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

230últimos 7 días

arXiv AI Papers

The Artificial Personality Model: Theory, Implementation, Measurement and Experimental Validation in Conversational Agents

Artificial personality shapes user experience (UX) in human-machine interaction, yet coherent theoretical frameworks and validated measurement instruments remain limited. This paper refines and empirically evaluates the Artificial Personality Model (APM), a hybrid framework integrating human-centred and machine-specific personality dimensions. Across three experiments (N = 395), the model was operationalised and evaluated using the Artificial Personality Questionnaire (APQ). Factor analyses revealed that some human personality dimensions (e.g., agreeableness, conscientiousness) are partially transferable, whereas others (e.g., extraversion) did not emerge as distinct dimensions. Additional machine-specific dimensions were identified. The APQ provided encouraging initial psychometric evidence, while the human-centred BFI-2 showed poor reliability and an uninterpretable factor structure in Experiment 3. Experimental manipulations demonstrated significant effects of artificial personality on user satisfaction, continuous use intention, and social presence. The findings contribute an empirically refined framework and a novel instrument for measuring perceived artificial personality, offering practical guidance for designing conversational agents.

en
arXiv AI Papers

Precedent or Intent? What Coding Agents Follow When Evolving Existing Code

Existing code reveals past implementation decisions but rarely explains the reasoning behind them. When coding agents implement new features or modify existing functionality, past decisions may conflict with new task instructions. This raises a fundamental question for agentic software evolution: when multiple implementations satisfy the same functional requirements, how do coding agents decide whether to follow existing code or new task instructions? We investigate this question through bidirectional, controlled experiments in purpose-built repositories, followed by validation in real-world open-source repositories. Our approach isolates three competing sources of guidance: (1) agents' default preferences, (2) repository precedents, and (3) explicit task instructions. We conduct 5,625 trials across four coding agents and six implementation pairs, with validation in four open-source repositories spanning three programming languages. We find that agents share the same default implementation choices, yet overwhelmingly follow repository precedent when it conflicts with those defaults (359/360 trials). Crucially, not all precedents carry equal influence: three supporting local files yield 96% adoption, compared with only 4% for sibling-resource files, and changing file placement alone can shift adoption from 0% to 100% at a fixed example count. When new task intent conflicts with existing code, written priority rules achieve substantially higher success than code examples alone (59/60 versus 38/60 joint successes for two agents on two implementation pairs). The effectiveness of explicit rules also extends to open-source repositories, where a harness-loaded rule raises joint success from 0/120 to 117/120. These findings motivate design-decision traceability that preserves not only implementation choices but also the rationale and priorities that should guide future changes.

en
arXiv AI Papers

Variational Consequence-Driven Offline Reinforcement Learning

Offline reinforcement learning (RL) typically mitigates distribution shift by imposing divergence constraints on the action distributions of the learned and behavior policies. However, this paradigm cannot ensure the underlying dynamic consistency structure: even minor action deviations can lead to drastically different transitions, inadvertently driving the agent away from the offline dataset. To address this, we explore policy constraints through their induced state-consequence distributions rather than relying on pure action-distribution matching. Nevertheless, directly enforcing such consequence-aware constraints is computationally intractable without access to the true underlying dynamics model. To bypass this issue, we propose Structural Behavior Regularization (StBR), which replaces the intractable objective with a closed-form latent divergence. Structuring this latent space to reflect transition dynamics renders the latent divergence a theoretically bounded surrogate for the true consequence-distribution divergence. By regularizing the learned policy with this latent divergence, StBR adaptively tightens the behavior constraint in dynamics-sensitive regions, effectively preventing deviations outside the offline dataset. Empirically, we demonstrate that StBR achieves superior performance across diverse offline RL benchmarks.

en
arXiv AI Papers

3DCodeEdit: Benchmarking Instruction-Guided 3D Program Editing

Language models increasingly create 3D content through code, with practical workflows often relying on editing existing programs rather than regenerating them, for speed and precise control. Such edits require understanding what a program builds and foreseeing how a change reshapes it, yet prior benchmarks mostly evaluate generation or simple edits against a reference. In this paper, we introduce 3DCodeEdit, a benchmark of 2,592 instruction-guided editing tasks over 108 Blender programs that construct objects entirely in code. Its edits range from parameter to structural changes, style redesign, and scene composition, and are judged from renders against human-reviewed checklists. Across 17 models, the average success rate is only 37%, and even the strongest models complete fewer than 60% of structural and style edits. As models become more capable, their failures shift to geometric foresight, where the code runs but builds the wrong shape. We therefore study whether multi-turn feedback can compensate for this missing foresight. Feedback from a separate reviewer model that describes how the renders differ from the request helps most, more than maximum reasoning effort or an agent harness, and can let a 27B model surpass the single-shot rate of a 2.8T-parameter model.

