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

Content Depth Matters in Short-Video Recommendation: Rethinking the Attention Economy

Liwei Deng, Jing Jiang, Zhiwei Li, Yang Wang, Guodong Long

Driven by the attention economy, short-video Recommender Systems (RSs) are primarily optimized to maximize user engagement by promoting videos that capture attention within seconds. These systems inherently favor shallow-content videos that are effective at attracting immediate attention. However, growing evidence suggests that prolonged exposure to such content may negatively affect users' cognitive engagement and mental well-being, raising concerns about the long-term societal impact of the short-video platform. To tackle this challenge, this paper introduces a new metric, the \textbf{Content Depth Score (CDS)}, to quantify the content depth of short videos. CDS measures the extent to which a video is expected to stimulate higher-order cognitive processes, using a seven-level scale grounded in established theories of cognitive psychology and learning. As an initial step toward this vision, we present \textbf{SCOPE-Bench}, the first benchmark for content-depth evaluation in short-video recommendation. Built upon a large-scale open-source short-video dataset, SCOPE-Bench provides CDS annotations for 150K videos, enabling systematic evaluation of RSs from a cognitive-content perspective. Leveraging SCOPE-Bench, we evaluate 13 representative RSs and reveal a consistent preference for shallow-content videos. Moreover, we find that these algorithms recommending cognitively deep content are only marginally better than random selection, highlighting a previously overlooked limitation of existing recommendation objectives. Our code and datasets are available at https://liweidengdavid.github.io/SCOPE-Bench/.

arXiv

Implementing Computational Law in Wolfram Language for the Governance of Artificial Intelligence

James K. Wiles

How do we govern AI systems whose reasoning we cannot fully inspect? Governance does not require understanding a system's reasoning. It requires stating what the system is obliged, permitted, and forbidden to do, and checking whether it complied. I present an implementation of Reified Input/Output Logic, the formalism behind the DAPRECO knowledge base, in Wolfram Language: the core I/O axioms, obligations, permissions, constitutive norms, reified eventualities, and temporal operators. I then test whether GPT-4 can translate English legal statements into the formalism, and report the failures: hallucinated functions, omitted temporal scope, deviation from the formalism, and (in the worst cases) code that runs, reads plausibly, but silently encodes the wrong norm. A case study, an AI guard dog operating under a computational contract, shows how formalized rules can extend from a contract directly into the operational code of an embodied agent, producing symbolic, auditable justifications for its behaviour. I argue that computational law can be used as a governance tool and that a desirable goal would be to formalize the law that can and ought to be programmatically executable.

arXiv

HELIX: Model-Harness Co-evolution for Recursive Self-Improvement

Tianyu Fan, Chao Huang

Scaling agent capability has largely focused on improving the model, yet an interactive agent acts through a runtime harness that mediates context, tools, control flow, and stopping. The harness shapes both what a model can accomplish and the trajectories from which it learns. This coupling motivates model-harness co-evolution for recursive self-improvement: build harnesses for a fixed model, update the model from verified sibling trajectories, and rebuild the harnesses as model capabilities change. Realizing this loop requires a controlled way to evolve harnesses while preserving intervention identity and effect. We present HELIX, a source-traceable substrate for harness evolution. HELIX decomposes agent systems into typed ports, reusable atoms, recipes, product shells, and runtime policies. It makes interventions explicit and auditable while retaining trajectories, test outcomes, and provenance. Harness evolution thus serves two linked roles: improving fixed-model execution and producing matched successes, regressions, near misses, and alternative solutions as data for subsequent model improvement. We evaluate HELIX in one evolution round on code repair. A 65-candidate portfolio discovers a fixed harness that improves task coverage by 4.0% over Pi, while the full portfolio exposes up to 58.0% more verified coverage through complementary sibling behavior. Selected candidates are assessed with repeated runs and the SWE-bench evaluator. A 200-slot sibling slice yields 438 verified SFT, critic, filter, and preference records. These results show how harness, model, and data form a feedback system: harness evolution expands current capability and creates learning signal for the next model; model updates motivate the next round of harness evolution. HELIX provides an auditable interface for studying this recursive process. Code is available at https://github.com/HKUDS/HELIX.

