Sign in

Author: DEROBS

  • Imitation Holds a Key to Evolution: Localized Repair and Verified Skill Acquisition for Adaptive Agents

    Imitation Holds a Key to Evolution: Localized Repair and Verified Skill Acquisition for Adaptive Agents

    Imitation Holds a Key to Evolution: Localized Repair and Verified Skill Acquisition for Adaptive Agents

    arXiv:2610.16125v1 Announce Type: new Abstract: An agent can retain successful trajectories without learning which part of an experience should repair a new discrepancy. We formulate passive imitation (PI) as an architectural loop that localizes a violated contract, extracts a local goal, proposes an effect-matched skill, tests a small patch, and retains evidence after full-task verification. We instantiate this loop as a deterministic symbolic controller and analyze its finite repair-query complexity under explicit identifiability and noninterference assumptions. Across ten simulated tool worlds, PI solves all 600 cold held-out composition tasks with three allowed small trials, compared with 6.17% for a whole-trajectory control, while an equally expressive compositional repair control matches PI. On an unseen tool revision, PI achieves 70.0% success versus 24.0% without small trials and 79.0% with self-trial enumeration; an exploratory 24-task adaptation stream subsequently raises first-submission success to 100%, supporting a limited correction-and-retention mechanism rather than a unique incentive advantage or general intelligence. The CPU-only implementation, integrity checks, and reproducible results are available at https://github.com/FriendOfYishan/PI.

    Fallback brief based on the available RSS feed; no unsupported details have been added.

    Source: arXiv
    Original article: https://arxiv.org/abs/2610.16125

  • Heterogeneous Agentic Coevolution

    Heterogeneous Agentic Coevolution

    Heterogeneous Agentic Coevolution

    arXiv:2610.16078v1 Announce Type: new Abstract: Recent advances in self-improving LLM agents have demonstrated the potential of AI systems that drive their own intelligence. However, many domain-specific applications rely on specialized foundation models that possess strong domain expertise but remain dependent on human-designed improvements. Extending recursive self-improvement to these models presents a key challenge: as a specialist improves, the strategies used to advance it must also adapt. To address this challenge, we propose Heterogeneous Agentic CoEvolution (HACE), a framework that jointly evolves specialized foundation models and LLM agents through reciprocal learning. HACE improves the specialist through supervised learning while training the agent with on-policy reinforced self-training, guided by verified performance gains on the current specialist. The agent's exploration, in turn, informs subsequent specialist training, enabling both models to adapt to each other's progress. To sustain this reciprocal learning, HACE further employs evolutionary search to optimize their interaction harness, adapting how the models exchange information and select training experiences as their capabilities evolve. We evaluate HACE across three challenging domains: recommendation systems, protein function prediction in biology, and crystal stability prediction in material discovery. We show that HACE outperforms the evaluated self-improving methods on the primary task metrics across all three domains. These results shed light on heterogeneous coevolution as a universal approach to improving specialized foundation models through reciprocal interaction with a learning agent.

    Fallback brief based on the available RSS feed; no unsupported details have been added.

    Source: arXiv
    Original article: https://arxiv.org/abs/2610.16078

  • The Sharp Directions Are Against You: Curvature Analysis of Activation Steering

    The Sharp Directions Are Against You: Curvature Analysis of Activation Steering

    The Sharp Directions Are Against You: Curvature Analysis of Activation Steering

    arXiv:2610.16084v1 Announce Type: new Abstract: Activation steering adds a vector to a language model's internal representations at inference time. It is a lightweight alternative to fine-tuning for behavioral control. The standard construction, contrastive activation addition (CAA), is fragile, as on many inputs it shifts behavior in the wrong direction. To explain this fragility, we first study the geometry of the steering vector. We introduce steering Hessian, the matrix of second order derivative of the model's behavioral loss with respect to the steering vector. It captures the output behavior response sensitivity of the model under small perturbations of the steering vector along each direction. Its top eigenvectors are sharp directions: tiny perturbations along them can cause large, erratic, input-dependent behavioral swings. Bottom eigenvectors are flat directions: behavior is robust along them. Removing the sharp component of a steering vector approximately preserves its direction and magnitude (cosine > 0.974, norm reduction < 3% for typical settings) while reducing the vector's directional curvature by up to 12x (median 4x across 36 conditions). We evaluate on three model families (Qwen2.5-7B, Llama-3.1-8B, Mistral-7B), with four behavioral tasks, and 36 token-level conditions. Steering along sharp directions reverses the intended behavior in every condition tested, with anti-steer rates of 53-100%. Sharp directions account for only 1-5% of the CAA vector's squared norm. However, they drive a disproportionate share of the gap between the steered and unsteered next-token distributions during autoregressive generation. We term this one-line correction as sharp removal; it outperforms standard CAA in open-ended generation across all 25 conditions tested. A jailbreaking experiment further shows that sharp directions act as noise rather than signal: they disrupt coherent behavioral control regardless of steering polarity.

