paperlist.ai

AI conference papers

AI conference paper library

Search papers from 30+ top conferences, including NeurIPS, ICLR, ICML, CVPR, ACL and AAAI. Filter by keyword, then open any paper for its abstract, authors and links.

arXiv

AI Playing Business Games: Benchmarking Large Language Models on Managerial Decision-Making in Dynamic Simulations

Berdymyrat Ovezmyradov

The rapid advancement of LLMs sparked significant interest in their potential to augment or automate managerial functions. One of the most recent trends in AI benchmarking is performance of Large Language Models (LLMs) over longer time horizons. While LLMs excel at tasks involving natural language and pattern recognition, their capabilities in multi-step, strategic business decision-making remain largely unexplored. Few studies demonstrated how results can be different from benchmarks in short-term tasks, as Vending-Bench revealed. Meanwhile, there is a shortage of alternative benchmarks for long-term coherence. This research analyses a novel benchmark using a business game for the decision making in business. The research contributes to the recent literature on AI by proposing a reproducible, open-access management simulator to the research community for LLM benchmarking. This novel framework is used for evaluating the performance of five leading LLMs available in free online interface: Gemini, ChatGPT, Meta AI, Mistral AI, and Grok. LLM makes decisions for a simulated retail company. A dynamic, month-by-month management simulation provides transparently in spreadsheet model as experimental environment. In each of twelve months, the LLMs are provided with a structured prompt containing a full business report from the previous period and are tasked with making key strategic decisions: pricing, order size, marketing budget, hiring, dismissal, loans, training expense, R&D expense, sales forecast, income forecast The methodology is designed to compare the LLMs on quantitative metrics: profit, revenue, and market share, and other KPIs. LLM decisions are analyzed in their strategic coherence, adaptability to market changes, and the rationale provided for their decisions. This approach allows to move beyond simple performance metrics for assessment of the long-term decision-making.

arXiv

Revisiting Black-Box Model Ownership Verification through Information Theory

Aoting Hu, Yanzhi Chen, Renjie Xie, Xinwei Zhang, Wei Xu

Modern machine learning models require substantial computational resources and data to train, making them valuable intellectual property. Model watermarking has emerged as a practical solution for black-box ownership verification, but existing methods suffer from a persistent trade-off between robustness and predictive utility. In this work, we analyze this limitation from an information-theoretic perspective and identify a fundamental capacity crisis: relying solely on predicted labels provides insufficient capacity to embed robust ownership signals without degrading accuracy. To deal with it, we propose a new black-box ownership verification framework that leverages the top-k output. By exploiting this richer output space, our approach increases the effective capacity available for watermarking while preserving predictive performance. Extensive experiments across image, text, and tabular domains demonstrate that our method achieves a more favorable robustness--utility trade-off than existing approaches, while remaining practical for real-world deployment.

arXiv

CoPlan: A Trustworthy Co-Intelligence Interface for Care Planning through Role-Based Contestable Argument Graphs

Hung Truong Thanh Nguyen, Hélène Fournier, Piper Jackson, Makoto Itoh, Shannon Freeman, Rene Richard, Hung Cao

AI-supported care planning can help clinicians, patients, caregivers, and care teams coordinate complex decisions across clinical, functional, psychosocial, and environmental needs. However, many AI systems present recommendations as fixed outputs, limiting stakeholders' ability to inspect, challenge, and revise plans when they conflict with clinical judgment, patient values, or real-world feasibility. We present CoPlan - a Co-Intelligent and Contestable Interface for Human-AI Care Planning. CoPlan uses a multi-agent workflow in which specialized AI agents generate candidate interventions and supporting or challenging arguments, while human care planners can accept, reject, modify, or add arguments before final plan generation. Through this design, CoPlan combines co-intelligence, in which humans and AI agents contribute complementary expertise, with contestability, where recommendations remain open to inspection, revision, and justification. We demonstrate CoPlan in an aging-in-place care planning scenario. The system supports adaptive care team recruitment, role-based argument review, final care plan generation, and practical follow-up through scheduling agents. This work contributes a contestable care planning interface and a design framing for trustworthy human-AI care planning that preserves human agency and clinical accountability.