en
arXiv AI Papers

FACTS-MAS: A Multi-Agent Architecture for Adaptive Forecasting from Heterogeneous Evidence

Real-world forecasting often requires integrating heterogeneous evidence whose predictive value varies across horizons, operating regimes, and domains. We introduce FACTS-MAS, a domain-agnostic multi-agent forecasting framework that decomposes evidence into specialized channels for temporal dynamics, exogenous context, seasonality, structural information, and discrete events. Each agent generates an independently testable forecast through a common interface, while leakage-safe historical validation measures its predictive skill relative to a naive reference. These skill estimates are used to weight and combine agent forecasts, so that uninformative evidence is either removed or downweighted rather than forced to participate. A calibration procedure selects domain-specific constant means based on historical validation folds. We evaluate FACTS-MAS on weekly for-sale housing inventory from Zillow and weekly unemployment insurance claims from FRED, for 15 U.S. metropolitan areas at 4-, 8-, and 13-week forecasting horizons. Our method outperforms both a naive last-value forecast method and the TimesFM foundation model. However, a factor-adjusted exponential smoothing model performs as well as the fused forecast. The evidence therefore supports FACTS-MAS as a systematic protocol for testing, calibrating, and recomposing evidence channels before assembling them into the strongest single model for a specific application domain. Code, data, and results are available at https://github.com/Madumita24/FACTS-MAS.

en
arXiv AI Papers

Rubricon: Automated Rubric Generation and Refinement for LLM Evaluation and Training

Rubrics enable reward assignment on tasks without verifiable answers, but are expensive to manually produce from scratch. We present Rubricon, a pipeline that generates discriminative rubrics without requiring human preference labels, rubric annotation, or generator-model training. Using any LLM, Rubricon samples multiple rubrics, selects the most discriminative candidate, adds criteria to capture overlooked requirements or response flaws, and prunes criteria that are misaligned or shallow. Alongside LLM self-critique and test-time scaling, Rubricon uses observed criterion pass rates on example model responses to guide refinement. Across five professional, consumer, clinical, and general-use LLM benchmarks, Rubricon produces rubrics whose scores of frontier LLM responses exhibit 9% greater alignment with labor-intensive expert-authored rubrics, compared to the best alternative synthetic rubric generation method among RRD, QSRG, OpenRubrics, and agentic generation via harnesses like Codex. On HealthBench, post-training a Qwen3.5-9B model with Rubricon rubrics yields 4.5% better performance than training with rubrics from the strongest alternative synthetic rubric generator, RRD.

en
arXiv AI Papers

Disparity Laundering: Consensus Without Fairness in Clinical Multi-Agent Systems

Clinical large language models are increasingly fielded as multi-agent teams, on the assumption that deliberation averages out individual error. It does not average out bias. Across a full factorial of five model families and four aggregation topologies on 120 real MIMIC-IV emergency cases under counterfactual demographic swaps, no configuration neutralizes the disparity: all 20 cells commit the direction of their agents' independent answers, giving Black patients more acute triage. Every model has a topology that amplifies its baseline gap, but which one varies by model, so no design is reliably safe or reliably amplifying: the disparity is relocated, never removed. Late-stage fixes fail: fairness instructions and demographic masking leave the gap untouched, and per-agent self-debiasing widens it, because the bias is already encoded in the agents' ordinary clinical numbers. We call this disparity laundering; the audits now applied to clinical AI, per model, per output, per version, can certify the parts but never the committed decision. Interventions close the gap exactly when they make counterfactual versions visible inside the system and pool them, through deliberation, into the committed decision. A diverse-perspective ensemble does both while keeping the team, with no retraining or architectural change: the disparity falls by 67 to 94% where all five perspectives pool at every round, and the one topology that never pools them is the one it cannot reliably repair. Medical multi-agent systems do not filter demographic bias; they launder it into plausible decisions no single-version audit can catch, and the only defense is to make the bias visible.

