Tema

LLMs

2972documentos

229últimos 7 días

Can LLM Agents Be Forward-Deployed Engineers? Requirement Discovery and Delivery for Enterprise Text-to-SQL

LLM coding agents can increasingly automate model post-training, but whether they can act as forward-deployed engineer (FDE) agents, discovering customer requirements and turning them into deployment decisions, remains unclear. We study this on a real enterprise text-to-SQL engagement: a simulated customer, grounded in the real use case's requirements, starts with an ambiguous request. An agent must discover acceptance criteria, data permissions, and hardware constraints in the discovery phase, then plan and execute a post-training recipe in the delivery phase. Across 15 models, the strongest discover over 80% of withheld requirements and open-weight models discover 40-50%; in the delivery phase, only 25% of runs across eight coding-agent configurations pass all acceptance criteria. We identify four bottlenecks in this engagement: (1) incomplete discovery, with 40% of withheld requirements missing or misrepresented; (2) unreliable execution; (3) underused compute budgets and a lack of systematic comparisons across base models and post-training methods; and (4) benchmark accuracy does not guarantee production readiness. We suggest human review of discovered requirements, monitoring of the agent's plan during execution, and an explicit experiment-environment specification covering hardware, budget scope, and production checks.

arXiv AI Papershace 10 días

Can LLM Agents Improve Imperfect Earth System Model Parameterizations?

Earth system models (ESMs) rely on parameterizations to represent unresolved processes such as convection, cloud microphysics, and turbulence. However, translating advances in physical understanding into stable, validated parameterizations and integrating them into ESMs often takes years. Agentic AI could accelerate this process and enable more systematic exploration of design choices. Using warm-rain collision-coalescence as a test case, we evaluate agents' ability to synthesize scientific literature, reimplement published bulk parameterizations, and propose new functional forms as differentiable JAX code. We compare conventional parameterizations, data-driven emulators, and agent-generated closures against high-fidelity superdroplet simulations, repeating unattended experiments across ten language models. With expert guidance or iterative feedback, agents produced executable, differentiable, mass-conserving code, although unattended performance depended strongly on the scheme and language model. Iterative feedback lowered median rollout error for eight of ten models. Retuned physical schemes matched or outperformed many learned parameterizations at substantially lower computational cost, but two of 100 unattended agent-generated closures achieved slightly lower rain-mass error than the most accurate retuned scheme on held-out simulations.

arXiv AI Papershace 10 días

Grading the Unannotated: Insights from the WorkRB Skill Extraction Challenge at RecSys-HR 2026

Skill extraction benchmarks score models against a few human-annotated positives and treat every other skill in the vocabulary as equally wrong. At the scale of ESCO (13,939 skills) this binary view can reward models that rank the annotated positive high for the wrong reason, and hides semantically nonsensical predictions. The WorkRB Challenge at RecSys-HR 2026 replaces it with graded relevance: every candidate skill in a model's ranking window carries a 0 to 4 grade, and the leaderboard scores nDCG@100 against these grades. Since ternary judgements proved too coarse for objective annotation, relevance is decomposed into a cascade of four binary questions (same domain, activity mentioned, right granularity, replacement of a gold positive) that a smaller LLM judge can answer reliably; the labels are validated with blind human and frontier-model re-annotation. This paper documents the annotation methodology, the construction of five benchmark datasets (four with vacancy sentences as queries, one with lexically distant skill surface forms), the validation of the LLM cascade, and insights from the submissions. The field converged on multi-stage retrieve-and-rerank pipelines, whose gains come from clearing nonsense out of the ranking window rather than finding more positives: at the top of the leaderboard, the graded ordering is uncorrelated with what binary evaluation would have said. Graded labels expose much bigger gaps between top submissions and baselines than binary evaluation does, and show that semantic-understanding skill recommendation is still wide open. The clear next direction is bringing efficiency back: every submitted system we could size uses at least 42x, typically several hundred times, more parameters than the baselines it beats.