arXiv

Musical Mirrors: The LLM as Sounding Board in Songwriting

Xiao Xiao

This paper examines a use of AI in creative practice as an interpretive sounding board for human-generated material, rather than the more familiar pattern of AI generation followed by human curation. Through the lens of resonance as theorized by Hartmut Rosa, I present a first-person case study of songwriting from July 2025 to March 2026, drawing on 16 original pieces in English, French, and other languages along with piano solos. I describe a configuration in which resonance is not located between user and model, but in the author's deepening contact with their own material, mediated through the model. This kind of resonance was supported rather than inhibited by AI when sounding-board behavior was cultivated through sustained calibration by the user. Two failure modes appeared when calibration was absent: sycophantic drift and magical overinterpretation. This account suggests both the potential and the risks of AI as an interpretive partner in creative practice.

arXiv

When Personal Memory Has No Single Answer: Evaluating LLM Agents under Irreducible Conflict

lu Yang, Shusheng Xu, Zhuoran Li, Tongkai Yang, Longbo Huang

LLM agents increasingly maintain personal memory across sessions, but it can conflict. Preferences depend on context, behavior evolves, and sources can conflict. When a query lacks context, time, or source authority to interpret conflict, treating one memory as definitive converts unresolved conflict into an unjustified, overconfident action. Existing benchmarks recover one answer from conflicting evidence, overlooking whether agents recognize underdetermination, preserve alternatives, seek missing information, and choose appropriate actions. We introduce \underline{T}esting \underline{A}gents' \underline{N}avigation of \underline{G}enuine, \underline{L}atent, and \underline{E}ntangled Memory Conflicts (\textsc{TANGLE}), a benchmark for genuinely unresolvable memory conflicts. It comprises 541 instances across 40 personas and three types: Context-Partitioned Conflict (CPC), Behavior-Oscillation Conflict (BOC), and Source-Contradiction Conflict (SCC). We evaluate two tracks---an oracle track with curated memory and a pipeline track that extracts memory from multi-session dialogues---on five dimensions: conflict perception, causal reasoning, confidence calibration, clarification seeking, and memory faithfulness. Experiments reveal pipeline challenges. With curated memory, models recognize conflicts more reliably than they calibrate actions or seek targeted clarification. With end-to-end pipeline memory, extraction fails to preserve conflict-bearing relations needed for downstream reasoning. Policy comparisons show fixed rules are insufficient when actions must reflect conflict. These findings motivate Conflict-Aware Action Policy (CAAP), which adapts actions to each conflict using available evidence. \textsc{TANGLE} frames conflict handling as recognizing underdetermination, retaining conflicting evidence, and acting without forcing a definitive answer.

arXiv

CipherSight: Robust Website Fingerprinting via Record-Resource Semantic Supervision under Distribution Shifts

Runhan Song, QIQI LIU, Chuanzhou Pan, Zhenquan Ding, Youquan Xian, Chongru Fan, Lei Cui, Wei Wang, Zhiyu Hao

HTTPS website fingerprinting (WF) aims to identify visited websites from metadata observable in encrypted traffic. However, real-world deployments introduce a significant out-of-distribution (OOD) problem caused by temporal and geographic changes, while previously unseen websites are common in open-world scenarios. Existing methods primarily learn from raw TCP packet sequences and struggle to capture stable and generalizable website representations, resulting in performance degradation under practical conditions. We propose CipherSight, a TLS-record-based hierarchical framework for robust HTTPS WF. Unlike existing approaches that rely on TCP packet sequences and are sensitive to transport-layer artifacts, CipherSight learns website representations from TLS records by jointly encoding multiple record-level attributes. It introduces a hierarchical architecture that captures both intra-flow dependencies among TLS records and inter-flow interactions across concurrent flows, enabling the model to exploit structural patterns in HTTPS traffic. Besides, to learn robust representations, CipherSight employs a masked record modeling (MRM) task to capture contextual traffic semantics and leverages fine-grained record-resource annotations as privileged supervision through structure-aware objectives and semantic distillation. Experiments show that CipherSight achieves 95.41% accuracy across more than 2,000 website classes in the closed-world setting and maintains over 90% accuracy under both temporal and geographic drift, consistently outperforming all evaluated baselines.