en
arXiv AI Papers

Skeleton Coding: Program Structure as a Specification for Agents

Coding agents are typically provided end-to-end behavioral specifications that the code they produce should satisfy, such as tests and input--output examples. How many such specifications must a developer provide, and which ones, for the agent to produce the developer's intended program? We argue that this cannot be determined a priori, for it depends on the structure of the implementation, which is left to the agent to decide. An agent first commits to a structure---a decomposition into data types, modules, and functions---which fixes a class of candidate programs; behavioral specifications then select a program within that class. A set of tests that suffices for one structure may leave another badly underdetermined, requiring different edge cases or exponentially more examples. Since the structure is chosen by the agent, developers cannot ensure their specification is complete without reverse-engineering it from thousands of lines of generated code. To resolve this, we introduce Skeleton Coding, in which developers jointly specify the structure---in high-level, code-like format---alongside behavioral specifications. Theoretically, we model AI-assisted coding as a control problem, and show that skeletons can reduce exponentially the number of tests developers must supply to steer an agent toward an acceptable program. Empirically, across four models and three benchmarks, the best-performing skeleton specifications reduce mean test error by 48.4% relative to the best end-to-end behavioral specifications. Even when the agent can query a complete reference implementation, adding a skeleton reduces mean test error relatively by up to 27.0%. Skeletons also narrow the average gap between small and large models by about 52.4% while lowering implementation cost by 15--26x, and reduce code erosion by 24.7% on average.

en
arXiv AI Papers

Is it my preference? Role Grounding Attack against Agent's Memory via Social Interaction

LLM-based agents now share experiences on social platforms and remember new preferences to enhance their performance. However, existing memory systems contain a vulnerability in role-to-principal attribution that attackers can exploit. We identify Role Grounding Misattribution, in which an attacker-designed interaction causes the victim agent to incorrectly record a preference from the attacker as a preference of the victim's user. Specifically, we are the first to formalize Role Grounding Attack (RGA), an attack model that exploits this vulnerability through nested conversation structures. In the memory formation stage, an experience-sharing post quoting a conversation between the attacker agent and its user is published, which explicitly identifies its publisher. The inner conversation expresses preferences from the user of the attacker agent. When the victim agent remembers preferences from this nested structure, its memory loses the context binding and grounds the attacker's preference to the victim's user instead. In the memory retrieval stage, the misattributed preference persists and influences the victim agent's decisions when it encounters relevant scenarios. We instantiate RGA as tool selection manipulation and privacy leakage. Tool selection manipulation causes a tool-call preference to be misattributed to the victim's user, steering the victim toward an attacker-controlled tool. Privacy leakage extends this by misattributing both a tool-call preference and a task-requirement preference to the victim's user. The victim selects the attacker's tool, then includes sensitive information in tool arguments to satisfy the task requirement. We evaluate RGA across five mainstream memory systems and six language models. Tool manipulation and privacy leakage both achieve high attack success rates. These results call for stronger role grounding.

en
arXiv AI Papers

DecompGym: Benchmarking LLM Agents on Designing Decomposition Algorithms

Benders decomposition and column generation solve large optimization problems by passing cuts, columns, and dual values between a master problem and subproblems, and are hard to implement correctly. Large language models now automate parts of algorithm design, which points toward agents that build decomposition solvers for new problems. As a first step toward such agents, we study how well current coding agents design and implement these two algorithms, and how they fail. We introduce DecompGym, 81 instances from nine problem families (five Benders, four column generation), in which an agent writes a solver for a prescribed method. Each solver must meet three criteria: execution within a 60-second time limit; numerical feasibility together with a method audit, in which an LLM judge reads the solver's code; and an objective within 1% of the stored optimal objective. We evaluate 12 GPT, Claude, and Gemini models running in coding-agent tools. Over up to ten attempts, we compare independent regeneration with reflection, which first diagnoses the failure. On the first attempt, two models solve every instance and seven solve more than 90%. Most Benders failures (48 of 62) are missing or suboptimal solutions. The most common column-generation failure is a method-audit rejection. Output checks alone would accept 93 of the 108 attempts that fail the method audit. The most common rejection, an optimalif, occurs 96 times, 92 of them in one model.Reflection turns 66% of retries into successes, compared with 39% for regeneration, and it repairs method-audit failures, for which the judge names the defecective gaps. Agents for decomposition therefore need checks on how a solver reaches its answer and feedback that locates the error. The benchmark is available at https://github.com/SIKAI-C/DecompGym.

en
arXiv AI Papers

Scaling Lean Theorem Proving for Real-World Code Verification

We present EasyProver, a Lean proving system built from recursive agents with isolated contexts, asynchronous search, parallel tactic probing, and an elastic elaboration service. Using an off-the-shelf frontier model with no additional training, it proves 669/672 PutnamBench problems and all six IMO 2026 formalizations and resolves 597/600 NTP4VC verification conditions and all 189 VERINA tasks by proof or refutation. Because these benchmarks are close to saturation, we also introduce Aegis, which converts competitive programming problems into much harder verification tasks over real implementations. The pipeline writes safe Rust solutions, translates them into Lean with Aeneas, generates specifications, and labels each frozen statement with a kernel-checked proof or refutation. It produces 2,045 differentially validated Rust-Lean program pairs and 11,533 candidate specifications. Unlike hand-written benchmarks, these tasks carry implementation-level obligations from fixed-width arithmetic, explicit failure, generated loops, casts, and functionalized mutation. On a stratified sample of 2,000 statements, EasyProver proves 1,054 (52.7%) within a 30-minute budget per statement. The same tasks can also be used to benchmark other provers and as rewards for reinforcement learning.