arXiv AI Papershace 10 días

Library of Layers (LoL): Adaptively Ordering Transformer Layers at Runtime

Computer programmers chain together the same reusable computational primitives, for example, conditional statements or loops, but in different orders to implement different algorithms. In contrast, existing language model architectures always execute their layers in the same order. We introduce Library of Layers (LoL), an architecture that dynamically orders its layers during inference to solve the problem at hand. LoL has a single hyperparameter, the size of its global library of transformer blocks, that allows it to transition seamlessly between parameter reuse and sparsity, generalizing the parameter-efficiency and FLOPs-efficiency tradeoffs of dense, depth-recurrent, and mixture of experts architectures in one unified family. We show that LoL achieves competitive performance with all three above baselines when pretrained on text data. On synthetic sudoku and maze data, we observe that the model employs distinct layer orderings to implement different solution strategies, and we can intervene on routing to force a model to apply a specific solution strategy to a problem instance. In a multilingual natural language setting, we find that LoL chooses different layer order patterns based on language and script. Similarly, we train LoL on safety data and fit probes to its router outputs, finding that these probes distinguish safe from unsafe text with high AUROC. LoL provides a path toward a future in which models dynamically compose their own computational graph, enabling more efficient and controllable reasoning.

arXiv AI Papershace 10 días

DistDebug-Bench: Can LLM Agents Diagnose Bugs in Distributed Systems?

LLM agents show strong potential in software engineering tasks such as competitive programming and code synthesis. Existing benchmarks, however, largely focus on small-scale settings such as self-contained Python modules, leaving distributed systems, an essential class of production software, under-examined. We introduce DistDebug-Bench, a benchmark for evaluating agents' ability to diagnose complex-system failures at the code level. It curates 120 high-quality real-world bugs from 11 widely used distributed systems, spanning 5 programming languages and 10 failure patterns. Through an extensive evaluation of state-of-the-art LLMs and agents, we identify substantial gaps between current agents and real-world debugging tasks. A recurring gap is tunnel vision due to a lack of explicit reasoning structure and nondeterminism from inconsistent tool-use scope. The benchmark and evaluator are available at https://github.com/OrderLab/distdebug-bench, with agent traces and a leaderboard at https://distdebug.com.

arXiv AI Papershace 10 días

VIAS: Value-Isolating Activation Steering for Multi-Value Alignment and Compliance for Organisations

Organisations increasingly deploy large language model agents that must follow organisational values. We check whether activation steering, which adds vectors to a model's internal activations during generation without changing its weights, can improve compliance beyond prompting alone. Since most scenarios involve several values at once, we focus on multi-value steering. A simple way to build these vectors is to contrast responses that follow all values relevant to a scenario with responses that violate them. However, this gives nearly identical vectors for different values: they capture a general compliance signal rather than individual values, which limits their use when combining several values. We propose Value-Isolating Activation Steering (VIAS), which contrasts responses to the same scenario under two prompts, one listing all relevant values and one omitting a single target value. We keep a pair only if the target value changes from compliant to non-compliant and both responses still meet a minimum compliance level on the other values. We evaluate VIAS on PROTECT, a workplace compliance dataset where each scenario is tagged with relevant values from a 21-value taxonomy. VIAS reduces overlap between value vectors, making them better suited for multi-value steering, although this alone does not lead to independent control over each value. Combined with prompting, VIAS complies with every tagged value on 69.6% of scenarios for Qwen2.5-7B, 75.2% for Mistral-7B, and 72.6% for Phi-3.5-mini, outperforming prompting alone for all three models.