arXiv

MemoryLake on MemoryArena: A Matched Study of Agent Memory Backends

Chaoqun Zhan, Qiang Zhou, Guannan Li, Zhenqiang Huang, Qianjin Wang

Most agent-memory benchmarks test post-hoc recall, whereas MemoryArena evaluates whether memory supports interdependent, multi-session task completion. We compare MemoryLake, a structured multi-track memory backend, with Mem0, text-embedding-3-small vector RAG, and a long-context control across all five MemoryArena domains. The systems share the same agent framework, requested gpt-5-mini model alias, task samples, and scoring code; the memory integration is the intentionally changed component. Because each backend bundles write, retrieval, consolidation, budgeting, and prompt-assembly choices, the study is a matched system-level comparison, not a representation-only ablation or a cost-matched experiment. On the shared evaluation sets, MemoryLake has the highest observed success rate (SR) in mathematics (9/40), physics (12/20), and progressive retrieval (4/20). Every system has zero SR in travel planning, and web shopping yields a single bundle-level success (long context, 1/150); MemoryLake ranks third on both the travel soft process score and shopping step match. Following MemoryArena's suite-level convention, a post-hoc equal-weight average over the five SRs is 20.5% for MemoryLake versus 13.6% for the best comparator. These are point estimates: sample sizes are modest, confidence intervals overlap, and we do not report paired significance tests. A separate MemoryLake-only run over all 221 progressive queries yields a failure-counted SR of 26.7% (59/221) and is not a baseline comparison. The results support a workload-dependent view of memory backends and an observed lead among the four evaluated systems on the shared sets; they do not establish benchmark-wide state of the art or a causal advantage of representation structure.

arXiv

Engineering Reliable Coding Agents: Evaluating and Operating the System Around the Model

Stephanie Jarmak

AI coding agents are commonly evaluated as models but deployed as systems. Their reliability depends not only on model capability, but on the harness, execution state, retrieval, memory and state management, permissions, review interfaces, and resource allocation. This monograph examines those boundaries and develops a framework for evaluating and operating coding agents reliably. It synthesizes 164 scholarly works, 100 practitioner records, 29 benchmark records, and 17 author-system case records through a structured multivocal review, targeted update audits, software-engineering coverage analysis, and distributed-systems evidence synthesis. Across this evidence, many apparent model failures originate elsewhere in the system, while improvements at one layer often fail to propagate to end-to-end outcomes. Evaluation and operation are treated as a dependency chain in which weaknesses in task construction, execution environments, retrieval, state management, verification, or observability can invalidate downstream conclusions. The monograph contributes a versioned catalog of 206 reliability records: 193 gated practices, including 56 developed in depth, plus 13 research leads; an evidence ledger; a framework for dependency and repair asymmetry across the agent lifecycle; measurements and failure cases from operated agent systems; runnable evaluation and reliability protocols; and five reusable agent skills with evidence maps. Together, these provide a system-level methodology for distinguishing model capability from infrastructure effects, designing defensible evaluations, and building systems that recover safely when components fail. The review is structured rather than exhaustive, evidence strength varies by topic, and results depend on workload and configuration. The methods record which search lanes were executed, which remain unexecuted, and limits on evidence-grading claims.

arXiv

Joint Optimization of Memory and Computing Frequency for Energy-Efficient DNN Inference

