smaller performance degradation than PromptLLM and MemoryLLM. These results indicate that CoT deliberation and interaction memory alone do not fully address delayed execution feedback, whereas settlement-grounded adaptation improves long-horizon negotiation in TradeWar.

en
arXiv AI Papers

AutoAnalysis: An automated, self-updating meta-analysis of human-AI collaboration

As generative artificial intelligence (AI) becomes more capable and widely used, understanding when and how humans should work with these systems is becoming increasingly important. However, the empirical evidence in this space offers conflicting recommendations, which leaves individuals and organizations without clear guidance on when to combine human and AI capabilities. Existing meta-analyses can help reconcile these findings, but they require substantial manual effort and cannot readily incorporate new evidence as it emerges. To address this challenge, we introduce AutoAnalysis: an automated, self-updating meta-analysis of when humans and AI work better together, and when they work better alone. AutoAnalysis' most recent run synthesizes 1,955 effect sizes from 420 papers. Across this body of work, we found that, on average, human-AI combinations performed significantly better than humans alone, but they performed significantly worse than the better of humans or AI alone. These findings highlight the important distinction between improving human performance and achieving human-AI synergy and underscore the need to evaluate collaboration against both human and AI performance alone. As new studies emerge, AutoAnalysis will integrate their findings into the meta-analysis, providing cumulative evidence about when humans and AI perform better together and how human-AI performance varies across AI agents, tasks, and processes.

en
arXiv AI Papers

SecPO: Principled Adversarial Training for Prompt Injection Security

Recognized as a top threat to AI agents, prompt injection allows instructions from untrusted data (email, documents, websites) to manipulate the agent's operation. The existing best-defended LLM, Meta-SecAlign, is trained with the DPO loss but still suffers from attack success rates (ASRs) approaching 100% under adaptive prompt injections. One reason is that DPO anchors the model around the undefended reference model, which is insecure. We show an idealized reference model---an injection-invariant, utility-preserving oracle---can nevertheless be approximated, as its output distribution in training is interestingly accessible. This new observation motivates a theoretically principled SecPO loss. Another Meta-SecAlign shortcoming is that it trains on weak simulated attacks. We implement an efficient adversarial training (AT) pipeline that synthesizes strong injected inputs (best@240), and train the model on them. Our AT reduces ASRs by 1.5-14.5across three SoTA adaptive attacks, compared with Meta-SecAlign; the SecPO loss reduces them by a further 2.4-4.6compared with using DPO loss. In agentic workflows, our SecPO + AT Qwen3.6-27B is much more secure than Meta-SecAlign: 8.8% vs. 78.8% AgentDojo ASR@800 under the AttackerMovesSecond attack. Moreover, our defended model shows no noticeable reduction in benign utility in nine benchmarks covering agentic tool calling, instruction following, science, and math. We release our {//github.com/Sizhe-Chen/SecPO}{code}, ${//huggingface.co/datasets/Sizhe-Chen/Qwen3.6-27B-Instruct-SecPO-trainset}{training data} (with optimized injections from AT), and {//huggingface.co/Sizhe-Chen/Qwen3.6-27B-Instruct-SecPO}{model}$.

en
Google Developers Blog

DevFest is back!

DevFest 2026 runs from October 1 to December 31, bringing together nearly a million developers across more than 800 global events centered on the agentic AI era. Under the theme "Build, Secure, Scale," participants gain hands-on experience with Google’s developer stack—including Gemini, Google AI Studio, Google Antigravity, and Web MCP—through live workshops and codelabs. The conference focuses on enabling developers…

en
arXiv AI Papers

From 1D Benchmarks to Complex 3D Geometries: Can Agents Reliably Specify Problems for Automated PDE Simulation?