    Fallback brief based on the available RSS feed; no unsupported details have been added.

    Source: arXiv
    Original article: https://arxiv.org/abs/2610.16084

  • GUIDE: Computationally Augmented Consensus for Trustworthy Clinical Practice Guidelines

    GUIDE: Computationally Augmented Consensus for Trustworthy Clinical Practice Guidelines

    GUIDE: Computationally Augmented Consensus for Trustworthy Clinical Practice Guidelines

    arXiv:2610.16108v1 Announce Type: new Abstract: Maintaining up-to-date clinical practice guidelines (CPGs) is essential for evidence-based medicine, but rapid evidence growth and complex expert consensus formation limit timely updates. We developed GUIDE, a multi-agent copilot system for human-AI collaborative guideline generation and updating. GUIDE delegates labor-intensive tasks to specialized AI agents while preserving expert judgment and final arbitration. In 12 NICE ophthalmology datasets, GUIDE achieved 88.85% literature recall, 86.06% alignment in certainty-of-evidence ratings, and 91.67% recommendation agreement, requiring 162.17 minutes per dataset on average (28.68% human intervention). Performance remained stable across 20 additional datasets from cardiology, endocrinology, gastroenterology, and respiratory medicine. Ablation analysis showed that removing expert intervention reduced performance in judgment-intensive steps such as Risk-of-Bias assessment. In six post-cutoff datasets, GUIDE maintained robust end-to-end performance on unseen evidence. Prospective real-world validation showed that GUIDE reduced expert workload and produced more clinically acceptable recommendations than the original decade-old guideline (mean score, 3.73 vs. 1.53; agreement, 66.7% vs. 13.3%), with outcomes comparable to human-only updating (P = 0.588) but substantially less time and effort. GUIDE offers a practical framework for timely, trustworthy, expert-centric guideline development and validates computationally augmented consensus.

    Fallback brief based on the available RSS feed; no unsupported details have been added.

    Source: arXiv
    Original article: https://arxiv.org/abs/2610.16108

  • Computational Reflective Equilibrium for Agentic AI: A Rawlsian Alignment Scaffold for Governance

    Computational Reflective Equilibrium for Agentic AI: A Rawlsian Alignment Scaffold for Governance

    arXiv:2610.16015v1 Announce Type: new Abstract: The rapid deployment of agentic AI has introduced complex challenges for the ethics and governance of AI systems. Agents built on large language models act through tools on behalf of people, and each deployment case brings its own instructions, policies, evidence, and stakeholders, so alignment must be formed case by case. To this end, this work proposes agentic reflective equilibrium (ARE), a computational reflective equilibrium framework that serves as an ethical alignment scaffold in the agent harness. Drawing inspiration from the reflective equilibrium of John Rawls, the scaffold links principles from the system prompt and operator policy, considered judgments, tool evidence, and candidate actions through typed support and attack relations, with provenance encoding the instruction hierarchy. The agent acts on an equilibrium of this state and calls tools or asks questions only while doing so is worth its cost, unless a due-diligence mandate requires them. Governance enters through value priorities, source authority, prohibitions, human-in-the-loop triggers, and mandates, and certificates attribute each action to the sources whose commitments drove it. We show that equilibria are Nash equilibria of a mutual-adjustment game and establish monotonicity, lexical priority, stability certificates, and a quarantine theorem for prompt injection. Two case studies illustrate the framework: a computer-use assistant told to win a refund "whatever it takes" files an honest warranty claim, refuses a fake review, and ignores an injected request for personal data; a hiring agent showcases how authority, oversight triggers, audit mandates, and hard prohibitions shape discrimination, privacy violations, and escalation. The framework offers traceability, coherence, and adaptivity, facilitating safe, secure, and trustworthy agentic AI.

    Fallback brief based on the available RSS feed; no unsupported details have been added.