Yunchu Han, Zhaojun Nan, Sheng Zhou, Zhisheng Niu

Deep neural network (DNN) inference on mobile devices often incurs high latency and energy consumption due to limited computing and memory resources. To enable energy-efficient DNN inference, most existing studies focus on dynamic voltage and frequency scaling (DVFS) for adjusting the computing frequency, while the impact of memory frequency on the inference performance has been greatly overlooked. In this paper, we consider the impact of memory frequency and computing frequency on DNN inference time, and jointly optimize these two frequencies together with communication resources for energy-efficient DNN inference. Based on a realistic inference time model, we formulate an optimization problem to minimize the energy consumption of all mobile devices under the deadline constraint. For local inference, we derive a near-optimal closed-form solution via convex optimization, while an optimal closed-form solution for transmission power is obtained for edge inference with the given bandwidth. Furthermore, we propose a low-complexity heuristic algorithm to effectively solve the overall problem with polynomial time complexity. Simulation results based on measured data show that the proposed near-optimal solution for local inference can achieve optimal performance under strict deadline constraints, with a performance gap of up to 2.5% compared with the optimal solution. Meanwhile, our proposed algorithm significantly reduces the energy consumption of devices by up to 10.4% compared to other methods.

arXiv

Integrating spectral and morphological plant features with decision-tree models for early-season cotton biomass and nitrogen status estimation from multi-year UAV data

Vaishali Swaminathan, Nithya Rajan, J Alex Thomasson, Amrit Shrestha, Karem Meza Capcha, Robert Hardin, Pramod Pokhrel

Precision nitrogen (N) management (PNM) for cotton requires in-season monitoring of crop growth parameters and N status indicators to decide fertilizer timing, placement, and application rates for optimal canopy development and yield. This study developed remote sensing and machine learning-based methods to estimate cotton dry biomass weight (DBW), plant N uptake (PNU), plant N concentration (PNC), critical N dilution (Nc), and nitrogen nutrition index (NNI) to support PNM. To achieve this, a three-year field-based N-management study was conducted and unmanned aerial vehicle (UAV)-based multispectral images were acquired between early vegetative growth and flowering stages, critical for fertilizer applications. Spatiotemporally consistent spectral and morphological plant features, including plant height (PH) and fractional canopy cover (FCC), provided reliable model training inputs. DBW, PNU, and PNC estimates from simple regression using vegetation indices (VIs), multiple linear regression (MLR) combining VIs, PH, and FCC, and decision-tree models, random forest regression (RFR) and extreme gradient boosting (XGB), combining spectral reflectance, PH, and FCC were evaluated using trial-held-out (THO) and leave-one-year-out (LOYO) validation methods. The best validation accuracies were from RFRTHO (R2 = 0.88 and MAPE = 23.14% for DBW; R2 = 0.84 and MAPE = 20.61% for PNU; R2 = 0.85 and MAPE = 7.82% for PNC) and XGBTHO (R2 = 0.87 and MAPE = 21.91% for DBW; R2 = 0.81 and MAPE = 21.40% for PNU; R2 = 0.86 and MAPE = 7.66% for PNC). Nc was calculated from model estimated DBW and PNC for high-yielding, medium-to-tall cotton varieties grown in the Texas Coastal Plains and validated using ground-truth biomass measurements. NNI derived from XGBTHO outputs performed marginally better than NNI from RFRTHO in identifying N-deficient plots and multi-level N-stress categorization.

arXiv

Sampling the Schwinger Model with Gauge-Equivariant Diffusion

Octavio Vega, Aida X. El-Khadra

We present a first study of a diffusion-based approach to accelerated sampling of the $N_f = 2$ lattice Schwinger model. Our work is inspired by recent and growing successes in developing such generative models for ensemble generation in LFT to overcome the well-known critical slowing down problem. We train a U(1)-equivariant score-based generative model to sample gauge link configurations from the marginal Schwinger model. By computing model likelihoods, we obtain unbiased estimates for observables that closely match those produced by MCMC simulations. We also demonstrate improvement over HMC as measured qualitatively by a reduction in topological freezing near critical parameters.