arXiv AI Papershace 10 días

Ask, Don't Equip: Question-Driven Coding Agents for Deep Kernel Optimization

LLM agents for GPU kernel optimization sit at two ends of a structure-freedom tradeoff. Scripted agents fix what the model does at each step, via a learned policy, an optimization menu, or fixed roles, and are sample-efficient where the recipe applies and stall where it does not. Open-ended agents let a self-directed model mutate a population of kernels and pay for the freedom in trials: thousands of evaluations, repeated edits, and wrong candidates. Both respond to hard targets by equipping the agent with more: parsed profiler output, disassembly analysis, retrieval over documentation and libraries, and stores of lessons. We argue that both lack direction, a hypothesis about where the remaining gap is, and that a short question asked at the right moment supplies it without narrowing what the agent may do next. We present KernelSeek, a question-driven agent that makes an existing CUDA kernel faster with no operator-specific knowledge and no faster implementation to imitate: a general-purpose coding agent, a minimal harness that enforces a verifiable goal, and questions at decision points, first from a human, then from a bank the agent applies to itself. On the same task, evaluator, hardware, and week, a tool-rich autonomous agent built in the prevailing style plateaued at 0.50x FlashAttention-3 after 133 model-driven steps; KernelSeek reached 1.13x. It then produced dependency-free FlashAttention forward kernels for Hopper and Blackwell, single CUDA files with no CUTLASS, CuTe, cuBLAS, or cuDNN, correct on all 182 scenarios per architecture and 1.16x FlashAttention-3 and 1.46x FlashAttention-4 (geometric mean). Across 162 human messages and 11.5K agent tool calls, every large gain followed a question that moved the agent to a different layer of the system or rejected a claimed limit, never one that supplied information. We release the kernels, harness, question bank, and all traces.

arXiv AI Papershace 10 días

Online Label-Free Gradient Matching for Continual Language Model Training

Language models in customer-facing products must be continually updated, since the data they serve shifts over time. As retraining on the full accumulated data is impractical, each update should instead run on a small set of examples carrying the training signal of all data seen so far. The strongest current methods build this set by gradient matching, which synthesizes examples whose training gradients match those of the full data. However, they require ground-truth labels, run once on a fixed snapshot rather than on a growing stream, and are slow on large data. We introduce OLGA, which lifts these limitations. It distills unlabeled data by drawing the gradient matching targets from the model's own next-token predictions. Across five text classification benchmarks with phi-1.5, it improves accuracy by 10 percentage points over the strongest selection baseline using as few as five examples. OLGA also distills online data streams by keeping a running rehearsal memory of synthetic examples, which is re-distilled together with each new batch as it arrives. In the online setting, it outperforms the strongest selection-based continual baseline by 6.6 stream-AUC percentage points. Finally, our method scales to large data by pairing distillation with selection in a hybrid pipeline, letting selection handle the mild stage of compression and distillation the extreme one. It cuts runtime by 30\% versus distillation alone at similar accuracy, and beats the best selection-only pipeline by up to 12.6 percentage points.

AWS Machine Learning Bloghace 10 días

Agentic engineering intelligence with Amazon Nova Multimodal Embeddings and Amazon Bedrock AgentCore

Learn how to build a multi-agent engineering assistant that compresses aerospace component substitution evaluation from days to minutes, using Amazon Nova Multimodal Embeddings, Amazon Bedrock AgentCore, and the Strands Agents SDK to assemble substitution evidence while keeping the engineer as the decision-maker.

