Skip to main content
Search

University of Illinois Urbana-Champaign

49 related articles

Subscribe to updates
  1. Phones and cloud split generative inference: MAGS bids instead of stampeding, cutting p99 latency 17.1%

    A generative query's cost is unknown until the answer is written, so devices reserve resources blind and many crowd one server at once. MAGS has each device forecast token count and generation entropy with a four-layer probe on its local model, then bid for cloud capacity against a broadcast congestion price, choosing its per-token privacy parameter in the same bid. Over ten seeds it cuts p99 latency 17.1%, energy per token 13.6% and raises throughput 20.7% against a reactive PPO baseline given identical observations; an eight-device, two-server testbed drops the cross-device correlation of offload decisions from 0.41 to 0.08.

  2. arXiv

    Agents must now identify the PDE themselves: RSI-PDEbench tests them on 1,001 cases, lifting mean pass rates by up to 181.9% across four models

    Recovering a partial differential equation from sampled solution data demands expert work in equation discovery, coefficient estimation and numerical solver configuration. RSI-PDEbench turns that workflow into a benchmark of 1,001 cases over 42 equation templates, split into noise-free, 50% Gaussian-noise and unseen-template-with-shifted-coefficient settings; the accompanying RSI-PDE agent shortlists candidate equations by residual, refines coefficients and solvers with relative feedback, and keeps improvements behind a validation gate. Across four frontier models its mean pass rate rises 106.5–181.9% over single-run baselines and 3.0–19.6% over native agent harnesses.

  3. arXiv

    A 27B model reads whole EEG recordings locally: ERIA tunes only its prompt policy, lifting protected-test report scores from 0.5052 to 0.6024

    Clinical EEG interpretation must cover technical quality, background and sleep states, interictal and ictal abnormalities across a whole recording, then synthesize a report, so event detection alone is not enough. ERIA has a locally deployed 27B language-model controller call deterministic signal analyses, learned clinical models and local knowledge retrieval, while controller weights, tools and safety constraints stay fixed and only the natural-language analysis policy is rewritten by GEPA using feedback from expert reports. On 200 paired clinical EEGs, the physician-aligned report score on the protected test set rose from 0.5052 to 0.6024, and the policy still performed on CerebraGloss-Bench and BrainBench Foundational Analysis.

  4. arXiv

    Suppressed misbehavior in language models can come back: PEARL trains from half-failed trajectories and holds under retraining

    Undesired behaviors in language models can re-emerge during later fine-tuning, and standard post-hoc suppression had not been compared on immediacy, durability and capability together. PEARL adds adversarial prefixes, continuations from intermediate states of cached misaligned trajectories, to GRPO's on-policy rollouts so the policy practices recovering from partly wrong states. Across Qwen3-4B and GPT-OSS-20B and two organism types, PEARL suppresses strongly while preserving task accuracy, with the clearest gains on the broad-trigger organism and GPT-OSS-20B; on Qwen3-4B with the narrow-trigger organism, SFT is more durable under heavy targeted retraining.

  5. arXiv

    Agents learn to think in latent space: HybridAgent gains 10.4% on average across 11 benchmarks while cutting tokens by up to 54.7%

    HybridAgent lets a single agent move back and forth between continuous latent reasoning and text interaction within one generation, so part of its thinking leaves token-by-token decoding while tool use stays intact. Text agents previously had to write every step as tokens, while latent-reasoning models lacked native tool access and were hard to inspect. Across 11 benchmarks in mathematics, science, medicine, search and agentic reasoning at 4B to 14B scale, it reports a 10.4% average gain over frontier text and latent agents, with 35.5%–54.7% fewer tokens and 1.8–2.6 times faster inference.

  6. arXiv

    Mixed-quality judge pools can still be aggregated: AGORA learns trust weights with item-response theory and holds its edge down to a few hundred items

    LLM judges are a common substitute for costly human evaluation, and aggregating several judges is the standard remedy for any single judge's bias, but judge pools mix very different reliabilities while the human-labeled sets used to validate them hold a few hundred items or fewer. AGORA places every item on one latent quality scale and describes each judge by a sensitivity parameter and ordered rating thresholds, so judge reliability is learned jointly from all items without human labels. Across three benchmarks, AGORA matches or exceeds Dawid-Skene on large evaluation sets, and its advantage widens as the set shrinks toward a few hundred items.

  7. arXiv

    Agent memory stops only looking back: Pro-Memory splits future intentions from the moment to act

    Most memory systems for large language model agents only store and retrieve past information, while proactive agents also need to hold future intentions and realize them when the right moment arrives. Pro-Memory separates keeping a future intention from deciding when and how to realize it: pending objectives stay linked to their supporting evidence, new observations are checked against the original goal and activation conditions, and contributions are coordinated with the agent's ongoing actions. On two benchmarks covering delayed-intention tasks and open-ended proactive assistance, proactive task performance improves consistently over representative memory approaches across multiple LLM backbones while unnecessary interventions are limited.

  8. Reward the search, not just the answer: process supervision lifts retrieval recall and holds up out of domain

    Search agents for multi-hop information seeking are trained on step-level judgments of each search action instead of only on final-answer correctness. RAG-Gym casts search as a Markov decision process and compares architecture, parameter optimization and action evaluation, combining a reasoning-reflection architecture, preference optimization and critic-guided inference into Re2Search++. Trained on HotpotQA, it beats outcome-supervised baselines on the unseen Bamboogle benchmark with higher retrieval recall at comparable or fewer search steps, and a critic trained on Llama-3.1-8B raises GPT-4o-mini MedQA accuracy.

  9. arXiv

    Private vector search stops scaling with database size: HNSecW brings online ANN queries to logarithmic time while holding recall at billion scale

    In the symmetric-privacy setting where both the query and the database must stay hidden, HNSecW turns HNSW graph-index approximate nearest neighbor search into a fully data-independent procedure that runs under secure multi-party computation, giving single-query online communication and local computation logarithmic complexity. Earlier protocols of this kind mostly used cluster-based pipelines whose online communication grows linearly with database size. On million- to billion-scale benchmarks, HNSecW keeps recall comparable to plaintext HNSW and reaches up to orders-of-magnitude end-to-end speedup over 2PC PANTHER on a wide-area network.

  10. aclanthology.org

    Failed proofs get a second life: a 7B pipeline lifts Isabelle success on miniF2F to 73.8%

    HybridProver joins whole-proof synthesis and stepwise tactic generation in one pipeline: a whole-proof model drafts candidate proofs, and candidates that fail Isabelle's checker are abstracted into proof sketches that keep the high-level structure, then filled subgoal by subgoal by a tactic model and Sledgehammer. On the 244 test problems of the Isabelle version of miniF2F, the pipeline reaches a 73.8% success rate, above the previous best Isabelle result of 61.9%. Both 7B-scale models are trained with supervised fine-tuning and reinforcement learning rewarded by Isabelle verification, indicating that lightweight models can generate Isabelle/HOL proofs.