arXiv

Computationally tractable robust differentially private mean estimation

Kelly Ramsay

We develop a new, differentially private mean estimator called the balloon mean. The main features of the balloon mean are that it is computationally tractable and enjoys robustness to outlying observations. It is based on an iterative clipping procedure over expanding Mahalanobis balls, or ``balloons.'' The method satisfies zero-concentrated differential privacy and depends on a small number of interpretable tuning parameters. We provide theoretical guarantees under heavy-tailed and contaminated elliptical models, characterizing its statistical performance and robustness to outliers. Extensive simulations demonstrate that the balloon mean is robust to heavy-tailed and contaminated data, and outperforms existing differentially private mean estimators in contaminated settings.

arXiv

Provably Efficient Personalized Multi-Objective Bandits with Proactive Conversational Queries

Linfeng Cao, Ming Shi, Ness B. Shroff

Personalized decision-making in multi-objective bandits requires learning user-specific trade-offs among competing objectives. Since arm utility depends on both unknown rewards and unknown preferences, existing methods infer preferences only from utility feedback, entangling preference learning with reward exploration. In practice, however, users often reveal their priorities through proactive conversational queries (e.g., "cheap and clean hotel"), yet this structured signal is not leveraged. We formalize a proactive query-based framework in which user queries provide structured preference signals. Modeling these signals via a Plackett-Luce subset choice model, we show that query-only learning is insufficient due to a fundamental shift-invariance barrier. To resolve this, we introduce MO-PQUCB, a hybrid algorithm that integrates query-based preference anchoring with bandit feedback through shift-invariant regularization and dual-exploration UCB. We prove that proactive queries accelerate preference estimation and yield improved regret scaling over prior preference-aware MO-MAB methods. Under corrupted queries, we further characterize statistical limits and design a robust estimator achieving near-optimal performance when the corruption is sparse. Experiments validate both theoretical and practical gains.

arXiv

Discovering Efficient and Explainable Communication Topologies for LLM-based Multi-Agent Systems via Causal Inference

Junzhi Li, Peng He, Qirui Ji, Wei Wang, Lixiang Liu, Chuxiong Sun

The performance of large language model (LLM)-based multi-agent systems (MAS) largely depends on effective communication topologies. Existing topology generation methods, however, typically learn communication topologies through black-box optimization driven solely by task-level rewards. While effective, such optimization provides little insight into why particular communication edges are selected, making it difficult to identify the critical communication subgraphs responsible for successful collaboration. To address this limitation, we propose E2-Explainer, a model-agnostic framework for providing interpretable explanations of communication topologies produced by arbitrary topology generators. Specifically, we formulate topology explanation as a causal attribution problem that identifies compact communication subgraphs supported by edge-level evidence of task preservation. We obtain this evidence with a Granger-style objective that measures how masking each communication channel changes the task outcome and the stability of the final response. The resulting budgeted subgraphs are then distilled into an amortized explainer, enabling efficient post-hoc explanation without repeated edge-level evaluations at deployment. Extensive experiments on multiple reasoning and coding benchmarks demonstrate that E2-Explainer identifies critical communication subgraphs that preserve successful collaboration. These subgraphs can also be executed directly to prune redundant communication edges, substantially reducing communication costs while maintaining competitive task performance.

arXiv

The Energy Blind Spot: NVIDIA's Flagship Edge AI Hardware Cannot Support Process-Level Energy Attribution