arXiv

ABSeeker: Training Long-Horizon Search Agents via Answer-Backtracked Credit Assignment

Yijun Lu, Rui Ye, Jiajun Wang, Yuwen Du, Tian Jin, Songhua Liu, Siheng Chen

Long-horizon search agents must make multiple sequential actions (steps) to search, retrieve, verify, and integrate evidence to reach a final answer. However, existing methods for training these agents typically treat all steps within a trajectory uniformly during both supervised fine-tuning (SFT) and reinforcement learning (RL), failing to distinguish useful actions from erroneous or redundant ones. In this paper, we propose Answer-Backtracked Credit Assignment (ABC), a fine-grained credit assignment framework for training long-horizon search agents by converting sparse trajectory-level outcomes into dense step-level supervision that rewards useful actions (even in failed trajectories) while suppressing erroneous or redundant actions. Specifically, given a potentially obscure query and its corresponding ground-truth answer, ABC first performs Answer-Backtracked Clue Recovery, which traces back from the answer to recover intermediate clues required to solve the question. It then applies Clue-Anchored Step Scoring to evaluate each search step against these clues, converting sparse binary outcome supervision into dense step-level rewards. Based on these rewards, we develop ABC-SFT, which reweights the loss of each turn, and ABC-GRPO, which uses the step-level scores as rewards in GRPO. Building on this framework, we train ABSeeker based on Qwen3.5-4B with only 8.5k examples. ABSeeker achieves 37.3% on BrowseComp and 39.1% on BrowseComp-ZH. With context management, the scores further improve to 55.3% and 52.9%, respectively, significantly outperforming same-scale (4B) agents and even matching the performance of larger ones (approximately 30B). These results demonstrate the effectiveness of answer-backtracked step-level credit assignment for training long-horizon search agents.

arXiv

Hierarchical Graph Memory for LLM Agents with Path-level Localization and Rewrite

Xiawei Yue, Boran Wang, Xiaoqing Zhang, Shuxin Zheng, Ziwei Zhang

Agents for long term reasoning require a memory that can be efficiently and effectively updated over time, as new facts and external feedback continue to arrive. Recently, graph memory has been adopted to offer structural organization for multi-hop retrieval and reasoning. However, existing methods store all memories in a flat graph, and accumulated historical memories can introduce irrelevant contexts and increase the cost of evidence selection during retrieval. Moreover, they typically update memory units independently, requiring repeated unit-wise rewrite to cover related changes. To address these issues, we propose HiGram, an evolving hierarchical graph memory framework with path-level localization and rewriting. Specifically, we first propose a hierarchical graph memory, which organizes the memory into coarse-to-fine architecture composed of upper-level nodes and MemoryUnits, thereby reducing the amount of irrelevant information during retrieval. We further propose MicroGraph-based path-level localization, which leverages query and update conditioned MicroGraphs to identify support subgraph and evidence path before rewrite. Finally, we propose a coordinated rewriting method that jointly revises intra-unit memory and inter-unit dependencies, enable valid dependency structures updating in the localized evidence path. Experiments on benchmarks for long-term conversational question answering and conflict-aware memory evaluation demonstrate that our method demonstrate substantial improvements over baselines in answer quality and token efficiency. Besides, our method improves answer accuracy and query-valid evidence selection under dynamic, static, and conditional conflicts.

arXiv

Hardware Design and Security in the Era of Chiplets and LLMs

Johann Knechtel, Ozgur Sinanoglu, Paul V. Gratz, Ramesh Karri

The semiconductor industry is undergoing a dual revolution: the shift toward heterogeneous 2.5D chiplet systems and the integration of Large Language Models (LLMs) into Electronic Design Automation (EDA) flows. While these paradigms offer unprecedented benefits in yield, modularity, design productivity, etc., they radically expand the hardware attack surface. This paper provides a unified analysis of these frontiers, ranging from attacks on chiplet systems (including hardware stacks for LLM acceleration) across architectural, logical, and physical levels, to various exploits against LLM-driven EDA pipelines. To secure chiplet systems, we review a powerful defense approach that leverages 2.5D split manufacturing and active interposers for physically isolated Root of Trust (RoT) architectures. To secure LLM-driven EDA pipelines, we first identify native threats and then review state-of-the-art defense techniques. Finally, we discuss how LLM systems can advance hardware security efforts for modern systems, including chiplets.