arXiv AI Papershace 10 días

Controlling Sharpening in LLM Post-Training

LLM post-training via reinforcement learning has shown consistent improvements in accuracy at the cost of reducing behavioral coverage - a phenomenon known as sharpening that can stall progress on difficult tasks. Repeated sampling objectives such as pass@k and max@k are known to mitigate sharpening, but the mechanism behind it remains poorly understood. Moreover, existing approaches for @k optimization use dedicated algorithms, and no general framework exists for adapting established policy optimization methods from @1 to @k. We derive the optimal policies for KL-regularized pass@k and max@k objectives in closed form. Our explicit solutions reveal that @k optimization naturally redistributes learning pressure based on prompt difficulty, directing it toward harder problems. Crucially, we show that standard @1 objectives achieve these exact same optimal policies through prompt-adaptive regularization or reward transformation. Ultimately, this yields an optimizer-independent explanation for why @k objectives reduce sharpening on easy tasks while prioritizing success on harder ones. Building on these insights, we introduce @k Adaptive Pressure for Policy Optimization (KAPPO). Following a one-time reference calibration, KAPPO seamlessly adapts existing @1 methods to @k via prompt-adaptive regularization or reward transformation, without otherwise altering their training procedures. Experiments with several RL methods on mathematical reasoning and code generation demonstrate that KAPPO provides direct control over sharpening. Crucially, we demonstrate that @k pressure can be fully realized with single completion training, matching the performance of multi-completion @k optimizers at a fraction of the cost.

arXiv AI Papershace 10 días

DepthGraft: Structural Regularization through Hierarchical Cross-Layer KV Reconstruction

Scaling depth is a key route to stronger large language models, but Pre-LN architectures often suffer from depth-wise information dilution, limiting the effective use of deep layers. While cross-layer connectivity has proven effective at mitigating this problem, existing designs usually introduce additional computation or memory access. We revisit cross-layer KV sharing as an efficient form of such connectivity. Beyond cache compression, each KV reuse edge creates a direct gradient path from deep layers to source KV projections, turning KV sharing into an implicit structural regularizer for KV representation geometry. We provide a systematic analysis of this mechanism, showing that proper sharing topologies sharpen key retrieval directions while enriching the value content subspace, whereas existing adjacent or global-anchor designs do not fully exploit this effect. Motivated by this, we propose DepthGraft, a hierarchical KV-sharing architecture that reconstructs deep-layer KV from stride-aligned shallow-middle source pairs. DepthGraft distributes non-local gradient flow across source layers, while preserving prefill early completion and reducing KV cache by roughly one third. Experiments on dense and MoE models from 0.5B to 16B parameters show consistent downstream improvements under both GQA and MLA. Notably, on the 16B MoE model, DepthGraft achieves a 7.0% absolute improvement on MMLU-Pro, along with gains of 6.6% on CMMLU and 6.4% on C3. These results validate the potential of DepthGraft as a scalable design for large-scale pretraining. The project page is available at https://github.com/jianke0604/DepthGraft.

arXiv AI Papershace 10 días

From Local Skills to Long-Horizon Web Tasks: Progressive Skill Exploration for LLM Web Agents

Large language models (LLMs) are driving autonomous agents toward real-world environments, with the Web emerging as one of the most representative interaction scenarios. However, training Web agents with naive exploration remains challenging: successful trajectories are rare, and the sparse terminal rewards make it difficult for agents to obtain useful feedback from failed trajectories. Inspired by skill acquisition theory, we propose Skill-Composed Progressive Exploration (SCOPE), a short-to-long learning framework for long-horizon Web agents that decomposes complex task exploration into a gradual expansion process from local skills to complete task-solving capability. Specifically, SCOPE iteratively explores around local skills: Skill Discovery extracts reusable local skills and failure experiences from historical rollouts; Skill Orchestration composes discovered skills into high-level skill chains; and Skill Expansion leverages failure experiences aligned with the current skill chain to guide the agent toward exploring new subskills. Through this process, SCOPE progressively constructs task-completing skill chains across rollouts and internalizes them into the policy parameters through agentic on-policy distillation. Extensive experiments on WebArena, WebVoyager, and WebShop show that SCOPE consistently improves exploration dynamics and achieves 3.9% to 18.6% relative gains over the strongest baselines in each setting.

arXiv AI Papershace 10 días

Preprocessing Choices in Fine-Tuning Data Matter: Utility and Demographic Sensitivity in LLM-Based Recommendation