Deepak Panigrahy, Aakash Tyagi

Agentic AI workloads - where a single user goal triggers multi-step orchestration, tool calls, retries, and failure recovery - are being targeted for edge deployment, with NVIDIA, Dell, HP, ASUS, MSI, Acer, and Gigabyte all shipping GB10-based desktop AI systems in 2026. Prior work shows orchestration structure dominates agentic energy cost and CPU-side processing accounts for up to 44% of total dynamic energy. We report a systematic energy-observability audit of the ASUS Ascent GX10 (GB10 SoC) and find that the platform exposes no CPU energy counter, no INA power-rail monitor, no IPMI/BMC, and no SCMI powercap protocol through any supported software interface. The only on-device energy telemetry is instantaneous GPU power via NVML. We further discover that the MediaTek firmware already computes per-rail energy internally via an undocumented ACPI interface (SPBM), but NVIDIA states there are "no plans to expose CPU rail information." On-device per-process energy attribution - as performed on x86 via RAPL - is therefore not reproducible on this platform through supported interfaces. We formalize a hardware requirements specification for energy-attributed AI, propose an interim calibration bridge for per-domain energy decomposition - confirmed on the Acer Veriton GN100 where CPU energy accumulators are live - and identify a standards-track path via SCMI powercap. Our findings motivate the low-carbon computing community to demand energy observability as a first-class hardware requirement.

arXiv

Predictive Memory Localization: Forecasting Selective Intervention Paths from Internal Signals

Jinhao Jing, Tian Zeyu, Lucas Qingyang Fang, Zhisheng Chen, Shuang Chen, Yuhao Luo, Qiannian Zhao

Activation steering turns localized representations into control directions, but localization alone does not reveal whether a direction has a selective operating regime. We introduce Predictive Memory Localization (PML), which treats the measured-grid intervention path as the predictive object of memory localization. PML separates random-calibrated target movement from semantic-neighbor and capability damage, and compares static localization and supervised geometry with a strength-disjoint low-dose causal response. Our frozen study covers 3,000 records from nine datasets and fourteen domains, yielding 30,000 distinct record-direction-layer paths and 210,000 distinct path-strength evaluations. At layer 7, the geometry-derived RFM/AGOP direction reaches 13.1% target-any and 12.3% clean-any, exceeding random by 3.6 and 3.4 percentage points under a record-paired bootstrap. Across record-, dataset-, and domain-grouped splits, responses at $|α|=0.1$ are the strongest signal for outcomes at disjoint strengths $|α|\in\{0.25,0.5\}$. On held-out records, a predictor-driven selector chooses a coefficient or abstains, improves utility and reduces semantic-neighbor damage relative to a train-tuned fixed-strength policy, and avoids most evaluations in a dense scan. Across three residual-norm-matched base models, learned directions retain selective-path gains and low-dose responses yield 0.801-0.828 record-held-out macro AUROC. PML therefore turns memory localization into a falsifiable forecast of margin-level selective outcomes and a risk-aware intervention decision.

arXiv

SynAct: A Reasoning-Acting Large Language Model Agent for Adaptive Synthesis Optimization

Fangzhou Liu, Peiyi Han, Jiawei Liu, Yuan Pu, Zhuolun He, Rongliang Fu, Tsung-Yi Ho, Bei Yu

Logic synthesis transforms RTL designs into gate-level netlists, where PPA results are highly sensitive to the choice of optimization commands, making synthesis tuning both high-dimensional and expensive. Previous approaches fall into two categories: automated methods, which perform black-box search over fixed action spaces with limited decision-level interpretability, and LLM-based methods, which typically generate static scripts upfront and cannot adapt to evolving circuit states. We present SynAct, an adaptive closed-loop LLM reasoning--acting agent that iteratively diagnoses live synthesis reports and reasons over the current circuit state, retrieved tool knowledge, and historical optimization experience to issue targeted commands. SynAct focuses on improving timing, particularly worst negative slack (WNS), while maintaining balanced area and power trade-offs. Experiments on a commercial synthesis tool across 14 designs show that SynAct reduces average WNS to 27% of that from bootstrap synthesis.

arXiv

Can Large Language Models Reason about Event-Time Stream-Processing Semantics?

