Daily Papers

Effective reward design is a central challenge in Reinforcement Learning (RL) for code generation. Mainstream pass/fail outcome rewards enforce functional correctness via executing unit tests, but the resulting sparsity limits potential performance gains. While recent work has explored external Reward Models (RM) to generate richer, continuous rewards, the learned RMs suffer from reward misalignment and prohibitive computational cost. In this paper, we introduce VeRPO (Verifiable Dense Reward Policy Optimization), a novel RL framework for code generation that synthesizes robust and dense rewards fully grounded in verifiable execution feedback. The core idea of VeRPO is constructing dense rewards from weighted partial success: by dynamically estimating the difficulty weight of each unit test based on the execution statistics during training, a dense reward is derived from the sum of weights of the passed unit tests. To solidify the consistency between partial success and end-to-end functional correctness, VeRPO further integrates the dense signal with global execution outcomes, establishing a robust and dense reward paradigm relying solely on verifiable execution feedback. Extensive experiments across diverse benchmarks and settings demonstrate that VeRPO consistently outperforms outcome-driven and RM-based baselines, achieving up to +8.83\% gain in pass@1 with negligible time cost (< 0.02\%) and zero GPU memory overhead.

Verifiable rewards improve language models through reliable task-level feedback, but methods based on Group Relative Policy Optimization (GRPO) apply a sequence-level advantage uniformly across all tokens. This coarse credit assignment reinforces or penalizes entire responses without identifying which local decisions to preserve, reinforce, or revise. Conversely, evidence-conditioned self-distillation provides denser token-level supervision, yet teacher imitation can transfer stylistic artifacts and miscalibrated confidence that destabilize training when misaligned with task success. We introduce VERPO, which converts evidence-conditioned guidance into reward-aligned token-level credit assignment while retaining the outcome objective. VERPO decomposes teacher guidance into an evidence-free reference term and signed, evidence-induced corrections at each token. A stopped controller combines selective acceptance, token-wise localization, and cost-aware scaling by balancing alignment with the local GRPO update direction against Fisher movement cost. Furthermore, we introduce Fisher Evidence Contrast (FEC), which attenuates nuisance shifts along an estimated evidence-presence direction through a regularized projection. Across five scientific reasoning and tool-use tasks, VERPO prevents optimization collapse and consistently achieves the highest multi-task average across model backbones, yielding marked improvements particularly on smaller models over strong baselines. Qualitative diagnostics confirm that token acceptance selectively targets reasoning bottlenecks consistent with local reward alignment and Fisher movement cost.

We present a search for the diffuse extremely-high-energy neutrino flux using 12.6 years of IceCube data. The non-observation of neutrinos with energies well above 10 , PeV constrains the all-flavor neutrino flux at 10^{18} , eV to a level of E^2 Phi_{nu_e + nu_mu + nu_tau} simeq 10^{-8} , GeV , cm^{-2} , s^{-1} , sr^{-1}, the most stringent limit to date. Using this data, we constrain the proton fraction of ultra-high-energy cosmic rays (UHECRs) above simeq 30 , EeV to be lesssim 70,% (at 90,% CL) if the cosmological evolution of the sources is comparable to or stronger than the star formation rate. This result complements direct air-shower measurements by being insensitive to uncertainties associated with hadronic interaction models. It is the first such result to disfavor the ``proton-only" hypothesis for UHECRs using neutrino data.

We report three searches for high energy neutrino emission from astrophysical objects using data recorded with IceCube between 2011 and 2020. Improvements over previous work include new neutrino reconstruction and data calibration methods. In one search, the positions of 110 a priori selected gamma-ray sources were analyzed individually for a possible surplus of neutrinos over atmospheric and cosmic background expectations. We found an excess of 79_{-20}^{+22} neutrinos associated with the nearby active galaxy NGC 1068 at a significance of 4.2,σ. The excess, which is spatially consistent with the direction of the strongest clustering of neutrinos in the Northern Sky, is interpreted as direct evidence of TeV neutrino emission from a nearby active galaxy. The inferred flux exceeds the potential TeV gamma-ray flux by at least one order of magnitude.

IceCube has performed several all-sky searches for point-like neutrino sources using track-like events, including a recent time-integrated analysis using 10 years of IceCube data. This paper accompanies the public data release of these neutrino candidates detected by IceCube between April 6, 2008 and July 8, 2018. The selection includes through-going tracks, primarily due to muon neutrino candidates, that reach the detector from all directions, as well as neutrino track events that start within the instrumented volume. An updated selection and reconstruction for data taken after April 2012 slightly improves the sensitivity of the sample. While more than 80% of the sample overlaps between the old and new versions, differing events can lead to changes relative to the previous 7 year event selection. An a posteriori estimate of the significance of the 2014-2015 TXS flare is reported with an explanation of observed discrepancies with previous results. This public data release, which includes 10 years of data and binned detector response functions for muon neutrino signal events, shows improved sensitivity in generic time-integrated point source analyses and should be preferred over previous releases.