Turning an engineering request into a simulation requires consistent geometry, physics, boundary conditions, and numerical settings. Recent agent-assisted systems automate simulation setup, but successful execution alone does not establish whether the specification preserves the intended problem or correctly handles missing information. We study whether agents can reliably construct complete executable JSON specifications for automated geometry creation, meshing, PDE solving, and result export. Our workflow combines model extraction with deterministic scientific and capability checks, explicit clarification, and validated local patches that preserve unrelated accepted fields. We evaluate specification correctness, execution completion, and numerical verification separately. On 120 template-related requests, the full workflow achieves 98.3% correct first-turn specification and decision outcomes, compared with 92.5% for schema-assisted single shot and 82.5% for model-only: gains of 5.8 and 15.8 percentage points, respectively. It makes no false-ready decisions among the 42 requests requiring clarification or rejection. Component ablations identify contributions from scientific checks and conditional repair. Separate downstream studies cover 1D, 2D, and 3D steady and unsteady, linear and nonlinear problems, including flow and elasticity with complex three-dimensional wing geometries. A 30-case gallery demonstrates automated execution from retained JSON specifications, while 9 of 12 selected live user-to-results tests achieve joint specification, execution, export, and numerical-reference success (75.0%). These results support traceable, engineer-reviewed simulation assistance within the tested scope, while fresh-response regressions identify consistency as a priority for further improvement.

en
arXiv AI Papers

Rome Wasn't Built in One Turn: Replay-Grounded Reward Signals for Long-Horizon Freeciv Agents

Training language-model agents to play long-horizon strategy games is hard because deterministic feedback is sparse and often arrives only at the end of a game. In-game scores can offer dense signals, but they do not reliably predict future outcomes: in 8-68% of position pairs across eight strategy games, the higher-scoring position leads to the worse outcome. We term this phenomenon scoreboard traps. In Freeciv, an open-source turn-based empire-building game where several players manage units, cities, and diplomacy over hundreds of turns, we look into better reward signals for gameplay agents. To facilitate this, we build CivHarness, an open system that saves current game states, branches on different decisions, and replays the game to future turns to provide measurable long-horizon feedback from saved positions. We use CivHarness to train CivTelescope, an LLM Judge that predicts which one of two game positions will yield the better outcome. On scoreboard-trap pairs, CivTelescope is 1.3-2.0 times more accurate than off-the-shelf language models, and it generalizes to new game starts, later turns, and unseen rules. We then train a Freeciv gameplay agent with CivTelescope as a dense reward, and call this recipe CivMarshmallow. When used in the middle stage of the game where scoreboard traps are common, CivMarshmallow reaches an average training phase gain of 8.94 points, 77% more than the best baseline, the end-of-game reward. Over the full 120-turn game, CivMarshmallow uses a hybrid reward that starts from the scoreboard or the end-of-game reward and shifts to CivTelescope as the game advances; this hybrid reward scores highest among the rewards we compare.

en
arXiv AI Papers

MEMIG: Self-evolving Memory Construction for Antibody Optimization

Memory has become central to self-evolving LLM agents, which store and retrieve experience from past rollouts to guide future decisions. Existing systems represent this experience as free-form natural language and maintain it by rewriting, which fits tasks whose experience is narratable. However, in scientific discovery and optimization, experience is often a quantity measured by an oracle under a specific context. Rewriting it as text leaves no index for where a record should be, replaces a measurement with a description, and cannot express how interventions interact. To address this, we argue that agent memory for biomolecule optimization should instead be indexable, quantitative, and structured, and we introduce MEMIG. This memory construction framework realizes these three properties. In detail, MEMIG addresses each insight with a domain-grounded identifier and accumulates the quantitative effect measured by a property oracle, so that updates remain local and retrieval becomes an exact lookup. Next, MEMIG connects insights whose interventions are applied together and measures their epistasis by decomposing each evaluated set. Our results show that MEMIG improves performance in most settings across in silico antibody optimization tasks.

en
arXiv AI Papers

From Evaluation to Evolution: Benchmarking Image Editing and Evolving Image Models