arXiv

RepairFormer: Automated Repair of Structured Inputs Using Transformers

Ovi Paul, Tom J King, Ali Shokri

Structured input files such as JSON, DOT, OBJ, INI, S-expression, and TinyC are widely used in software systems, but small corruptions can cause parsers to reject otherwise useful data. Repairing such inputs is important because malformed configuration, program, and data files can interrupt testing, analysis, deployment, and downstream automation even when most of the original content remains intact. Existing repair techniques can produce structurally valid inputs, but they often rely on deletion or repeated search, which may lose original content and result in semantic incorrectness. This paper presents RepairFormer, a transformer-based framework for structured input repair. The approach formulates repair as a supervised sequence generation task and uses format tags, oracle validation, and boundary-localized repair to generate valid outputs while preserving content. The boundary workflow focuses generation on the detected fault region, reducing the input size, and supporting repair of longer files. In evaluation, RepairFormer achieves a 88% in repair and 94% in recovery, showing strongest content preservation when repairs are successful. Additional experiments on our benchmark shows RepairFormer repairs 97.57% and recovers 94.29% with 5x faster runtime compared to state of the art.

arXiv

From Score Matrices to Football-Aware Match-State Simulation: An Auditable LLM Harness for Exact-Score Reranking

Shaopeng Liang

Football score forecasting combines a strong statistical core with a difficult contextual edge. Dynamic Poisson-family models estimate team strength, expected goals, and coherent score probabilities, but do not directly understand roles, tactical matchups, motivation, or how a first goal changes behaviour. Large language models (LLMs) can reason about such concepts, yet are not calibrated probability engines. We combine both components through an auditable information harness. This paper documents four iterations: V1, a dynamic score-driven Dixon-Coles baseline; V2, which maps LLM contextual ratings back into expected-goal parameters; V3, which replaces scalar correction with goal-by-goal simulations over a frozen score-candidate set; and V4, which adds shared first-breakthrough and post-goal cascade judgments, time-aware stopping, and deterministic tail candidates. The harness defines input semantics, supplies pre-match evidence, and constrains the LLM to an inspectable reasoning route. On a chronological replay of the first 150 matches of the 2025-26 English Premier League, V1 achieved 10.0% Top-1 and 26.7% Top-3 exact-score accuracy. V3 reached 12.0% and 30.0%, while V4 reached 14.7% and 30.7%. V4 increased candidate coverage from 77.3% to 84.7%, although no added tail candidate became a Top-3 exact hit. V1's native 1X2 distribution achieved 53.3% argmax accuracy, 0.9878 log loss, 0.5870 Brier score, and 0.2095 ranked probability score. These results are exploratory: the development slice is not an untouched benchmark, and temporal input isolation cannot exclude outcome memory in a closed LLM. The contribution is an auditable hybrid architecture, a clear design evolution, and negative findings showing where football-aware simulation does and does not improve score selection.

arXiv

ArtAnno: Annotating Implicit Semantics in Artworks through LLM Agent-Driven Bidirectional Human-AI Augmentation

Xiaoyan Gu, Yifang Wang, Wenqing Zheng, Haozhong Liu, Yixia Zheng, Peiyi Jiang, Wenjie Ning, Wei Zhang, Wei Chen

High-quality annotation of artworks is essential for computational art research, yet extracting implicit semantics remains challenging due to the reliance on culturally grounded meanings and deep contextual knowledge behind the images. Current AI-assisted annotation tools often lack assistance or rely on one-way workflows where experts have to perform extra manual calibrations to improve AI models, resulting in limited efficiency. To address this, we propose Bidirectional Human-AI Augmentation(BiHAA), a closed-loop framework in which skills and domain knowledge base evolve through real-time interaction and bidirectional HAI augmentation. Informed by a formative study with 20 artwork annotators from different backgrounds, we implement this framework in ArtAnno, an artwork annotation system driven by a multi-agent architecture. The system includes a Proactive Agentic Support Module, where AI augments humans through semantic mining and label suggestion, and an Interaction-Driven Evolution Module, where human expertise continuously enhances the AI through distilling annotation trajectories into reusable experience. Evaluation through a user study and two case studies demonstrates that our framework and system improve annotation efficiency, enable knowledge accumulation, and reduce the effort of information seeking and verification for annotators with limited domain expertise. We conclude by discussing broader implications and future directions.