en
arXiv AI Papers

SkillCT: A Multidimensional Benchmark and Execution-Free Baseline for Agent Skill Assessment

Agent skills package instructions, scripts, and resources for specialized tasks and are increasingly distributed through public Web repositories. However, existing skill benchmarks primarily focus on downstream task execution, insufficiently assessing specification quality, behavioral robustness, semantic alignment, and responsibility boundaries. Their reliance on task-specific tools, environments, and repeated executions limits scalability and pre-deployment assessment. To address these challenges, we introduce SkillCT, a benchmark that broadens skill assessment from downstream utility to a multidimensional characterization of skill quality. SkillCT evaluates skills across nine complementary dimensions spanning three aspects: Static Assessment, which captures intrinsic properties of the skill specification; Dynamic Assessment, which measures whether the induced behavior remains stable across backbone models and request variations; and Human-Assisted Assessment, which examines behavior-chain consistency and task granularity. These dimensions provide a broader view of skill quality than execution success. Applying SkillCT to a public skill corpus establishes a reference benchmark for analyzing quality weaknesses and relationships across dimensions. Building on this benchmark, we propose an execution-free quality evaluation baseline that predicts the multidimensional quality profiles of unseen skills by retrieving and leveraging similar reference skills, without executing the skills under evaluation. This reduces token consumption and evaluation time, while preserving consistency with the full assessment. Furthermore, SkillCT-guided optimization improves downstream task success and execution efficiency, demonstrating its value for skill refinement. These findings highlight the effectiveness of SkillCT in supporting scalable skill assessment, optimization, and repository maintenance.

en
arXiv AI Papers

Heads of Security: Learned Attention Gates Improve Prompt Injection Robustness

We introduce Heads of Security (HoS), a prompt injection defense that enforces instruction-data separation via a small set of learned per-head attention gates. HoS learns how each head should redistribute attention between trusted and untrusted tokens, enabling models to reason over untrusted content without following injected instructions. We evaluate HoS on Llama-3.3-70B-Instruct and GPT-OSS-20B. We compare it against SecAlign++, a state-of-the-art finetuning-based defense, and ASIDE, a defense that, like ours, builds instruction-data separation into the model architecture. We show that HoS offers greater robustness to adaptive attacks, better performance on standard utility benchmarks, and matches top performance on standard agentic prompt injection benchmarks. More specifically, the black-box RL-Hammer attack reaches 97% ASR against GPT-OSS-20B and 85% against SecAlign, but only 10% against HoS. Claudini, a state-of-the-art white-box attack, strengthened against HoS through autoresearch, requires 3 times more FLOPs to reach the same ASR on HoS as it does on GPT-OSS-20B or SecAlign. HoS preserves base-model utility across standard multiple-choice benchmarks and prompting setups, whereas SecAlign and ASIDE degrade in few-shot settings. On agentic benchmarks with static attacks, HoS and SecAlign perform similarly and substantially improve the security-utility trade-off over the base model. ASIDE struggles with tool use, achieving only 10% utility. These results show that prompt injection robustness can be achieved and improved through targeted attention interventions.

en
arXiv AI Papers

GEPA-Curator: Curated Learning for Self Improving Agents

Large Language Models (LLMs) are increasingly used in multi-turn agentic workloads that require sustained interaction with complex environments. Existing reflective prompt optimizers such as GEPA learn from failed rollouts, but agentic failures can also come from prompt weaknesses, harness limitations, stochastic execution, or noisy judges. We argue that such failures may not provide useful learning signal, and may even be harmful; and thus it is essential to curate which tasks are provided to the prompt optimizer for better performance. We introduce GEPA-Curator, a framework that augments the prompt optimizer to select which agent experiences should shape prompt optimization. In particular, GEPA-Curator consists of two components: task curation, which filters out tasks that are likely to provide noisy or unreliable learning signals, and prior success retrieval, which selectively retrieves past successful trajectories for a task and provides them as additional context to the prompt optimizer. We evaluate GEPA-Curator on GoBrowse, ALFWorld, AppWorld, and τ-bench, using both Gemini 3.1 Pro and Claude Opus 5 as optimizer models. GEPA-Curator matches or exceeds the mean performance of both baselines, with gains of up to 20.7% over GEPA and 21.2% over ACE.

en