Real-world image editing requires coordinating multiple visual transformations with content preservation and reference constraints, yet aggregate scores can readily obscure unmet local requirements. Effective evaluation must therefore identify local failures and translate them into priorities for subsequent model improvement. We introduce WeGenEditBench, comprising 2,740 evaluation instances and 148 task types across single-image, text-intensive, and multi-reference editing. Pre-generated checklists shared across models decompose each request into atomic requirements; item-level deductions and visual evidence are established first and then summarized into scores for edit execution, preservation, visual quality, and task-specific correctness. To support the experience-acquisition component of recursive self-improvement (RSI), we develop WeGenEvoStudio, a unified multi-agent harness for RSI-oriented learning that integrates model-conditioned failure diagnosis, retrieval-grounded data construction, supervised adaptation, and re-evaluation. Among 15 evaluated configurations, GPT-Image-2 leads single-image editing with an Overall score of 4.076, while Seedream-5.0-Pro leads text-intensive editing at 4.291. Evolution experiments across four generation and editing benchmarks demonstrate substantial targeted gains: on their report-selected Top-5 single-image targets, FLUX.2 [dev] improves Overall from 1.083 to 3.517, while Qwen-Image-Edit-2511 gains 13.2%. Together, our benchmark and harness provide a foundation for developing more reliable image models through interpretable evaluation and feedback-driven learning.

en
arXiv AI Papers

Beyond CLIP: Calibrated (Few-Shot) Defect Detection With System One Decision Models

Cameras and vision sensors are widely used for product and process inspection in manufacturing environments. Traditionally, this process required thousands of images of both nominal and defective products to train such models. Recent research shows that vision transformer (ViT) models, such as CLIP, can reduce this requirement to 50-100 images per nominal and defective class. However, collecting even 50 defective images can be difficult in high-yield or low-volume manufacturing processes. In this paper, we examine the utility of two recently proposed structured decision models (Jev and Clef-Flash) in applications using as few as k=2 reference images per class at inference. In the process, we provide three main contributions: (a) a framework for k-shot learning of these models for image classification/inspection applications; (b) an agentic approach for automatically refining the text descriptions that guide image classification in these decision models; and (c) an approach to calibrate the resulting defect probabilities to improve their reliability for inspection decisions. We test these contributions in five manufacturing case studies. Using two reference images per class, both Jev and Clef-Flash outperform CLIP's test accuracies with the same references (0.75-1.00 [Jev] and 0.71-0.99 [Clef-Flash] vs 0.67-0.84 [CLIP]). Furthermore, we show that our agentic refinement of text descriptions significantly improves accuracy across 6 of 8 model-application combinations, and our calibration approach reduces the Brier score in 13 of the 15 model-application configurations. To support the reproducibility of our work, we provide our replication code and have created the R "decisions" package for evaluating additional models. We also provide a publicly available web app that allows practitioners to inspect their own images with no code.

en
arXiv AI Papers

When AI Investigators Cannot Trust Their Tools: Conflict-Aware Evidence Verification for Cyber Threat Investigation

LLM agents increasingly triage security alerts by combining the outputs of several detection tools, implicitly treating those tools as trustworthy. Unlike prior work on conflicts between a model's knowledge and its context, we study conflicts among the tools themselves: what happens when this machine-generated evidence is conflicting or wrong. On the corrected CIC-IDS2017 dataset, four heterogeneous detectors emit labels and confidences that we corrupt under a threat model varying the number of corrupted tools, the persistence of the corruption, and the confidence attached to wrong outputs. Across open-weight LLMs from 3B to 14B parameters, unverified investigators are fragile: one corrupted detector out of four lowers naive accuracy to .50-.72, three lower every unverified investigator to .13 or less, and honest disagreement alone makes them abstain on up to 63% of flows. We propose Conflict-Aware Evidence Verification (CAV), built from established components: an equal-weight vote that ignores reported confidences, an evidence-conflict gate, and an independent nearest-neighbour trust check that tests the leading candidates. With its prompt frozen before testing, CAV-LLM improves on the naive investigator in every corrupted condition (p < 0.001), reaching .84-.88 with three corrupted detectors against at most .08, while calling the LLM on 0.4% of clean traffic. A fixed verification rule is as accurate or better unless most tools are corrupted. When we make the independent channel itself noisy, CAV inherits its errors: it stays ahead when two or more tools are corrupted, but adding the channel as an extra voter is better when at most one is. Verification thus moves trust from the tools to the check, which must be measured and protected in turn.