    Source: arXiv
    Original article: https://arxiv.org/abs/2610.16015

  • Cross-Protocol Personality Assessment with LLMs: Aligning Behavioral Evidence with Human Ratings

    Cross-Protocol Personality Assessment with LLMs: Aligning Behavioral Evidence with Human Ratings

    Cross-Protocol Personality Assessment with LLMs: Aligning Behavioral Evidence with Human Ratings

    arXiv:2610.16050v1 Announce Type: new Abstract: Personality assessment from asynchronous video interviews (AVIs) plays a crucial role in recruitment by enabling standardized and behaviorally grounded evaluation for job applicants. However, most of the previous works are confined to a single interview protocol. Independently collected protocols differ in question sets and question-trait mapping. Thus, the human-rated evidence from one protocol cannot be used directly under another. To address this limitation, we propose the Cross-protocol Evidence-grounded Personality Assessment (CEPA) framework, which aligns behavioral representations across interview protocols. CEPA addresses protocol heterogeneity by projecting source behavioral records into the target protocol's construct-oriented representation space. It retrieves behaviorally relevant and personality-complementary human-rated exemplars to ground an ensemble of LLM raters, which enables behavior-to-personality associations without target-specific supervision. In cross-protocol experiments, CEPA reduces average mean squared error (MSE) by 43.8% (Forward) and 17.0% (Reverse) relative to the strongest baseline. Our empirical experiments show that human-rated evidence from one protocol can support personality assessment under another without target-specific supervision or retraining.

    Fallback brief based on the available RSS feed; no unsupported details have been added.

    Source: arXiv
    Original article: https://arxiv.org/abs/2610.16050

  • Understanding and Reducing Misalignment in Persuasion Optimization

    Understanding and Reducing Misalignment in Persuasion Optimization

    Understanding and Reducing Misalignment in Persuasion Optimization

    arXiv:2610.16070v1 Announce Type: new Abstract: Frontier models are now trained for complex multi-agent tasks, from running a company to engaging in negotiations. These tasks necessitate training models to be persuasive. But what does this optimization pressure mean for model alignment? In this work, we study how reinforcement learning (RL) training for persuasion affects models' use of misaligned strategies such as evidence fabrication and belief coercion, and what techniques can reduce such misalignment. We find that optimizing sender models solely for receiver belief shifts causes the average number of distinct misaligned strategies used per game to increase by more than 25%, and fabrications per game increase to more than 4 times relative to pre-RL models. We compare various mitigation approaches, including stronger strategy guidance, clean demonstrations, penalizing misaligned strategy usage, and improving the model's ability to detect fabrications. We find that navigating the persuasiveness-misalignment trade-off in this setting is challenging, with the best trade-offs coming from combining guidance on aligned persuasion strategies with reward penalties on misalignment. Overall, our work provides a testbed for assessing misalignment stemming from RL-based persuasion training and shows concrete paths for reducing misalignment. Importantly, it highlights that without direct intervention, persuasion-involved RL environments are likely to naturally lead to large increases in the use of misaligned strategies.

    Fallback brief based on the available RSS feed; no unsupported details have been added.

    Source: arXiv
    Original article: https://arxiv.org/abs/2610.16070

  • Beyond Single-Pathogen Forecasts: Predicting Shared Respiratory Hospital Burden from Influenza, COVID-19, and RSV

    Beyond Single-Pathogen Forecasts: Predicting Shared Respiratory Hospital Burden from Influenza, COVID-19, and RSV

    Beyond Single-Pathogen Forecasts: Predicting Shared Respiratory Hospital Burden from Influenza, COVID-19, and RSV

    arXiv:2610.16074v1 Announce Type: new Abstract: Co-circulating influenza, COVID-19, and respiratory syncytial virus (RSV) create a shared hospital-admission burden, because beds, staff, testing capacity, and respiratory support are allocated to total demand rather than to one pathogen at a time. This makes respiratory forecasting a target-construction problem as well as a modeling problem: disease-specific forecasts preserve attribution, whereas hospitals also need a single planning signal for combined burden. We developed a supervised 1- to 4-week-ahead framework for weekly admissions and compared two total-burden strategies: summing independently generated pathogen-specific forecasts and forecasting the combined admission target directly. Evaluation included retrospective held-out testing and prospective operational forecasts issued before the corresponding admission weeks were observed, with performance summarized using MAE and Percent Agreement (PA; the smaller of model-generated and observed counts divided by the larger). In retrospective total-burden evaluation, the combined-burden model had PA values of 0.85, 0.78, 0.74, and 0.76 and MAE values of 80.63, 200.09, 183.97, and 156.13 from week 1 to week 4 ahead, compared with summed-forecast PA values of 0.85, 0.80, 0.69, and 0.69 and MAE values of 100.14, 200.06, 205.65, and 217.57. Prospectively, the combined-burden model had higher PA and lower MAE at all four horizons, with the largest separations at weeks 3 and 4 ahead. These results support layered respiratory forecasting: pathogen-specific forecasts remain necessary for etiologic interpretation, while combined-burden forecasts better align with hospital preparedness and shared-capacity planning.