Large language models (LLMs) have introduced a generative approach to recommendation, producing item lists from textual representations of user histories and item information. However, this generative setting raises challenges concerning output validity, prompt consistency, and sensitivity to demographic descriptors. In this work, we investigate how preprocessing choices in fine-tuning data affect recommendation utility and fairness-related behavior in a generative LLM-based recommender system. We first establish a controlled recommendation pipeline that combines supervised fine-tuning, catalog-constrained decoding, and prompt augmentation. We then study three preprocessing choices: item-title representation, demographic balancing, and auxiliary item-knowledge enrichment. Experiments on MovieLens-1M show that the catalog-constrained pipeline eliminates out-of-catalog items and ensures complete ten-item outputs, while prompt augmentation improves prompt consistency and utility. Original MovieLens titles increase HR@10 from 10.67% to 12.47% and Coverage@10 from 41.36% to 47.88%. Fairness-related effects are attribute-dependent: age balancing and knowledge enrichment reduce selected group-level utility gaps while largely preserving utility, whereas gender balancing reduces utility without improving the evaluated gender-related indicators. Overall, preprocessing choices in fine-tuning data should be evaluated jointly in terms of utility, output behavior, and demographic sensitivity.

arXiv AI Papershace 10 días

Diagonal Equivalence in State Space Models: Characterization, Retrieval Rank, and Selective Extensions

We classify real and complex state-space models (SSMs) with linear transitions, distinguishing fixed-basis diagonal equivalence from input-output equivalence and tracking coefficient-conditioning windows under coordinate changes. We characterize diagonal equivalence through commuting transition families whose members are diagonalizable over the chosen field. With time-shared token-local matrix maps, we identify this class's state-mediated kernels with unnormalized scalar-mode linear attention with multiplicative masks. Mamba 3's multiple-input, multiple-output (MIMO) construction lifts one value per local interface; SSD-MIMO routes independent values for local retrieval rank above one. HybridMamba combines Mamba 1's per-coordinate decay, Mamba 2-style heads and Mamba 3's complex rotations and two-endpoint writes, mixing real and rotating state blocks with different decay laws. They recover Mamba 1-3 single-input, single-output (SISO) configurations as exact special cases. On five large H100 bfloat16 workloads, our fused GPU kernels improve geometric-mean training time over official Mamba 1/3 in matched SISO recoveries, with Mamba 2 near parity at SSM-core scope. Memory tradeoffs depend on the baseline and metric: saved-for-backward versus peak allocation. In small-model multi-token recall experiments, both designs outperform Mamba 1-3 on the hardest tier; higher routing ranks perform best in gated or phase-diverse configurations. In single-seed language models with about 500M parameters, both improve on Mamba 1/2 in test loss at 2B tokens, but the routing gains do not translate into lower language-model loss. Our best configurations approach Mamba 3 SISO through 10B tokens while remaining behind it and Mamba 3 MIMO in language-model loss.

arXiv AI Papershace 10 días

DR Pixel: Page-Native Deep Research with Vision-Language Models

Complex documents such as scientific papers contain rich information in tables, figures, and equations; however, existing deep research (DR) agents typically reduce papers to OCR-extracted text. We instead ask whether vision-language models (VLMs) can enable page-native deep research: directly retrieving and reasoning over rendered document page images. We introduce DR Pixel, the first open-source end-to-end multimodal DR agent that uses rendered page images as its sole retrieval and reasoning unit, operating over a corpus of 1.06M pages. To evaluate this setting, we construct DRPixelBench, a benchmark on scientific papers requiring reasoning over text, figures, tables, and equations. Surprisingly, page-native DR already works well without training, outperforming OCR-based baselines across state-of-the-art models like GPT-5.4, Gemini-3.5-Flash, and Qwen3.6-27B, while requiring fewer tool calls. We next turn to DR training. A key challenge is that teacher trajectories for agentic supervised finetuning are noisy, mixing critical reasoning and action steps with redundant or failed attempts. To address this, we introduce counterfactual credit reweighting, a fine-grained credit assignment method that weights individual reasoning and action steps by their counterfactual contribution to the final answer. Our training improves retrieval recall by about 15 points and final accuracy by over 10 points on DRPixelBench, and likewise outperforms the untrained baseline on four existing benchmarks. On out-of-distribution ViDoRe-V3, DR Pixel comes within 1.8 points of an oracle that is given the gold pages directly. Our results suggest that the conventional OCR-then-retrieve pipeline is not only unnecessary but suboptimal: directly retrieving and reasoning over visual document pages makes complex DR both more effective and more efficient.