arXiv

ORACLE: A Multi-Objective Reinforcement Learning-Based Analog Circuit Design Optimizer with Large Language Models-Guided Exploration

Osei Brempong, Mohammed Ayman Habib, Vivan Poddar, Morteza Fayazi

Analog circuit design automation using reinforcement learning (RL) has emerged as a promising approach for reducing manual effort. However, many existing RL-based methods focus on single-objective optimization. Even methods designed for multi-objective (MO) problems often reduce multiple design specifications to a single scalar reward. This simplification limits the ability to capture the true Pareto trade-off among competing objectives and often leads to suboptimal designs. Moreover, requiring the model to be retrained from scratch whenever the desired MO specifications change remains a key limitation. To address these challenges, we present ORACLE, an open-source RL-based framework for MO analog circuit design optimization that replaces scalar reward optimization with vector-valued learning and preference-aware conditioning. ORACLE represents a true MO analog circuit design optimizer that uses a preference vector to specify the relative weights of multiple objectives, enabling a single trained model to generate designs across diverse trade-off settings without retraining. We further propose two preference-guidance strategies, namely normalized-weight guidance and cosine-aligned guidance, to improve convergence. In addition, we incorporate a large language model (LLM)-guided action selection mechanism to filter actions that are likely to lead to suboptimal designs or increased runtime. Our results show that, on multiple circuit topologies with 2,000 test cases, ORACLE reduces runtime by 20.4x - 104.4x compared to state-of-the-art approaches. It also meets 99.9% of the 2,000 target specifications, and achieves 5.1x - 318.6x better figure of merit in the resulting output specs.

arXiv

SciCode-Verified: How Benchmark Defects Underestimated the Scientific-Coding Ability of Language Models

Sihan Hu, Lyuhan Huang, Youjin Deng, Kun Chen

SciCode is the standard measure of the scientific-coding ability of language models: research-level problems that demand both frontier scientific theory and its implementation as working numerical code. It is a component of the Artificial Analysis Intelligence Index and a standing evaluation in government and national-laboratory suites. Yet its scores have recently plateaued: the strongest 2026 models cluster tightly around 60\% subproblem accuracy, and a successor model ties its predecessor. We trace this stagnation to defects in the benchmark itself. A per-problem, domain-expert audit of all 65 test problems uncovers 263 defects; 192 of them, spread across 91\% of the main problems, cause correct, instruction-following solutions to be wrongly rejected---through non-reproducible gold answers, over-tight tolerances, or self-contradictory specifications. Critically, 78\% of these score-suppressing defects require specialized physics or mathematics knowledge to detect, not mere clerical proofreading. We corrected every confirmable defect to produce SciCode-Verified. The corrections add only the specifications a well-posed problem requires, repair grading, and tighten the tests that were too lenient; every change is recorded with its justification and independently re-checked by a second domain expert. We re-evaluate twelve frontier model snapshots on the corrected benchmark and find a substantial recovery: subproblem accuracy rises from 45--60\% to 84--98\%, and main-problem accuracy from 9--27\% to 69--92\%. State-of-the-art models are far more proficient in scientific coding than SciCode has suggested---the bottleneck was not model capability, but the quality of the evaluation instrument. We release SciCode-Verified with its complete audit trail as the corrected public standard.

arXiv

A General Sufficient Condition for Rewriting Horn-ALCHI Atomic Queries into GQL

David Carral, Calixte Gruson, Quentin Manière

The emergence of the ISO standard GQL introduces a powerful query language extending first-order logic with controlled recursion, raising the question of its applicability to evaluation of ontology-mediated queries (OMQs). We focus on OMQs consisting of atomic queries over ontologies expressed in Horn-ALCHI, an expressive Description Logic that is not, in general, first-order rewritable. To address this, we introduce DL automata, a novel formalism that captures the semantics of such OMQs via runs over fact sets. We then identify a large class of DL automata that can be rewritten into unions of conjunctive two-way regular path queries (UC2RPQs), a central fragment of GQL. Our class of automata relies on a stratification of their states, ruling out specific forms of cyclic dependencies known to raise the complexity. This yields a broad class of Horn-ALCHI OMQs that are GQL-rewritable.