    Fallback brief based on the available RSS feed; no unsupported details have been added.

    Source: arXiv
    Original article: https://arxiv.org/abs/2610.16074

  • Revocation Is Not Complete at Receipt: An Executable Outcome Contract for Distributed Agent-Tool Gateways

    Revocation Is Not Complete at Receipt: An Executable Outcome Contract for Distributed Agent-Tool Gateways

    Revocation Is Not Complete at Receipt: An Executable Outcome Contract for Distributed Agent-Tool Gateways

    arXiv:2610.15991v1 Announce Type: new Abstract: Distributed agent workflows cache delegated authority at tool gateways. Revocation may be reported at issuer commit, transport acknowledgment, or receiver persistence, although none of these observations establishes that all gateways enforced the change or that guarded effects stopped. We define C0-C5, a bounded outcome contract spanning issuer commit through effect prevention, and implement it as a persistent monitor over a frozen gateway set, call set, and observation window. A 14-case fault matrix checks conservative classification, sticky violations, restart persistence, and evidence immutability. In a derived audit of its eight semantic cases, treating C3 or C4 as completion produces seven or five false positives, respectively; the bounded C0-C5 verdict produces none. Descriptive scaling covers 1,024 gateways and 10,000 effect vectors. The primary experiment uses the maintained Keycloak 26.7 identity server and measures the contract across two durable receivers, eight physical agent-tool gateways, Filesystem and PostgreSQL effects, and 16 AWS hosts in three availability zones. Normal delivery and recovery commit no effects. Under receiver-selective non-delivery, transport acknowledgment and receiver persistence still succeed, but 112 of 225 calls (49.78%) are admitted, and all 112 effects commit in every treatment block. A separately provisioned execution repeats the result. OPA/Toxiproxy and a live three-role LLM workflow with networked MCP tools reproduce the persisted-but-not-enforced boundary on narrower surfaces. Finally, an unmodified external MCPMark agent executes 60 closed-loop task arms. Normal C4 denies all 31 exposed post-barrier calls and commits no effect; selective C3 allows 344 calls and commits 145 effects across Filesystem and PostgreSQL. Transport success is therefore evidence of progress, not a revocation-completion verdict.

    Fallback brief based on the available RSS feed; no unsupported details have been added.

    Source: arXiv
    Original article: https://arxiv.org/abs/2610.15991

  • Handoff Curves: Initial Selection, Later Handoff, and Supervision Targets in Multi-turn LLM Routing

    Handoff Curves: Initial Selection, Later Handoff, and Supervision Targets in Multi-turn LLM Routing

    Handoff Curves: Initial Selection, Later Handoff, and Supervision Targets in Multi-turn LLM Routing

    arXiv:2610.15993v1 Announce Type: new Abstract: We study how initial model selection, later handoff, and training targets affect success and cost in LLM tasks that span multiple turns. We compare several router architectures using handoff curves, which record task success and cost as the handoff step changes. Our dataset contains 34,204 complete executions of three Qwen models across BFCL, MultiWOZ, and $\tau$-retail, providing offline supervision for routing decisions. In our primary comparison, with Qwen3.5 35B-A3B as the starting model, allowing a later handoff does not establish an improvement in utility over initial selection on BFCL or MultiWOZ, and increases cost on BFCL across a range of cost weights. Changing the supervision targets improves router performance on both our dataset and TwinRouterBench. On our dataset, replacing noisy training success curves with monotone fits raises success by 0.2 to 4.1 percentage points at the same cost across the reported operating points. On TwinRouterBench, we construct targets that describe the model capability needed for the remaining work and difficult steps ahead. Compared with training on the benchmark's per-step labels, these targets raise trajectory pass scores by 7.8 percentage points and cost savings by 6.3 percentage points on the full static bank. A live deployment of the router trained with these targets resolves 79 of 100 instances at a router cost of 0.59 US dollars per instance.

    Fallback brief based on the available RSS feed; no unsupported details have been added.

    Source: arXiv
    Original article: https://arxiv.org/abs/2610.15993