Zhuoxi Wang, Shibo Zheng, Haoyu Zhang

Streaming systems increasingly hand work to large language models (LLMs): writing pipelines, triaging alerts, reading logs. All of it assumes the model knows how event-time stream processing behaves, and we test that assumption directly. StreamReason-Bench asks a model to stand in for an event-time stream processor. Given a windowed query and a stream of out-of-order events, it reports which windows fire, with their aggregates, and which events are dropped as late. The answer key comes from a small reference implementation of Dataflow-model semantics, so we can grade exactly, and with a partial-credit row-F1, without running an engine. On 600 generated items covering tumbling, hopping, session, and processing-time windows, the models do poorly on event time. When told to answer directly, no model that actually follows the instruction clears 34% exact match; chain-of-thought (CoT) roughly doubles that for several of them (GPT-4o goes from 0.34 to 0.48), and only one frontier model that reasons by default comes near solving the set (0.85). A processing-time control, with no watermarks and nothing late, is almost solved by every capable model. The gap points to event-time and late-data handling, not windowing or arithmetic, as the hard part. Sorting errors by window type tells the same story: late-data mistakes dominate the event-time windows and vanish on the control, while session windows mostly fail on where the session boundaries fall.

arXiv

Long-Horizon AI Research for Grothendieck Constant: A Case Study in Human-AI Mathematical Collaboration

Alan Li, Rahul Saha, Anton Xue, Swarat Chaudhuri, Adam Klivans, Pravesh K Kothari, Raghu Meka

AI agents are increasingly used in mathematics research, but it is often unclear how to use them effectively. Towards this, we present an extensive case study of how AI was used to improve bounds on the Grothendieck constant $K_G$, which captures the hardness between combinatorial problems and their continuous relaxations. Specifically, while the precise value of $K_G$ is not known, we recently tightened the best known bounds to \[ \frac{6π}{11} \;\le\; K_G \;\le\; \fracπ{2\log(1+\sqrt2)} - 10^{-4}. \] Crucially, these improvements were achieved using an AI research system that could arrive at insights deemed novel by domain experts. We give a detailed discussion of our experience using AI for mathematics research, particularly touching upon its strengths and weaknesses, as well as our experience with creating ideal conditions for AI to arrive at breakthrough insights.

arXiv

SKILLER: Language-Level Reinforcement Learning for Reusable Skill Extraction in Small Language Models

Chenhao Dang, Siyuan Xiong, Conghui He, Weijia Li

Agent skills represent a standardized format for packaging procedural knowledge and domain expertise, serving within agent harness systems as an essential mechanism to continually constrain a language model's behavior space for repeatable, high-quality task execution. However, because strong closed-source models entail high inference costs, current popular agent harnesses, such as Codex and OpenClaw, remain prohibitively expensive when deploying these skills to accomplish real-world tasks. The rapid capability enhancement of open-source models deployable on consumer-grade GPUs presents a compelling opportunity to drastically reduce these costs by leveraging skill-based behavioral constraints. Nevertheless, automatically generating effective skills tailored specifically for such compact models remains a significant practical challenge. To address this, we propose SKILLER, a natural-language-driven reinforcement learning framework designed to automatically generate executor-specific skills for small models, which employs a strong model as the actor and critic, treats the small-model agent system as the environment, and propagates all reinforcement learning signals entirely via natural language. Extensive experimental evaluations across five relevant benchmarks using Qwen3.5-9B and Qwen3.5-4B demonstrate that SKILLER outperforms three open-source and one closed-source skill generation or evolution methods, achieving absolute gains ranging from 4.3 to 20.4 percentage points for the 9B model and 1.8 to 13.3 points for the 4B model, while remarkably matching the performance of strong closed-source models on single-skill tasks in SkillsBench. The project is available at https://github.com/DANG-ai/SKILLER.

Keep browsing

More papers from top AI conferences

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