arXiv

A Chain Is Only as Strong as Its Weakest Link: A Scoping Review of System Integration Audits in AI

Leah Davis, Dominic Martin, AJung Moon

As AI systems become increasingly integrated into diverse interfaces and applications, model-centric audits are insufficient to address risks arising from interactions among system components and deployment environments. System integration has long been central to software audits in safety-critical domains such as aerospace. However, its role in AI auditing remains underexplored. Scanning through 4,259 documents, we present a scoping review of AI audits that treat system integration as a core tenet of evaluation (n = 58). Using reflexive thematic analysis, we analyze their elements, actors, enablers, and constraints. We find that the corpus represents an emerging yet still fragmented form of AI auditing: few existing measures target integration-specific risks; large gaps remain in meeting traditional audit expectations; and access to necessary information and resources significantly influences audit design. Nonetheless, integration can be categorized across three sites (inter-component, system-environment, and multi-system), each serving the functions of risk exploration, risk determination, coordination, and procedural regularity. Deviating from other types of evaluations, these audits assess qualities specific to system integration, including compatibility, completeness, and oversight. This review calls on the AI community to prioritize system integration as a core strategy for addressing AI risk, and to develop audit practices capable of capturing failures across components, environments, and systems beyond the reach of component-level evaluation.

arXiv

ContextWeave: A Real-World Workflow Benchmark

Bo Wang, Yuqian Yao, Enxi Wang, Luozhijie Jin, Yang Liu, Yiran Suo, Yuxuan Cai, Enyu Zhou, Yufei Gao, Honglin Guo, Tianyu Huai, Li Ji, Zhikai Lei, Bufan Li, Lizhi Lin, Jinxiu Liu, Jie Yang, Jiazheng Zhou, Maosen Zhou, Pengfang Qian, Shichun Liu, Guanshan Liu, Hao ZHENG, Yunhao Yu, Hang Yan, Jihua Kang, Xinchi Chen, Xipeng Qiu

Memory is essential as language agents move from isolated tasks to long-horizon, stateful workflows, yet existing evaluations often reduce it to retrieval or question answering. We introduce ContextWeave, a longitudinal benchmark that evaluates whether recalled experience improves downstream agent performance in realistic office-work streams. ContextWeave reconstructs privacy-preserved, multi-month workflows of 14 participants into 1,005 executable tasks, including 568 core evaluation tasks, with instructions, containerized environments, trajectories, and task-specific rubrics. It measures workspace quality and alignment with participant-specific preferences, complemented by diagnostics of relevance, continuity, solvability, and robustness to misleading recall. Across six memory components under a fixed model, the strongest configuration raises Workspace Score from 68.08 to 78.20 and Preference Score from 41.50 to 70.60. With a fixed memory component, recall improves both outcomes for all five tested base models, although gains vary substantially. Our analysis shows that actionable, experience-rich memory supports workflow continuation and reduces redundant exploration more effectively than compact summaries, while it can also be more susceptible to misleading recall. These findings motivate memory systems that optimize not only retrieval relevance but also reliable use during execution.