arXiv AI Papershace 10 días

A Fine-Grained Hierarchy and Benchmark for State Tracking in Language Models

Theoretical limitations of transformers on state tracking---the ability to track information about entities or variables over long contexts---have motivated new recurrent language modeling (LM) architectures such as Gated DeltaNet (GDN). These architectures have, in particular, been benchmarked against the S_5 word problem, a theoretically hard state-tracking task that captures abilities such as code evaluation under arbitrary variable assignment. It, however, remains open whether other, simpler forms of state tracking might both be more relevant in practice and already explain observed differences between these architectures. We propose evaluating state tracking using a hierarchy of word problems with four increasing levels of difficulty: r-trivial, corresponding to immutable assignment to variables in programming; aperiodic, where assignments are mutable; soluble, where assignments are self-referential; and general finite state tracking. Theoretically, we show that the class of problems transformers are thought to length-generalize on does not even contain all aperiodic state tracking. On the other hand, we prove that GDN with positive eigenvalues expresses all aperiodic problems, and the regular languages recognized by certain transformers are precisely all soluble ones, thus providing a fine-grained picture of state tracking capabilities of various architectures. Taking these ideas to practice, we construct StateBench, a 4-tier long-horizon state-tracking benchmark. Our systematic direct training experiments across architectures largely align with theoretical expectation, albeit with interesting observations at very large scale length-generalization. Additionally, we also evaluate pretrained models---both open hybrid and closed frontier ones---on StateBench, finding that none of them robustly solves even soluble state tracking, suggesting a direction for future improvement.

arXiv AI Papershace 10 días

An Experimental Study of Hybrid Retrieval, NLI and Open-source LLMs for Scientific Claim Verification

Claim verification is the task of deciding whether a source text supports a claim, contradicts it, or lacks sufficient evidence. Natural Language Inference (NLI) models can judge whether a single sentence supports or contradicts a claim, but they struggle when the evidence is spread across several sentences. Conversely, Large Language Models (LLMs) can reason across sentences, but may draw conclusions the text does not support. In this experimental study, we test whether a conservative fusion rule, labeling a claim Support or Contradict only when both models agree and defaulting to Not Enough Evidence otherwise, combines their strengths. We construct a benchmark of 2,035 claims from SciFact and CliniFact (858 Support, 152 Contradict, 1,025 Not Enough Evidence). We retrieve the top five most relevant sentences per claim using a hybrid of semantic and lexical (BM25) retrieval, which slightly outperforms either method alone. These retrieved sentences are then provided to every verification model. We then compare a DeBERTa-v3-base-mnli-fever-anli NLI baseline against Llama 3.1 8B, Qwen3 8B, and Mistral 7B. Qwen3 achieves the highest Macro-F1 (0.7937), followed by Llama 3.1 (0.7204) and Mistral (0.6388), while the NLI baseline reaches only 0.3157. Contrary to our hypothesis, fusion degrades performance, dropping Macro-F1 to 0.7392, 0.6730, and 0.5991, respectively. To understand this decline, we analyze agreements, disagreements, and common error patterns between the NLI and LLM verifiers. Our error analysis shows that NLI and LLM disagreements often result in correct LLM predictions being overturned.

arXiv AI Papershace 10 días

PACERec: Progressive Adaptation of LLM Item Embeddings with Collaborative Evidence for Recommendation