en
arXiv AI Papers

TraceSpec: Understanding and Improving Speculative Decoding for LLM Agents

LLM agents execute tasks through repeated model calls over evolving histories of reasoning, actions, and tool feedback. Aggregate speculative-decoding metrics merge these distinct decisions, providing limited guidance on where draft supervision is needed. We present TraceSpec, a framework connecting trajectory evaluation with adaptive draft training. It combines dynamic execution with fixed-prefix replay and introduces TraceSpec-Traj, a corpus of 10,000 training states and 2,500 test states spanning browsing and software engineering. Analysis of five speculative baselines reveals that aggregate acceptance can rise with context length while declining within matched late browsing actions. Workload and phase further distinguish these trends, motivating supervision guided by trajectory conditions. TraceSpec trains on intermediate assistant turns and allocates a fixed prediction budget using state-conditioned estimates of prefix-aware acceptance gaps. Across three target sizes and two temperatures, it improves replay throughput by 12.5% to 22.6% over its DSpark base. Qwen3-4B ablations show that adaptive allocation increases accepted length by 3.3% to 10.0% over fixed full-turn supervision, with additional comparisons substantiating the roles of state conditioning and consecutive-token agreement. The resulting evaluation resources, trajectory findings, and training strategy connect the analysis of agent execution to practical draft improvement.

en
arXiv AI Papers

Context as Infrastructure: Knowledge Compilation for Retrieval in Agentic Systems with Harnesses

Retrieval-augmented generation is becoming agentic. A search harness writes queries, reads results, reformulates, and decides when to stop. This largely solves accuracy: a harness with only BM25/grep and MiniMax M3 answers 85% of BrowseComp-Plus and 91% on multi-hop FRAMES in our runs, without compiled or vector indexes. It exposes a context problem: an undisciplined loop repeats queries, rereads documents, and fills the window with unused passages. The missing layer is knowledge compilation: a configurable ingestion pipeline where LLMs enrich documents with context no chunk contains alone--navigation hierarchies with claim-evidence leaves, entity graphs, timelines, mind maps, ontologies, wikis, and memory. Compilation is not a better retriever: under a competent harness, structural artifacts gave no detectable accuracy gain on FRAMES, and a PageIndex-style outline degraded at scale. It is a supply layer. A navigation tree whose leaves are claim-evidence pairs--the mechanism we measure--cuts query tokens by 91% when evidence suffices and adds 1.9% when it does not, a 38% average reduction; this implies a 2% break-even sufficiency rate and a measured rate near 43%. A decision gate cuts latency from 140 s to 30 s, though substitution's token saving is bought with retrieval rounds and carries its own latency cost. Other artifacts--ontology, graph, wiki, timeline, mind map, memory--pay off in deployment (governance, integration, onboarding, temporal orientation, continuity) where accuracy benchmarks cannot see them. We describe RAGFlow's pipeline and harness (open source at https://github.com/infiniflow/ragflow), which turns the loop into five disciplined stations and keeps the context entering the model the smallest sufficient set; together they form an agent-native database: a store that hands the agent compiled, governed context instead of a ranked list of passages.

en
arXiv AI Papers

ImplicitHop: Evaluating knowledge integration across context and memory

The ability to integrate new information and deduce its consequences is central to learning, understanding, and reasoning in large language models (LLMs). Whether information arrives during training or in-context, models must not only store local facts, but propagate their long-range implications globally. To explore information integration in LLMs, we introduce two complementary natural language benchmarks for large-scale evaluation of deductive reasoning as a function of inference depth. The first is a formal graph benchmark enabling controlled evaluation over a wide range of graph topologies and integration tasks; the second is a knowledge composition benchmark grounded in real-world knowledge graphs. We use these benchmarks to compare knowledge integration from information encoded in context versus information encoded in model weights during pretraining, evaluating a set of open models implicitly, without chain of thought. We find that accuracy decays sharply with increased composition length for both pretrained and in-context knowledge. Information presented in-context, however, substantially outperforms deduction over information encoded in weights. These results quantify a fundamental limitation of current models with direct implications for prompt-based control of agent behavior and for continual learning strategies, and they provide a foundation for developing training, prompting, and integration methods that support deeper reasoning.

en