arXiv

Scrouting: Cost-Aware Routing of Coding Agents by Scouting the Repository First

Ishaan Bhola, Adithyan Krishnan, Mukunda NS

Frontier language models can resolve repository-level software issues, but each attempt is expensive, and existing routers select a model from the issue text alone. We present SuperScout, which routes after scouting the repository: a 7B searcher, SuperScout-7B, first explores the repository and produces a structured handoff whose reproduction claims are sandbox-verified, with false claims stripped before delivery. The searcher's hidden states, together with the task text, then feed a resume-based router that dispatches the task to one of four frontier fixers. Adding a new fixer requires no retraining. On the full Python slice of SWE-bench Pro (266 tasks) under the benchmark's official capped budget tier, SuperScout matches the best single model's solve rate (159 of 266 for SuperScout, 158 for the best model) at about a fifth of the total cost per solve, and the reported configuration sits above the random traffic-splitting baseline. A no-router ablation, always the cheapest fixer with the handoff, ties the routed system on this benchmark, so the handoff rather than the routing decision carries the result. A paired calibration study points to the mechanism: the handoff appears to redistribute rather than add solving ability, lifting the three cheaper fixers while slightly hurting the strongest, though at $N=99$ the per-fixer effects are directional only; the searcher's hidden states improve cost routing on the calibration labels while the handoff's own text does not. The searcher's compute adds less than half a cent of GPU time per task.

arXiv

NSF-HRPT: Neural Semantic Field meets Hierarchical Risk Perception Tree for Safety-Critical Scenario Assessment

Yu Zhao, Jiangyu Pan, Tao Hu, Ming Yin, Fan Yang, Jiangfan Liu, Xiubo Liang

The ability to accurately assess and anticipate risks in safety-critical scenarios is crucial for autonomous driving systems. While existing research has made progress in collision prediction, accurately quantifying risk levels from monocular vision inputs remains challenging due to the complex dynamics of multi-agent interactions and the inherent uncertainty in real-world environments. To address these challenges, we present NSF-HRPT, a novel framework that combines learning-based perception with structured reasoning for quantitative risk assessment. Our approach features a Neural Semantic Field (NSF) that learns to model scene semantics, trajectory predictions, and probabilistic Time-to-Collision (TTC) distributions from simulation data. During inference, the pre-trained NSF serves as a prior for our Hierarchical Risk Perception Tree (HRPT), which enables efficient parallel computation and spatial reasoning about multi-agent risks. Additionally, we introduce a Sim2Real enhancement strategy that improves real-world applicability without retraining by incorporating priors from foundation models. Extensive evaluations demonstrate that our framework achieves state-of-the-art performance on synthetic benchmarks and delivers competitive, near-state-of-the-art results on real-world datasets for both TTC estimation accuracy and risk localization precision. The proposed method provides an effective solution for real-time risk awareness from monocular camera inputs.

arXiv

Fewer Tokens, Smaller Cache: Reward-Coordinated Efficient Reasoning

Qiyuan Zhu, Dezhi Li, Pengyu Cheng, Tianle Chen, Jiacheng Wang, Ruijie Shen, Hao Gu, Sida Lin, Zirui Liu, Jiacheng Liu, Sirui Han

Large Reasoning Models (LRMs) excel on complex tasks through long chain-of-thought (CoT) reasoning, but their lengthy intermediate steps cause severe overthinking that inflates inference cost. KV-cache compression is a common solution, yet existing reasoning-oriented methods apply a uniform policy across the trajectory and judge compression only by what it removes from the cache. Two observations point the other way. First, a reasoning state's tolerance to context loss varies along the trajectory, and process reward tracks it: deleting tokens at high-reward steps preserves accuracy far better than deleting the same budget at random. Second, compression is not free on the generation side, since a smaller cache leads the model to generate more tokens, partly canceling the saving. Together these motivate coordinating both sides under a single process reward. We propose ReCo (Reward-Coordinated Compression), a step-wise framework in which a lightweight process-reward estimator scores each completed step and drives three components: (1) reward-adaptive KV-cache compression that shrinks the retained cache harder at high-reward steps and less at low-reward ones, (2) a reward-banded penalty on reflection tokens that curbs redundant generation, and (3) confidence-based early stopping that triggers when the reasoning is reliable. Across three reasoning models and six benchmarks, ReCo reduces generated tokens by 37%-65% and end-to-end latency by 2.08x-2.35x over Full CoT, all while largely preserving accuracy.

arXiv

PURPOSE: Poisoning Conflict Resolution in RAG via Proxy-Fact-Grounded Updates

Zijian Wang, Yubo Zhu, Muzhi Dong, Yanjun Lou, Yisheng Li, Ziliang Zhang, Wei Tong, Yuan Zhang, Jingyu Hua, Sheng Zhong