Large language model (LLM) embeddings have been increasingly adopted in sequential recommendation to encode static item attributes and alleviate the limitations of item ID embeddings under sparse interactions. However, these embeddings typically capture only static content similarity while neglecting sequential transitions, and since their adaptation quality relies on sparse per-item updates or global geometric calibration, existing methods still struggle to explicitly transfer preceding interaction contexts from frequent to long-tail items under unevenly distributed behavioral evidence, limiting recommendation effectiveness across the catalog. To address this challenge, we propose PACERec, an ID-free progressive adaptation framework that incorporates preceding interaction contexts into semantic representation adaptation by learning a shared velocity field from items with sufficient interactions via frequency-weighted flow matching. In this way, PACERec progressively guides static LLM embeddings toward collaborative behavioral targets while preserving original item semantics, overcoming sparse per-item updates to effectively generalize sequential transition patterns to long-tail items for both user modeling and candidate scoring. Extensive experiments on three real-world datasets across three sequential backbones demonstrate the superiority of our method over competitive baselines in both overall and long-tail recommendation.

arXiv AI Papershace 10 días

Towards a Trustworthy and Governable Internet of Agentics: An Architectural Perspective on Protocols, Systems, and Services

Large language model applications are increasingly being organized as tool-using and multi-agent workflows rather than as isolated chat interfaces. This perspective paper examines the architectural problem that follows from that shift: agents may reason, invoke tools, and delegate work, but dependable deployment still requires interoperability across frameworks, runtimes, data boundaries, and organizational control domains. We study this problem through the lens of the Internet of Agentics (IoA), an emerging service-computing view in which heterogeneous agents are treated as governable service participants rather than only as stand-alone model endpoints. The paper organizes the landscape as a three-layer progression: from today's fragmented agent ecosystem, to interoperable agents, and ultimately to trustworthy and governable autonomy. First, it examines the protocol stack centered on the Agentic AI Foundation, including MCP for agent--tool interaction; A2A for agent--agent coordination; AGENTS.md and Skills-style procedural manifests; and discovery, transport, and trust mechanisms such as AGNTCY and SLIM. Second, it reviews the systems abstractions that make agents deployable as service components, including logical agent architectures, orchestration patterns, gateways, registries, runtime control loops, and hardware-aware inference infrastructure. Third, it situates these developments within services computing, arguing that agentic systems reinterpret classical concerns from SOA and microservices---discovery, composition, governance, pricing, and trust---at the level of cognitive capabilities rather than deterministic functions.

arXiv AI Papershace 10 días

PRIME: Predictive Routing of Interventions by Modeling Effects for Scientific Ideation

Feedback-driven iteration is widely used to improve LLM-generated scientific ideas, but existing systems either leave revision decisions implicit in generation, align revisions with feedback-localized weaknesses, or restrict action selection to system-specific operations. This is problematic because problems, hypotheses, and solutions are interdependent: the location where a weakness manifests does not itself determine the revision scope that will produce a better successor. We term this phenomenon diagnosis-intervention mismatch. We introduce Predictive Routing of Interventions by Modeling Effects (PRIME), a plug-and-play feedback-to-revision decision layer for existing scientific ideators. PRIME operates in three stages: (1) Structural Attribution interprets feedback over the problem-hypothesis-solution structure without fixing a revision target; (2) Counterfactual Routing constructs alternative scope-conditioned interventions and compares their projected successor utility and risks through lightweight rollouts; and (3) Intervention Execution compiles the selected intervention into an ordered generator-facing plan with semantic actions, preservation constraints, and dependency requirements for successor generation. We validate diagnosis intervention mismatch on 112 human-annotated idea-feedback pairs. Across four benchmarks, two ideators, and fixed- and open-problem settings, PRIME improves successor quality and routing reliability over strong baselines; removing counterfactual routing reduces quality from 3.463 to 1.960 and increases route regret from 0.426 to 1.929, confirming cross-scope effect modeling as the primary source of its gains.