In Retrieval-Augmented Generation (RAG), post-retrieval conflict resolution arbitrates among noisy or contradictory retrieved passages. However, the robustness of this safeguard against knowledge poisoning has not been adequately studied. Existing black-box poisoning methods all assert the target answer in frontal contradiction with what the resolver treats as settled, the very signal these methods are built to detect. We propose PURPOSE, a strict black-box poisoning attack that reframes the injection as an update that minimizes conflict, rather than as a counter-claim. PURPOSE extracts query-related facts approximating the resolver's possible reference, then grounds a pivot event in them to keep the injection consistent with what the resolver might verify while steering the generator toward the target answer. Across three QA benchmarks, five generators, and three conflict-resolution methods, PURPOSE attains the highest attack success rate (ASR) in 35 of 45 settings and exceeds the strongest prior attack with +9.7 mean ASR points. These results show that our poisoning method is effective against conflict resolution in RAG and identify non-contradicting injection as a practical mode to enhance poisoning attack.

arXiv

Chain-of-Thought Monitoring Can Be Unreliable in Implicit-Influence Settings

Agatha Duzan, Asa Cooper Stickland

Chain-of-thought (CoT) monitoring is increasingly treated as an important safety layer for frontier reasoning models. Most monitorability evaluations study explicit-influence settings: setups where the prompt directly incentivizes the model to hide something, e.g., by instructing it to perform a hidden side-task. A complementary axis for CoT-monitor evaluations is implicit-influence settings, where the prompt contains no instruction to hide, but the model's behavior is still shaped by features of the task or context, e.g. an irrelevant detail about a candidate that biases a hiring rating. We introduce the first benchmark that directly compares CoT monitorability under the two regimes. We test how model behavior changes in the presence of a nudge to choose a particular option. The nudge is delivered either as a casual aside (implicit), or as a direct instruction to act on the nudge and to conceal having done so (explicit). The benchmark spans four task formats (binary choice, numeric rating, multiple-choice QA, open-ended coding) and seven frontier extended-thinking models. Under explicit influence, a CoT monitor detects 60-94% of behavior shifts: even models instructed to conceal it leak the instruction into their CoT. Under implicit influence, the same factors still shift behavior, but detection falls by 41-46 percentage points in two of our four settings. Realistic system-prompt additions (of the kind a developer might deploy to reduce off-topic bias) lower implicit detection further, to as low as 5%, while preserving the behavioral influence itself. These results suggest that monitorability estimates obtained in explicit-influence settings may over-estimate monitorability, and that monitorability can be further decreased by well-intentioned deployment choices. Our benchmark and code are available at https://github.com/agatha-duzan/implicit-vs-explicit-influence

arXiv

Toward Integrating Adaptive Experience Replay and Online Uncertainty Estimation in Safe Actor-Critic Optimal Control

Mahshad Rastegarmoghaddam, Davoud Nikkhouy, Shima Samadzadeh

Safe actor-critic control often treats barrier filtering, uncertainty estimation, and experience replay as separate modules, even though each changes the data used for learning and control. We develop an integrated architecture in which the uncertainty estimate updates the obstacle geometry used by a control barrier function, filter interventions and estimation residuals determine replay priority, and the critic learns from the executed rather than nominal action. We instantiate the architecture on a two-dimensional robot-navigation task with corrupted obstacle measurements and compare six component-matched configurations under common training budgets, random seeds, sensor streams, exploration, and disturbances. Evaluation includes a moderate post-training test, an eleven-level perception-noise sweep, and an exploratory extreme-stress test at multiplier $6.0$. In the extreme test, the integrated configuration recorded no contacts and reached the goal in all five evaluation seeds. Its mean cost was $7.63\pm0.44$ and its obstacle-belief root-mean-square error was $3.52\pm0.55$ cm. The uncertainty-estimation ablation also recorded no contacts but reached the goal in four of five seeds, with mean cost $8.96\pm2.08$ and belief error $11.08\pm1.23$ cm. A finite-training bound clarifies replay exposure, and a robust barrier condition states the required estimation-error and feasibility assumptions. The results support coupling estimation, safety filtering, and replay on this benchmark; broader safety and convergence claims require further study.

Keep browsing

More papers from top AI conferences

30+ top conferences, by conference, year, and topic.